DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on March 12th, 2026 has been entered.
Response to Arguments
Claims 1-17 contain allowable subject matter and are allowed under 35 U.S.C. § 103, described below in section “Allowable Subject Matter.” However, the independent claims recite an antecedent issue under 35 U.S.C. § 112(b), and therefore remain rejected.
Allowable Subject Matter
Claims 1-17 would be allowable if the claims were amended to overcome the antecedent issues referenced in section “Claim Rejections - 35 USC § 112.”
The following is a statement of reasons for the indication of allowable subject matter:
Independent claims 1, 13-15 appear to recite allowable subject matter when considered as a whole. In particular, the claim is not merely directed to decoding neural-network weight parameters using arithmetic coding generally as described in Brothers and Marpe, nor merely to selecting a context based on previously decoded information. Rather, claim 1 further requires a specific context-selection structure for unary-code or truncated-unary-code bits: contexts are selected from two possible contexts per bit position for a first range of bit positions in dependence on a sign of the currently decoded weight parameter, while contexts for a second range of bit positions are selected independently from the sign of the currently decoded weight parameter.
This limitation provides a meaningful technical distinction over conventional context-dependent arithmetic decoding. The claimed decoder treats different bit-position ranges of the unary or truncated unary representation differently, using sign-dependent context selection only for a first range while deliberately omitting sign dependence for a second range. Thus, the claim is not merely using sign information as another generic context variable, instead defining a structured, range-specific context-selection scheme that applies sign-dependent modeling selectively based on the bit-position range being decoded. This is a particularized entropy-decoding technique, not an abstract instruction to improve compression.
The apparent technical rationale is that lower-order or earlier unary/truncated-unary bit positions may exhibit useful statistical dependence on the sign of the currently decoded weight parameter, whereas later bit positions may not justify separate sign-dependent context modeling. By selecting between two possible contexts per bit position in the first range based on sign, the decoder can exploit sign-correlated statistics where they are useful. By selecting contexts independently of sign in the second range, the decoder avoids unnecessary context splitting, reduces context-model complexity, and preserves better probability adaptation where sign correlation is weaker or less reliable. The claimed arrangement therefore reflects a specific balance between compression efficiency and context-model overhead.
The prior art of record, Brothers and Marpe, teaches a generic combination of neural-network weight compression, with the arithmetic coding characteristic of the CABAC framework. However, the art does not appear to teach or suggest the particular claimed division in which a first range of unary/truncated-unary bit positions uses sign-dependent selection from two possible contexts per bit position, while a second range of unary/truncated-unary bit positions uses sign-independent context selection. Accordingly, the claimed subject matter, especially this range-specific sign-dependent/sign-independent context-selection scheme for unary or truncated unary coded weight-parameter bits, appears to distinguish over the prior art of record.
Claim Rejections - 35 USC § 112
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.
Claims 1-17 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.
Claim 1 and analogous claims 13-15 are rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor regards as the invention. Claim 1 recites “selecting contexts out of two possible contexts per bit position for a decoding of bits in a first range of one or more bit positions of the unary code or of the truncated unary code,” and further recites decoding bits in a second range of bit positions of “the unary code or of the truncated unary code.” However, the claim does not previously introduce a unary code or truncated unary code, nor does the claim clearly specify that the previously recited “number representation” or “syntax element” is represented by a unary code or truncated unary code. Accordingly, it is unclear what “the unary code” or “the truncated unary code” refers to.
This lack of clear referential basis renders the scope of the context-selection limitations unclear because the claimed first and second ranges are defined as ranges of bit positions of an unidentified unary/truncated unary code. Thus, one of ordinary skill in the art cannot determine with reasonable clarity whether the claimed context selection is applied to the number representation of the weight parameter, to a syntax element thereof, to a binarized representation used in arithmetic coding, or to some other code structure.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PAUL JUSTIN BREENE whose telephone number is (571)272-6320. 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, Michael J Huntley can be reached on 303-297-4307. 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.
/P.J.B./ Examiner, Art Unit 2129
/MICHAEL J HUNTLEY/Supervisory Patent Examiner, Art Unit 2129
Prosecution Insights