{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/code/build-mask-cache","entry":"build_mask_cache","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+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.","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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":6,"n_papers_ran":6,"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":1,"n_samples_ran":1,"n_samples_fingerprinted":1,"n_places":6,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":0},"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":"2411.12892","paper":"/paper/selective-attention-enhancing-transformer","title":"Selective Attention: Enhancing Transformer through Principled Context Control","date":"2024-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umich-sota/selective_attention","path":"lit_gpt/model.py","file_url":"https://github.com/umich-sota/selective_attention/blob/HEAD/lit_gpt/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7ee1c3ba71156110","mcp_get_code":{"code_sha256":"7ee1c3ba71156110"}},{"arxiv_id":"2410.11190","paper":"/paper/mini-omni2-towards-open-source-gpt-4o-model","title":"Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities","date":"2024-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gpt-omni/mini-omni2","path":"litgpt/model.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/litgpt/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7ee1c3ba71156110","mcp_get_code":{"code_sha256":"7ee1c3ba71156110"}},{"arxiv_id":"2410.08102","paper":"/paper/multi-agent-collaborative-data-selection-for","title":"Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"beccabai/multi-agent-data-selection","path":"src/lit_gpt/model.py","file_url":"https://github.com/beccabai/multi-agent-data-selection/blob/HEAD/src/lit_gpt/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ee1c3ba71156110","mcp_get_code":{"code_sha256":"7ee1c3ba71156110"}},{"arxiv_id":"2408.16725","paper":"/paper/mini-omni-language-models-can-hear-talk-while","title":"Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming","date":"2024-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gpt-omni/mini-omni","path":"litgpt/model.py","file_url":"https://github.com/gpt-omni/mini-omni/blob/HEAD/litgpt/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7ee1c3ba71156110","mcp_get_code":{"code_sha256":"7ee1c3ba71156110"}},{"arxiv_id":"2406.10209","paper":"/paper/be-like-a-goldfish-don-t-memorize-mitigating","title":"Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ahans30/goldfish-loss","path":"lit_gpt/model.py","file_url":"https://github.com/ahans30/goldfish-loss/blob/HEAD/lit_gpt/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7ee1c3ba71156110","mcp_get_code":{"code_sha256":"7ee1c3ba71156110"}},{"arxiv_id":"2406.06046","paper":"/paper/mates-model-aware-data-selection-for","title":"MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models","date":"2024-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cxcscmu/MATES","path":"src/lit_gpt/model.py","file_url":"https://github.com/cxcscmu/MATES/blob/HEAD/src/lit_gpt/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7ee1c3ba71156110","mcp_get_code":{"code_sha256":"7ee1c3ba71156110"}}]}