{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BGHW63PMMT5JDP2HDHIGP2UKS7","short_pith_number":"pith:BGHW63PM","schema_version":"1.0","canonical_sha256":"098f6f6dec64fa91bf4719d067ea8a97c37e412e4119482683df358f19e1078c","source":{"kind":"arxiv","id":"2503.14936","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Code LLM Training with Programmer Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.SE","authors_text":"Chen Huang, Dung Thuy Nguyen, Kevin Leach, Yifan Zhang, Yu Huang, Zachary Karas","submitted_at":"2025-03-19T06:44:29Z","abstract_excerpt":"Human attention provides valuable yet underexploited signals for code LLM training, offering a perspective beyond purely machine-driven attention. Despite the complexity and cost of collecting eye-tracking data, there has also been limited progress in systematically using these signals for code LLM training. To address both issues, we propose a cohesive pipeline spanning augmentation and reward-based fine-tuning. Specifically, we introduce (1) an eye-tracking path augmentation method to expand programmer attention datasets, (2) a pattern abstraction step that refines raw fixations into learnab"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.14936","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-19T06:44:29Z","cross_cats_sorted":["cs.HC","cs.LG"],"title_canon_sha256":"33a88a53321b171d3a5c3524ee179caab5fe88fa79ffef5cb4b1fccf79292919","abstract_canon_sha256":"090b42dba4991c5dac77541b41370fe4dfde4ed33631ba2b3865addab9f177f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:15.607101Z","signature_b64":"ms5Hp2Lkz6kiY0pTEoQaKA6upfFnv6kKUFxUgaf4WVyVOIPKduCmg1zN87x3elT2bDzzzTjsLEessXfLbLgxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"098f6f6dec64fa91bf4719d067ea8a97c37e412e4119482683df358f19e1078c","last_reissued_at":"2026-07-05T10:49:15.606646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:15.606646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Code LLM Training with Programmer Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.SE","authors_text":"Chen Huang, Dung Thuy Nguyen, Kevin Leach, Yifan Zhang, Yu Huang, Zachary Karas","submitted_at":"2025-03-19T06:44:29Z","abstract_excerpt":"Human attention provides valuable yet underexploited signals for code LLM training, offering a perspective beyond purely machine-driven attention. Despite the complexity and cost of collecting eye-tracking data, there has also been limited progress in systematically using these signals for code LLM training. To address both issues, we propose a cohesive pipeline spanning augmentation and reward-based fine-tuning. Specifically, we introduce (1) an eye-tracking path augmentation method to expand programmer attention datasets, (2) a pattern abstraction step that refines raw fixations into learnab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14936","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.14936/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.14936","created_at":"2026-07-05T10:49:15.606705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.14936v2","created_at":"2026-07-05T10:49:15.606705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14936","created_at":"2026-07-05T10:49:15.606705+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGHW63PMMT5J","created_at":"2026-07-05T10:49:15.606705+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGHW63PMMT5JDP2H","created_at":"2026-07-05T10:49:15.606705+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGHW63PM","created_at":"2026-07-05T10:49:15.606705+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00693","citing_title":"Human Attention During Localization of Memory Bugs in C Programs","ref_index":87,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BGHW63PMMT5JDP2HDHIGP2UKS7","json":"https://pith.science/pith/BGHW63PMMT5JDP2HDHIGP2UKS7.json","graph_json":"https://pith.science/api/pith-number/BGHW63PMMT5JDP2HDHIGP2UKS7/graph.json","events_json":"https://pith.science/api/pith-number/BGHW63PMMT5JDP2HDHIGP2UKS7/events.json","paper":"https://pith.science/paper/BGHW63PM"},"agent_actions":{"view_html":"https://pith.science/pith/BGHW63PMMT5JDP2HDHIGP2UKS7","download_json":"https://pith.science/pith/BGHW63PMMT5JDP2HDHIGP2UKS7.json","view_paper":"https://pith.science/paper/BGHW63PM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.14936&json=true","fetch_graph":"https://pith.science/api/pith-number/BGHW63PMMT5JDP2HDHIGP2UKS7/graph.json","fetch_events":"https://pith.science/api/pith-number/BGHW63PMMT5JDP2HDHIGP2UKS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGHW63PMMT5JDP2HDHIGP2UKS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGHW63PMMT5JDP2HDHIGP2UKS7/action/storage_attestation","attest_author":"https://pith.science/pith/BGHW63PMMT5JDP2HDHIGP2UKS7/action/author_attestation","sign_citation":"https://pith.science/pith/BGHW63PMMT5JDP2HDHIGP2UKS7/action/citation_signature","submit_replication":"https://pith.science/pith/BGHW63PMMT5JDP2HDHIGP2UKS7/action/replication_record"}},"created_at":"2026-07-05T10:49:15.606705+00:00","updated_at":"2026-07-05T10:49:15.606705+00:00"}