{"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/dot-product-attention","entry":"dot_product_attention","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":15,"n_papers_ran":13,"n_papers_ran_no_instrument_failure":8,"n_papers_ran_instrument_only":5,"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":10,"n_samples_ran":8,"n_samples_constructed":0,"n_samples_ran_checked":5,"n_samples_instrument":3,"n_samples_unverified":2,"n_samples_fingerprinted":1,"n_places":15,"n_places_pointer_only":3,"n_places_pointer_only_link_open":0,"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":3,"ran":5,"unverified":2},"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":"2501.06999","arxiv_id_is_arxiv":true,"paper":"/paper/likelihood-training-of-cascaded-diffusion","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","date":"2025-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lihenryhfl/pcdm","path":"nn.py","file_url":"https://github.com/lihenryhfl/pcdm/blob/HEAD/nn.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"3650a2dfe2e97298","code_sha256_prefix":"3650a2dfe2e97298","mcp_get_code":{"code_sha256":"3650a2dfe2e97298"}},{"arxiv_id":"2410.10012","arxiv_id_is_arxiv":true,"paper":"/paper/naraim-native-aspect-ratio-autoregressive","title":"NARAIM: Native Aspect Ratio Autoregressive Image Models","date":"2024-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"daniel-gallo/naraim","path":"model/pretraining.py","file_url":"https://github.com/daniel-gallo/naraim/blob/HEAD/model/pretraining.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, daniel-gallo/naraim when it was checked","code_sha256":"d1eecbe4982a95d1","code_sha256_prefix":"d1eecbe4982a95d1","mcp_get_code":{"code_sha256":"d1eecbe4982a95d1"}},{"arxiv_id":"2406.13476","arxiv_id_is_arxiv":true,"paper":"/paper/llms-are-zero-shot-context-aware-simultaneous","title":"LLMs Are Zero-Shot Context-Aware Simultaneous Translators","date":"2024-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RomanKoshkin/toLLMatch","path":"whisper-jax/whisper_jax/layers.py","file_url":"https://github.com/RomanKoshkin/toLLMatch/blob/HEAD/whisper-jax/whisper_jax/layers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"2000f34f95c683d6","code_sha256_prefix":"2000f34f95c683d6","mcp_get_code":{"code_sha256":"2000f34f95c683d6"}},{"arxiv_id":"2403.00043","arxiv_id_is_arxiv":true,"paper":"/paper/rinalmo-general-purpose-rna-language-models","title":"RiNALMo: General-Purpose RNA Language Models Can Generalize Well on Structure Prediction Tasks","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lbcb-sci/rinalmo","path":"rinalmo/model/attention.py","file_url":"https://github.com/lbcb-sci/rinalmo/blob/HEAD/rinalmo/model/attention.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":"f6afd2235cdb7855","code_sha256_prefix":"f6afd2235cdb7855","mcp_get_code":{"code_sha256":"f6afd2235cdb7855"}},{"arxiv_id":"2308.06912","arxiv_id_is_arxiv":true,"paper":"/paper/causallm-is-not-optimal-for-in-context","title":"CausalLM is not optimal for in-context learning","date":"2023-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/causallm_icl","path":"self_attention_patch.py","file_url":"https://github.com/google-research/causallm_icl/blob/HEAD/self_attention_patch.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":"25ce8c68e697049c","code_sha256_prefix":"25ce8c68e697049c","mcp_get_code":{"code_sha256":"25ce8c68e697049c"}},{"arxiv_id":"2305.03935","arxiv_id_is_arxiv":true,"paper":"/paper/improved-techniques-for-maximum-likelihood","title":"Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs","date":"2023-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-ml/i-dode","path":"model_vdm.py","file_url":"https://github.com/thu-ml/i-dode/blob/HEAD/model_vdm.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":"f25b8c5dd6fba4a7","code_sha256_prefix":"f25b8c5dd6fba4a7","mcp_get_code":{"code_sha256":"f25b8c5dd6fba4a7"}},{"arxiv_id":"2303.16133","arxiv_id_is_arxiv":true,"paper":"/paper/exposing-and-addressing-cross-task","title":"Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models","date":"2023-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adymaharana/cococon","path":"unified-io/uio/t5x_layers.py","file_url":"https://github.com/adymaharana/cococon/blob/HEAD/unified-io/uio/t5x_layers.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":"dac0288079ac279f","code_sha256_prefix":"dac0288079ac279f","mcp_get_code":{"code_sha256":"dac0288079ac279f"}},{"arxiv_id":"2212.04356","arxiv_id_is_arxiv":true,"paper":"/paper/robust-speech-recognition-via-large-scale-1","title":"Robust Speech Recognition via Large-Scale Weak Supervision","date":"2022-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sanchit-gandhi/whisper-jax","path":"whisper_jax/layers.py","file_url":"https://github.com/sanchit-gandhi/whisper-jax/blob/HEAD/whisper_jax/layers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"Apache-2.0, as GitHub detects it on this paper's repository, sanchit-gandhi/whisper-jax, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it","code_sha256":"2000f34f95c683d6","code_sha256_prefix":"2000f34f95c683d6","mcp_get_code":{"code_sha256":"2000f34f95c683d6"}},{"arxiv_id":"2206.05408","arxiv_id_is_arxiv":true,"paper":"/paper/multi-instrument-music-synthesis-with","title":"Multi-instrument Music Synthesis with Spectrogram Diffusion","date":"2022-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"magenta/music-spectrogram-diffusion","path":"music_spectrogram_diffusion/layers.py","file_url":"https://github.com/magenta/music-spectrogram-diffusion/blob/HEAD/music_spectrogram_diffusion/layers.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":"dac0288079ac279f","code_sha256_prefix":"dac0288079ac279f","mcp_get_code":{"code_sha256":"dac0288079ac279f"}},{"arxiv_id":"2205.01580","arxiv_id_is_arxiv":true,"paper":"/paper/better-plain-vit-baselines-for-imagenet-1k","title":"Better plain ViT baselines for ImageNet-1k","date":"2022-05-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuyangshu/retinavit","path":"big_vision/models/attn_override.py","file_url":"https://github.com/yuyangshu/retinavit/blob/HEAD/big_vision/models/attn_override.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":"2c4ed3f75ab6ee14","code_sha256_prefix":"2c4ed3f75ab6ee14","mcp_get_code":{"code_sha256":"2c4ed3f75ab6ee14"}},{"arxiv_id":"2112.00791","arxiv_id_is_arxiv":true,"paper":"/paper/controlling-conditional-language-models-with","title":"Controlling Conditional Language Models without Catastrophic Forgetting","date":"2021-12-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google/t5patches","path":"t5patches/layers.py","file_url":"https://github.com/google/t5patches/blob/HEAD/t5patches/layers.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":"dac0288079ac279f","code_sha256_prefix":"dac0288079ac279f","mcp_get_code":{"code_sha256":"dac0288079ac279f"}},{"arxiv_id":"2107.00630","arxiv_id_is_arxiv":true,"paper":"/paper/variational-diffusion-models","title":"Variational Diffusion Models","date":"2021-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/vdm","path":"model_vdm.py","file_url":"https://github.com/google-research/vdm/blob/HEAD/model_vdm.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"3650a2dfe2e97298","code_sha256_prefix":"3650a2dfe2e97298","mcp_get_code":{"code_sha256":"3650a2dfe2e97298"}},{"arxiv_id":"2106.03598","arxiv_id_is_arxiv":true,"paper":"/paper/scifive-a-text-to-text-transformer-model-for","title":"SciFive: a text-to-text transformer model for biomedical literature","date":"2021-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"justinphan3110/SciFive","path":"biot5x/configs/t5/layers.py","file_url":"https://github.com/justinphan3110/SciFive/blob/HEAD/biot5x/configs/t5/layers.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":"dac0288079ac279f","code_sha256_prefix":"dac0288079ac279f","mcp_get_code":{"code_sha256":"dac0288079ac279f"}},{"arxiv_id":"2005.04732","arxiv_id_is_arxiv":true,"paper":"/paper/towards-robustifying-nli-models-against","title":"Towards Robustifying NLI Models Against Lexical Dataset Biases","date":"2020-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"owenzx/LexicalDebias-ACL2020","path":"models/hex.py","file_url":"https://github.com/owenzx/LexicalDebias-ACL2020/blob/HEAD/models/hex.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":"0403fe04af127ad4","code_sha256_prefix":"0403fe04af127ad4","mcp_get_code":{"code_sha256":"0403fe04af127ad4"}},{"arxiv_id":"1909.11942","arxiv_id_is_arxiv":true,"paper":"/paper/albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brightmart/albert_zh","path":"modeling_google.py","file_url":"https://github.com/brightmart/albert_zh/blob/HEAD/modeling_google.py","status":"unverified","verification_level":0,"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, brightmart/albert_zh when it was checked","code_sha256":"847351b08a6a93c6","code_sha256_prefix":"847351b08a6a93c6","mcp_get_code":{"code_sha256":"847351b08a6a93c6"}}],"record_sha256":"001da6ac3b813f1af6e146806fa9fbbd79e4d5735067f635055431247269a363","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}