{"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/split-heads","entry":"split_heads","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":10,"n_papers_ran":2,"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":9,"n_samples_ran":2,"n_samples_fingerprinted":1,"n_places":10,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":1,"unverified":7},"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":"2411.17525","paper":"/paper/pushing-the-limits-of-large-language-model","title":"Pushing the Limits of Large Language Model Quantization via the Linearity Theorem","date":"2024-11-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"goodevening13/aquakv","path":"aquakv/cache_utils.py","file_url":"https://github.com/goodevening13/aquakv/blob/HEAD/aquakv/cache_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"45d1e56d523d67f7","mcp_get_code":{"code_sha256":"45d1e56d523d67f7"}},{"arxiv_id":"2403.07809","paper":"/paper/pyvene-a-library-for-understanding-and","title":"pyvene: A Library for Understanding and Improving PyTorch Models via Interventions","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"frankaging/pyvene","path":"pyvene/models/constants.py","file_url":"https://github.com/frankaging/pyvene/blob/HEAD/pyvene/models/constants.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a2d93b74f75430a8","mcp_get_code":{"code_sha256":"a2d93b74f75430a8"}},{"arxiv_id":"2211.00593","paper":"/paper/interpretability-in-the-wild-a-circuit-for","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","date":"2022-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/transformer-debugger","path":"neuron_explainer/models/transformer.py","file_url":"https://github.com/openai/transformer-debugger/blob/HEAD/neuron_explainer/models/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ef93b73d7c3c9ea","mcp_get_code":{"code_sha256":"3ef93b73d7c3c9ea"}},{"arxiv_id":"2205.03766","paper":"/paper/scheduled-multi-task-learning-for-neural-chat","title":"Scheduled Multi-task Learning for Neural Chat Translation","date":"2022-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xl2248/sml","path":"thumt-sml/thumt/layers/attention.py","file_url":"https://github.com/xl2248/sml/blob/HEAD/thumt-sml/thumt/layers/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"79a8f2b2454736a1","mcp_get_code":{"code_sha256":"79a8f2b2454736a1"}},{"arxiv_id":"2004.11867","paper":"/paper/improving-massively-multilingual-neural","title":"Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation","date":"2020-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bzhangGo/zero","path":"models/transformer_l0drop.py","file_url":"https://github.com/bzhangGo/zero/blob/HEAD/models/transformer_l0drop.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"688a6272dc140cd0","mcp_get_code":{"code_sha256":"688a6272dc140cd0"}},{"arxiv_id":"1912.08777","paper":"/paper/pegasus-pre-training-with-extracted-gap","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","date":"2019-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/pegasus","path":"pegasus/layers/attention.py","file_url":"https://github.com/google-research/pegasus/blob/HEAD/pegasus/layers/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7eb8334d0e01c2d2","mcp_get_code":{"code_sha256":"7eb8334d0e01c2d2"}},{"arxiv_id":"1810.03581","paper":"/paper/improving-the-transformer-translation-model","title":"Improving the Transformer Translation Model with Document-Level Context","date":"2018-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Glaceon31/Document-Transformer","path":"thumt/layers/attention.py","file_url":"https://github.com/Glaceon31/Document-Transformer/blob/HEAD/thumt/layers/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"79a8f2b2454736a1","mcp_get_code":{"code_sha256":"79a8f2b2454736a1"}},{"arxiv_id":"1805.00631","paper":"/paper/accelerating-neural-transformer-via-an","title":"Accelerating Neural Transformer via an Average Attention Network","date":"2018-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bzhangXMU/transformer-aan","path":"code/thumt/layers/attention.py","file_url":"https://github.com/bzhangXMU/transformer-aan/blob/HEAD/code/thumt/layers/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"98b6d2c44a099591","mcp_get_code":{"code_sha256":"98b6d2c44a099591"}},{"arxiv_id":"1803.02155","paper":"/paper/self-attention-with-relative-position","title":"Self-Attention with Relative Position Representations","date":"2018-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenNMT/OpenNMT-tf","path":"opennmt/layers/transformer.py","file_url":"https://github.com/OpenNMT/OpenNMT-tf/blob/HEAD/opennmt/layers/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"615a2551db0eca16","mcp_get_code":{"code_sha256":"615a2551db0eca16"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"abhaskumarsinha/MinimalGPT","path":"GPT.py","file_url":"https://github.com/abhaskumarsinha/MinimalGPT/blob/HEAD/GPT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e4dc4987aab04a09","mcp_get_code":{"code_sha256":"e4dc4987aab04a09"}}]}