CTNF 18/477,574 CTNF 93954 DETAILED ACTION 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. This action is responsive to the original application filed on 9/29/2023. Acknowledgment is made with respect to a claim of priority to Japanese Application JP2022-212372 filed on 12/28/2022. Specification 06-11 AIA The title of the invention is not descriptive. A new title is required that is clearly indicative of the invention to which the claims are directed. 06-11-01 AIA The following title is suggested: METHOD, APPARATUS, AND COMPUTER-READABLE RECORDING MEDIUM FOR PRUNING NEURAL NETWORKS Claim Rejections - 35 USC § 112 07-30-02 AIA The following is a quotation of 35 U.S.C. 112(b): (b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention. The following is a quotation of 35 U.S.C. 112 (pre-AIA), second paragraph: The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention. 07-34-01 Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention. Claims 1, 8 and 15 recite the limitations “deleting an element included in at least one of a tensor QT and a tensor KT such that elements having a same index are left in the tensor QT and the tensor KT ” (emphasis added). The claim covers both deleting from QT only, KT only, or both. However, the subsequent limitation requires that “elements having a same index are left in the tensor QT and the tensor KT”. If only one tensor is modified, such as QT, it is unclear how both tensors end up with only same-index elements. For examination purposes, the limitation will be interpreted to mean “deleting an element included in at least one both of a tensor QT and a tensor KT such that elements having a same index are left in the tensor QT and the tensor KT ” (emphasis added). Dependent claims 2-7, 9-14, and 16-20 depend on indefinite claims 1, 8, and 15, respectively , and are also rejected under 35 USC § 112(b) by virtue of this dependency. Appropriate correction is required. Claim Rejections - 35 USC § 101 07-04-01 AIA 07-04 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claims 1-20 are rejected under 35 U.S.C 101 because the claimed invention is directed to an abstract idea without significantly more. The analysis of the claims will follow the 2019 Revised Patent Subject Matter Eligibility Guidance, 84 Fed. Reg. 50 (“2019 PEG”). When considering subject matter eligibility under 35 U.S.C. 101, it must be determined whether the claim is directed to one of the four statutory categories of invention, i.e., process, machine, manufacture, or composition of matter (Step 1). If the claim does fall within one of the statutory categories, the second step in the analysis is to determine whether the claim is directed to a judicial exception (Step 2A). The Step 2A analysis is broken into two prongs. In the first prong (Step 2A, Prong 1), it is determined whether or not the claims recite a judicial exception (e.g., mathematical concepts, mental processes, certain methods of organizing human activity). If it is determined in Step 2A, Prong 1 that the claims recite a judicial exception, the analysis proceeds to the second prong (Step 2A, Prong 2), where it is determined whether or not the claims integrate the judicial exception into a practical application. If it is determined at step 2A, Prong 2 that the claims do not integrate the judicial exception into a practical application, the analysis proceeds to determining whether the claim is a patent-eligible application of the exception (Step 2B). If an abstract idea is present in the claim, any element or combination of elements in the claim must be sufficient to ensure that the claim integrates the judicial exception into a practical application, or else amounts to significantly more than the abstract idea itself. Claim 1 Step 1 : The claim recites a non-transitory computer-readable recording medium; therefore, it is directed to the statutory category of a manufacture. Step 2A Prong 1 : The claim recites, inter alia: deleting an element included in at least one of a tensor QT and a tensor KT such that elements having a same index are left in the tensor QT and the tensor KT from among one or more elements included in the tensor QT included in a reduced Q layer in which one or more elements are reduced based on a first reduction ratio and one or more elements included in the tensor KT included in a reduced K layer in which one or more elements are reduced based on a second reduction ratio: Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of deleting elements in tensor or matrices based on reduction ratios, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. For example, one can practically and mentally decide to prune an entry in a tensor or matrix based on an item in the tensor or matrix being irrelevant or unimportant per predetermined pruning ratios or thresholds. Step 2A Prong 2 : The claim does not recite any additional limitations which integrate the abstract idea into a practical application. Specifically, the additional elements consist of “ a machine learning program for causing a computer to execute a process comprising ” and “ for an element of each of a Q layer and a K layer, the Q layer outputting a Query, the K layer outputting a Key, the Query and the Key being a result of an arithmetic operating process on an input tensor in an attention mechanism in a trained machine learning model of a neural network having the attention mechanism ”. The additional elements of “ insert processors or functional units here, separated by quotes a machine learning program for causing a computer to execute a process comprising ” amount to generic computer components used as a tool to perform an existing process. Thus, the additional elements amount to no more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer ( see MPEP § 2106.05(f)). The additional element of “ for an element of each of a Q layer and a K layer, the Q layer outputting a Query, the K layer outputting a Key, the Query and the Key being a result of an arithmetic operating process on an input tensor in an attention mechanism in a trained machine learning model of a neural network having the attention mechanism ” amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use ( see MPEP § 2106.05(h). Thus, even when viewed individually and as an ordered combination, these additional elements do not integrate the abstract idea into a practical application and the claim is thus directed to the abstract idea. Step 2B : Finally, the claim taken as a whole does not contain an inventive concept which provides significantly more than the abstract idea. The additional elements of “ insert processors or functional units here, separated by quotes a machine learning program for causing a computer to execute a process comprising ” amount to generic computer components used as a tool to perform an existing process. Thus, the additional elements amount to no more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer ( see MPEP § 2106.05(f)). The additional element of “ for an element of each of a Q layer and a K layer, the Q layer outputting a Query, the K layer outputting a Key, the Query and the Key being a result of an arithmetic operating process on an input tensor in an attention mechanism in a trained machine learning model of a neural network having the attention mechanism ” amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use ( see MPEP § 2106.05(h). Taken alone or in combination, the additional elements of the claim do not provide an inventive concept and thus the claim is subject-matter ineligible. Claim 2 Step 1 : A manufacture, as above. Step 2A Prong 1 : The claim recites, inter alia: calculating a logical product of a first index of an element included in the tensor QT except of a zero element in the tensor QT and a second index of an element included in the tensor KT except of a zero element in the tensor KT: Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mathematical concept of calculating a product of two indices, which is performed through mathematical computation. deleting an element of an index not included in the logical product from the tensor QT or the tensor KT: Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of deleting elements in tensor or matrices based on a determined product, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper Step 2A Prong 2, Step 2B : The claim does not recite any additional elements that are sufficient to integrate the judicial exceptions into a practical application or amount to significantly more than the judicial exception. As such, the claim is ineligible. Claim 3 Step 1 : A manufacture, as above. Step 2A Prong 1 : The claim recites, inter alia: inserting a padding layer into a downstream side of the V layer, the V layer outputting a Value as a result of the arithmetic operation on the input tensor in the attention mechanism, the padding layer padding one or more elements of a tensor: Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of inserting a padding layer or zero values into another layer, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. padding a tensor VT included in a reduced V layer in which one or more elements are reduced based on a third reduction ratio such that heads of the tensor VT have a same number of elements: Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of inserting a padding layer or zero values into a tensor, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. Step 2A Prong 2, Step 2B : The additional element of “ when the attention mechanism has a multi-head attention mechanism and each of the Q layer, the K layer, and a V layer outputs respective tensors of a plurality heads ” amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use ( see MPEP § 2106.05(h). Taken alone or in combination, the additional elements of the claim do not provide an inventive concept and thus the claim is subject-matter ineligible. Claim 4 Step 1 : A manufacture, as above. Step 2A Prong 1 : The claim recites, inter alia: deleting, from the tensor QT, the tensor KT, and the tensor VT, heads having a same index as a head in which all elements are zero among heads of the tensor QT, the tensor KT, and the tensor VT: Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of deleting heads or information from tensors, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. Step 2A Prong 2, Step 2B : The claim does not recite any additional elements that are sufficient to integrate the judicial exceptions into a practical application or amount to significantly more than the judicial exception. As such, the claim is ineligible. Claim 5 Step 1 : A manufacture, as above. Step 2A Prong 1 : The claim recites, inter alia: wherein the attention mechanism outputs a matrix product based on a tensor VT after the padding and the deletion of the head and a matrix product obtained by normalizing a matrix product of the tensor QT after the deleting of the element and the deleting of the heads and the tensor KT after the deleting of the element and the deleting of the head: Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mathematical concept of determining or outputting a matrix product, which is performed through mathematical computation. Step 2A Prong 2, Step 2B : The claim does not recite any additional elements that are sufficient to integrate the judicial exceptions into a practical application or amount to significantly more than the judicial exception. As such, the claim is ineligible. Claim 6 Step 1 : A manufacture, as above. Step 2A Prong 1 : The claim recites, inter alia: the neural network outputs a result of concatenating elements of the matrix product outputted from the attention mechanism: Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mathematical concept of concatenating elements of a matrix, which is performed through mathematical computation. Step 2A Prong 2, Step 2B : The claim does not recite any additional elements that are sufficient to integrate the judicial exceptions into a practical application or amount to significantly more than the judicial exception. As such, the claim is ineligible. Claim 7 Step 1 : A manufacture, as above. Step 2A Prong 1 : The claim recites, inter alia: inserts a zero matrix into a corresponding tensor to be input: Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of inserting a zero matrix into a tensor, which is an evaluation or observation that is practically capable of being performed in the human mind with the assistance of pen and paper. Step 2A Prong 2, Step 2B : The additional element of “ wherein the padding layers are each a zero padding layer ” amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use ( see MPEP § 2106.05(h). Taken alone or in combination, the additional elements of the claim do not provide an inventive concept and thus the claim is subject-matter ineligible. Claims 8-14 Claims 8-14 recite a method (step 1: a process) to perform the steps of claims 1-7, respectively, without any additional elements that integrate the abstract ideas into a practical application or provide significantly more than the abstract idea by itself, and are thus rejected for the same reasons set forth in the rejection of claims 1-7, respectively. Claims 15-20 Claims 15-20 recite an apparatus (step 1: a machine) using a processor and memory to perform the steps of claims 1-6, respectively, which by MPEP 2106.05(f) (“apply it”) cannot integrate an abstract idea into a practical application or provide significantly more than the abstract idea by itself, and are thus rejected for the same reasons set forth in the rejection of claims 1-6, respectively. Claim Rejections - 35 USC § 102 07-06 AIA 15-10-15 In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. 07-07-aia AIA 07-07 The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action: A person shall be entitled to a patent unless – 07-08-aia AIA (a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention. 07-15 AIA Claim s 1, 2, 8, 9, 15, and 16 are rejected under 35 U.S.C. 102( a)(1 ) as being anticipated by Wang et al. (Wang et al., “SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning”, Jan. 4, 2021, arXiv:2012.09852v2, pp. 1-15, hereinafter “Wang”) . Regarding claim 1 , Wang discloses [a] non-transitory computer-readable recording medium having stored therein a machine learning program for causing a computer to execute a process comprising: (Abstract; “In this paper, we present SpAtten, an efficient algorithm-architecture co-design that leverages token sparsity, head sparsity, and quantization opportunities to reduce the attention computation and memory access” ; and Page 9, §B; the section discloses experimental results that are inherently generated using a non-transitory computer-readable recording medium to produce the results ) for an element of each of a Q layer and a K layer, the Q layer outputting a Query, the K layer outputting a Key, the Query and the Key being a result of an arithmetic operating process on an input tensor in an attention mechanism in a trained machine learning model of a neural network having the attention mechanism, (§II.A; “BERT for discriminative and GPT-2 for generative tasks are the most widely-used models as illustrated in Figure 3. BERT only contains the summarization stage, while GPT 2 contains summarization and generation stages”, the trained attention based neural networks are BERT and GPT-2 ; and Algorithm 1; “Input: Qin ∈ RL0×Din, Kin ∈ RL1×Din, Vin ∈ RL1×Din; Number of Heads: h ; Split Qin,Kin,Vin to h chunks: Q ∈ Rh×L0×D,K ∈ Rh×L1×D,V ∈ Rh×L1×D,D = Din h”, which discloses the Q, K, and V projections ; and Page 3, §II.A; “Inside each block, block in are first multiplied with three matrices to get Query (Q), Key (K) and, Value (V)”, which discloses the Q and K tensors that are the result of a linear arithmetic operation or arithmetic process on the input tensor in the attention mechanism of a trained model or neural network (BERT, GPT-2) ; and Figure 4; the figure discloses the Q and K layers ) deleting an element included in at least one of a tensor QT and a tensor KT such that elements having a same index are left in the tensor QT and the tensor KT from among one or more elements included in the tensor QT included in a reduced Q layer in which one or more elements are reduced based on a first reduction ratio and one or more elements included in the tensor KT included in a reduced K layer in which one or more elements are reduced based on a second reduction ratio (§III.A; “Once a token is pruned, the QKV of it will never be used in all the following attention heads and layers; in every layer/head, several new tokens can be selected and pruned away, thus being global and cascade”, which discloses that when a token at a given position or index is pruned or deleted from K, the corresponding token position is also pruned from Q because the pruning or deleting decision is global across all QKV vectors of the same token ; and Figure 4 and its caption; “Cascade token pruning removes redundant tokens and corresponding entire QKV vectors according to the cumulative token importance scores computed from attention_prob”, which, along with the figure, discloses that after pruning or deleting elements in the tensor QT and KT, only the elements of QT and KT that share the same remaining token indices are retained. Figure 4 further discloses that pruning or deleting one token or element removes that index’s entire row from each of Q, K, and V simultaneously, so the remaining pruned tensors are index aligned ; and Algorithm 2; “Token pruning ratio: pt; Head pruning ratio: ph”, which discloses the claimed two pruning ratios, where the reduced Q layer and reduced K layer are the Q and K matrices after application of the token pruning ratio (first reduction ratio) and the head pruning ratio (second reduction ratio) ). Regarding claim 8 , it is a method claim corresponding the steps of claim 1, and is rejected for the same reasons as claim 1. Regarding claim 15 , it is an apparatus claim corresponding the steps of claim 1, and is rejected for the same reasons as claim 1. Regarding claims 2, 9, and 16 , the rejection of claim 1, 8, and 15 are incorporated and Wang further discloses the deleting comprises: calculating a logical product of a first index of an element included in the tensor QT except of a zero element in the tensor QT and a second index of an element included in the tensor KT except of a zero element in the tensor KT, and deleting an element of an index not included in the logical product from the tensor QT or the tensor KT (Figure 5 and its caption; “Tokens with small importance scores are pruned”, which discloses that tokens with small importance scores or whose cumulative score are zero corresponds to an effectively zero element. The attention probabilities summed per column are a measure of token importance, and tokens with near-zero or negligible attention probability contributions will have an importance score approaching zero and will be excluded ; and Algorithm 2; “remained token id=top-k(st,L1×(1−pt))”. The claimed “logical product” is interpreted as the set of token indices remaining after the “top k operation” of algorithm 2 ) . Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. 07-20-aia AIA The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. Claims 3-7, 10-14, and 17-20 are rejected under 35 U.S.C. § 103 as being obvious over Wang in view of Michel et al. (Michel et al., “Are Sixteen Heads Really Better than One?”, Nov. 4, 2019, arXiv:1905.10650v3, pp. 1-13, hereinafter “Michel”). Regarding claims 3, 10, and 17 , the rejection of claims 1, 8, and 15 are incorporated and Wang further discloses when the attention mechanism has a multi-head attention mechanism and each of the Q layer, the K layer, and a V layer outputs respective tensors of a plurality heads (Algorithm 1; “Split Qin,Kin,Vin to h chunks”, which discloses a multi-attention head mechanism with Q, K, and V tensors splits across multiple heads ) a reduced V layer in which one or more elements are reduced based on a third reduction ratio such that heads of the tensor VT have a same number of elements (§III.C; “SpAtten also supports local Value (V) pruning, which is performed after Softmax. The V vectors to be pruned are decided solely with the current head’s attention probabilities. A pre-defined ratio of V vectors with the smallest attention probabilities are pruned” ). Wang fails to explicitly disclose but Michel discloses inserting a padding layer into a downstream side of the V layer, the V layer outputting a Value as a result of the arithmetic operation on the input tensor in the attention mechanism, the padding layer padding one or more elements of a tensor, and padding a tensor VT included in a reduced V layer (§2.3; “In order to mask head h, we simply set ξh = 0.”, which discloses the zeroing of a head’s output, and this is equivalent to padding the pruned head’s portion of the V-layer output with zeroes so that the tensor has a same number of elements per head ). Wang and Michel are analogous art because both are concerned with transformer attention mechanisms. Before the effective filing date of the claimed invention, it would have been obvious to one skilled in transformer attention mechanisms to combine the Michel’s padding technique with Wang’s V-layer pruning to yield to the predictable result of when the attention mechanism has a multi-head attention mechanism and each of the Q layer, the K layer, and a V layer outputs respective tensors of a plurality heads, inserting a padding layer into a downstream side of the V layer, the V layer outputting a Value as a result of the arithmetic operation on the input tensor in the attention mechanism, the padding layer padding one or more elements of a tensor, and padding a tensor VT included in a reduced V layer in which one or more elements are reduced based on a third reduction ratio such that heads of the tensor VT have a same number of elements . The motivation for doing so would be to iteratively prune away attention heads that contribute less to the model (Michel; §1). Regarding claims 4, 11, and 18 , the rejection of claims 1, 3, 8, 10, 15, and 17 are incorporated and Wang further discloses deleting, from the tensor QT, the tensor KT, and the tensor VT, heads having a same index as a head in which all elements are zero among heads of the tensor QT, the tensor KT, and the tensor VT (§III.B; “Each QKV vector has multiple chunks corresponding to multiple heads… some of the heads are redundant [5] and have little influence on outputs ..:once removed, a head will not appear in the following layers” ; and Figure 4; the figure discloses pruning the 3 rd head by removing or deleting all chunks from all Q, K, and V vectors simultaneously ). Regarding claims 5, 12, and 19 , the rejection of claims 1, 3, 4, 8, 10, 11, 15, 17, and 18 are incorporated and Wang further discloses wherein the attention mechanism outputs a matrix product based on a tensor VT after the padding and the deletion of the head and a matrix product obtained by normalizing a matrix product of the tensor QT after the deleting of the element and the deleting of the heads and the tensor KT after the deleting of the element and the deleting of the head (Algorithm 1; the algorithm discloses calculating a matrix product based on a tensor VT after padding and deletion of the head and the matrix product obtained by normalizing a matrix, and this is reflected within the “for” loop of the algorithm ). Regarding claims 6, 13, and 20 , the rejection of claims 1, 3-5, 8, 10-12, 15, and 17-19 are incorporated and Wang further discloses the neural network outputs a result of concatenating elements of the matrix product outputted from the attention mechanism (Algorithm 1; “Concatenate heads of E ∈ Rh×L0×D as output; Output: attention out ∈ RL0×Din” ). Regarding claims 7 and 14 , the rejection of claims 1, 3, 8, 10, 15, and 17 are incorporated and Wang fails to explicitly disclose but Michel discloses wherein the padding layers are each a zero padding layer that inserts a zero matrix into a corresponding tensor to be input (§2.3; “In order to mask head h, we simply set ξh = 0.”, which discloses the zeroing of a head’s output, and this is equivalent to padding the pruned head’s portion of the V-layer output with zeroes so that the tensor has a same number of elements per head ). The motivation to combine Wang and Michel is the same as discussed above with respect to claim 3. Conclusion 07-96 AIA The prior art made of record and not relied upon is considered pertinent to applicant's disclosure : Shim et al., “LAYER-WISEPRUNINGOFTRANSFORMERATTENTIONHEADS FOREFFICIENTLANGUAGEMODELING”, Oct. 7, 2021, arXiv:2110.03252v1, pp. 1-5. Any inquiry concerning this communication or earlier communications from the examiner should be directed to Brent Hoover whose telephone number is (303)297-4403. The examiner can normally be reached Monday - Friday 9-5 MST. Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Abdullah Kawsar can be reached on 571-270-3169. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /BRENT JOHNSTON HOOVER/Primary Examiner, Art Unit 2127 Application/Control Number: 18/477,574 Page 2 Art Unit: 2127 Application/Control Number: 18/477,574 Page 3 Art Unit: 2127 Application/Control Number: 18/477,574 Page 4 Art Unit: 2127 Application/Control Number: 18/477,574 Page 5 Art Unit: 2127 Application/Control Number: 18/477,574 Page 6 Art Unit: 2127 Application/Control Number: 18/477,574 Page 7 Art Unit: 2127 Application/Control Number: 18/477,574 Page 8 Art Unit: 2127 Application/Control Number: 18/477,574 Page 9 Art Unit: 2127 Application/Control Number: 18/477,574 Page 10 Art Unit: 2127 Application/Control Number: 18/477,574 Page 11 Art Unit: 2127 Application/Control Number: 18/477,574 Page 12 Art Unit: 2127 Application/Control Number: 18/477,574 Page 13 Art Unit: 2127 Application/Control Number: 18/477,574 Page 14 Art Unit: 2127 Application/Control Number: 18/477,574 Page 15 Art Unit: 2127 Application/Control Number: 18/477,574 Page 16 Art Unit: 2127 Application/Control Number: 18/477,574 Page 17 Art Unit: 2127 Application/Control Number: 18/477,574 Page 18 Art Unit: 2127 Application/Control Number: 18/477,574 Page 19 Art Unit: 2127
Prosecution Insights