{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/code/calc-banned-ngram-tokens","entry":"calc_banned_ngram_tokens","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":14,"n_papers_ran":12,"n_papers_ran_no_instrument_failure":12,"n_papers_ran_instrument_only":0,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":7,"n_samples_ran":6,"n_samples_constructed":0,"n_samples_ran_checked":6,"n_samples_instrument":0,"n_samples_unverified":1,"n_samples_fingerprinted":0,"n_places":15,"n_places_pointer_only":7,"n_places_pointer_only_link_open":4,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":6,"unverified":1},"key_notes":{"n_samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2601.09141","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-09141","title":"Identity-Robust Language Model Generation via Content Integrity Preservation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"shmsw25/AmbigQA","path":"codes/models/seq2seq_with_prefix.py","file_url":"https://github.com/shmsw25/AmbigQA/blob/HEAD/codes/models/seq2seq_with_prefix.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, shmsw25/AmbigQA when it was checked","code_sha256":"8d77347cfa15b834","code_sha256_prefix":"8d77347cfa15b834","mcp_get_code":{"code_sha256":"8d77347cfa15b834"}},{"arxiv_id":"2410.03968","arxiv_id_is_arxiv":true,"paper":"/paper/decoding-game-on-minimax-optimality-of","title":"Decoding Game: On Minimax Optimality of Heuristic Text Generation Strategies","date":"2024-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"omar-hagrass/decoding-game","path":"src/transformers_utils.py","file_url":"https://github.com/omar-hagrass/decoding-game/blob/HEAD/src/transformers_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, omar-hagrass/decoding-game when it was checked","code_sha256":"0cd7c4bac19d0a72","code_sha256_prefix":"0cd7c4bac19d0a72","mcp_get_code":{"code_sha256":"0cd7c4bac19d0a72"}},{"arxiv_id":"2402.02503","arxiv_id_is_arxiv":true,"paper":"/paper/gerea-question-aware-prompt-captions-for","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","date":"2024-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"upper9527/gerea","path":"src/generation_utils.py","file_url":"https://github.com/upper9527/gerea/blob/HEAD/src/generation_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, upper9527/gerea when it was checked","code_sha256":"8d77347cfa15b834","code_sha256_prefix":"8d77347cfa15b834","mcp_get_code":{"code_sha256":"8d77347cfa15b834"}},{"arxiv_id":"2312.06149","arxiv_id_is_arxiv":true,"paper":"/paper/unlocking-anticipatory-text-generation-a","title":"Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding","date":"2023-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SalesforceAIResearch/Unlocking-TextGen","path":"FactaulQA/generate.py","file_url":"https://github.com/SalesforceAIResearch/Unlocking-TextGen/blob/HEAD/FactaulQA/generate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from shmsw25/AmbigQA, and GitHub detected no licence in that repository when it was checked","code_sha256":"8d77347cfa15b834","code_sha256_prefix":"8d77347cfa15b834","mcp_get_code":{"code_sha256":"8d77347cfa15b834"}},{"arxiv_id":"2312.06149","arxiv_id_is_arxiv":true,"paper":"/paper/unlocking-anticipatory-text-generation-a","title":"Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding","date":"2023-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SalesforceAIResearch/Unlocking-TextGen","path":"InstructionFollowing/generate.py","file_url":"https://github.com/SalesforceAIResearch/Unlocking-TextGen/blob/HEAD/InstructionFollowing/generate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"1f5f980fef237c7a","code_sha256_prefix":"1f5f980fef237c7a","mcp_get_code":{"code_sha256":"1f5f980fef237c7a"}},{"arxiv_id":"2309.01017","arxiv_id_is_arxiv":true,"paper":"/paper/contrastive-grouping-with-transformer-for-1","title":"Contrastive Grouping with Transformer for Referring Image Segmentation","date":"2023-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"toneyaya/cgformer","path":"bert/generation_utils.py","file_url":"https://github.com/toneyaya/cgformer/blob/HEAD/bert/generation_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from shmsw25/AmbigQA, and GitHub detected no licence in that repository when it was checked","code_sha256":"8d77347cfa15b834","code_sha256_prefix":"8d77347cfa15b834","mcp_get_code":{"code_sha256":"8d77347cfa15b834"}},{"arxiv_id":"2204.03084","arxiv_id_is_arxiv":true,"paper":"/paper/knowledge-infused-decoding-1","title":"Knowledge Infused Decoding","date":"2022-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/KID","path":"KID/agent/agent_utils.py","file_url":"https://github.com/microsoft/KID/blob/HEAD/KID/agent/agent_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"2e5a5db3f5b8e8eb","code_sha256_prefix":"2e5a5db3f5b8e8eb","mcp_get_code":{"code_sha256":"2e5a5db3f5b8e8eb"}},{"arxiv_id":"2109.08828","arxiv_id_is_arxiv":true,"paper":"/paper/perspective-taking-and-pragmatics-for","title":"Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes","date":"2021-09-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"skywalker023/focused-empathy","path":"from_epitome/modeling_utils.py","file_url":"https://github.com/skywalker023/focused-empathy/blob/HEAD/from_epitome/modeling_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"f1cff4633a737beb","code_sha256_prefix":"f1cff4633a737beb","mcp_get_code":{"code_sha256":"f1cff4633a737beb"}},{"arxiv_id":"2109.04096","arxiv_id_is_arxiv":true,"paper":"/paper/a-three-stage-learning-framework-for-low","title":"A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation","date":"2021-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neukg/kat-tslf","path":"kat/gen_utils.py","file_url":"https://github.com/neukg/kat-tslf/blob/HEAD/kat/gen_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from shmsw25/AmbigQA, and GitHub detected no licence in that repository when it was checked","code_sha256":"8d77347cfa15b834","code_sha256_prefix":"8d77347cfa15b834","mcp_get_code":{"code_sha256":"8d77347cfa15b834"}},{"arxiv_id":"2106.01317","arxiv_id_is_arxiv":true,"paper":"/paper/enriching-transformers-with-structured-tensor","title":"Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization","date":"2021-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiangycTarheel/TPT-Summ","path":"models/modeling_utils.py","file_url":"https://github.com/jiangycTarheel/TPT-Summ/blob/HEAD/models/modeling_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"f1cff4633a737beb","code_sha256_prefix":"f1cff4633a737beb","mcp_get_code":{"code_sha256":"f1cff4633a737beb"}},{"arxiv_id":"2104.04039","arxiv_id_is_arxiv":true,"paper":"/paper/plug-and-blend-a-framework-for-controllable","title":"Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes","date":"2021-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xxbidiao/plug-and-blend","path":"gedi_helpers/modeling_utils.py","file_url":"https://github.com/xxbidiao/plug-and-blend/blob/HEAD/gedi_helpers/modeling_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"35214bf3a3709500","code_sha256_prefix":"35214bf3a3709500","mcp_get_code":{"code_sha256":"35214bf3a3709500"}},{"arxiv_id":"2103.11790","arxiv_id_is_arxiv":true,"paper":"/paper/language-models-have-a-moral-dimension","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","date":"2021-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ml-research/MoRT_NMI","path":"MoRT/mcm_textgeneration/mcm_models.py","file_url":"https://github.com/ml-research/MoRT_NMI/blob/HEAD/MoRT/mcm_textgeneration/mcm_models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"bf60ebe2c2b77444","code_sha256_prefix":"bf60ebe2c2b77444","mcp_get_code":{"code_sha256":"bf60ebe2c2b77444"}},{"arxiv_id":"2009.06367","arxiv_id_is_arxiv":true,"paper":"/paper/gedi-generative-discriminator-guided-sequence","title":"GeDi: Generative Discriminator Guided Sequence Generation","date":"2020-09-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/GeDi","path":"modeling_utils.py","file_url":"https://github.com/salesforce/GeDi/blob/HEAD/modeling_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"35214bf3a3709500","code_sha256_prefix":"35214bf3a3709500","mcp_get_code":{"code_sha256":"35214bf3a3709500"}},{"arxiv_id":"1910.13461","arxiv_id_is_arxiv":true,"paper":"/paper/bart-denoising-sequence-to-sequence-pre","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","date":"2019-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"i2r-simmc/i2r-simmc-2020","path":"src/generation_utils.py","file_url":"https://github.com/i2r-simmc/i2r-simmc-2020/blob/HEAD/src/generation_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from shmsw25/AmbigQA, and GitHub detected no licence in that repository when it was checked","code_sha256":"8d77347cfa15b834","code_sha256_prefix":"8d77347cfa15b834","mcp_get_code":{"code_sha256":"8d77347cfa15b834"}},{"arxiv_id":"2025.findings-emnlp.70","arxiv_id_is_arxiv":false,"paper":null,"title":"ACL Anthology id 2025.findings-emnlp.70","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"passing2961/EmpGPT-3","path":"from_epitome/modeling_utils.py","file_url":"https://github.com/passing2961/EmpGPT-3/blob/HEAD/from_epitome/modeling_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"f1cff4633a737beb","code_sha256_prefix":"f1cff4633a737beb","mcp_get_code":{"code_sha256":"f1cff4633a737beb"}}],"record_sha256":"3b9b2880e14f59bb389253aea547e109491604f871031fce26bd2eb30a7a4da7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}