{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6AGVVCFIGZ3524FQJSB62OUMKA","short_pith_number":"pith:6AGVVCFI","schema_version":"1.0","canonical_sha256":"f00d5a88a83677dd70b04c83ed3a8c500856c6d4568e9e9893f8e4995bf175a1","source":{"kind":"arxiv","id":"2406.01006","version":2},"attestation_state":"computed","paper":{"title":"SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Baishakhi Ray, Gail Kaiser, Jinjun Peng, Junfeng Yang, Marcus J. Min, Yangruibo Ding","submitted_at":"2024-06-03T05:36:57Z","abstract_excerpt":"Code Large Language Models (Code LLMs) have excelled at tasks like code completion but often miss deeper semantics such as execution effects and dynamic states. This paper aims to bridge the gap between Code LLMs' reliance on static text data and the need for semantic understanding for complex tasks like debugging and program repair. We introduce a novel strategy, monologue reasoning, to train Code LLMs to reason comprehensive semantics, encompassing high-level functional descriptions, local execution effects of individual statements, and overall input/output behavior, thereby linking static c"},"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":"2406.01006","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T05:36:57Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"81f9d32af00d20a69916a40eeafa9322394c867b8ef0db6ce814dae2a0dc5a04","abstract_canon_sha256":"34ed04ec3f7c5ab063cd22dc173451a2558a293777fdbb057efce87d453247e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:29.819287Z","signature_b64":"3p8/odLA/NZBNBE3rm7GwRA6BSDncQyvBL+OMlvtJ6pbaWAd4zGWSN092HpFRJTuzXGyOi2alYrSw8XfrPA3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f00d5a88a83677dd70b04c83ed3a8c500856c6d4568e9e9893f8e4995bf175a1","last_reissued_at":"2026-07-05T09:29:29.818177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:29.818177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Baishakhi Ray, Gail Kaiser, Jinjun Peng, Junfeng Yang, Marcus J. Min, Yangruibo Ding","submitted_at":"2024-06-03T05:36:57Z","abstract_excerpt":"Code Large Language Models (Code LLMs) have excelled at tasks like code completion but often miss deeper semantics such as execution effects and dynamic states. This paper aims to bridge the gap between Code LLMs' reliance on static text data and the need for semantic understanding for complex tasks like debugging and program repair. We introduce a novel strategy, monologue reasoning, to train Code LLMs to reason comprehensive semantics, encompassing high-level functional descriptions, local execution effects of individual statements, and overall input/output behavior, thereby linking static c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01006","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/2406.01006/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":"2406.01006","created_at":"2026-07-05T09:29:29.818417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01006v2","created_at":"2026-07-05T09:29:29.818417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01006","created_at":"2026-07-05T09:29:29.818417+00:00"},{"alias_kind":"pith_short_12","alias_value":"6AGVVCFIGZ35","created_at":"2026-07-05T09:29:29.818417+00:00"},{"alias_kind":"pith_short_16","alias_value":"6AGVVCFIGZ3524FQ","created_at":"2026-07-05T09:29:29.818417+00:00"},{"alias_kind":"pith_short_8","alias_value":"6AGVVCFI","created_at":"2026-07-05T09:29:29.818417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.09664","citing_title":"CodeMind: Evaluating Large Language Models for Code Reasoning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17958","citing_title":"Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18747","citing_title":"Code as Agent Harness","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2508.16771","citing_title":"EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2510.15079","citing_title":"Assessing Coherency and Consistency of Code Execution Reasoning by Large Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2512.00127","citing_title":"Generating Verifiable Chain of Thoughts from Exection-Traces","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6AGVVCFIGZ3524FQJSB62OUMKA","json":"https://pith.science/pith/6AGVVCFIGZ3524FQJSB62OUMKA.json","graph_json":"https://pith.science/api/pith-number/6AGVVCFIGZ3524FQJSB62OUMKA/graph.json","events_json":"https://pith.science/api/pith-number/6AGVVCFIGZ3524FQJSB62OUMKA/events.json","paper":"https://pith.science/paper/6AGVVCFI"},"agent_actions":{"view_html":"https://pith.science/pith/6AGVVCFIGZ3524FQJSB62OUMKA","download_json":"https://pith.science/pith/6AGVVCFIGZ3524FQJSB62OUMKA.json","view_paper":"https://pith.science/paper/6AGVVCFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01006&json=true","fetch_graph":"https://pith.science/api/pith-number/6AGVVCFIGZ3524FQJSB62OUMKA/graph.json","fetch_events":"https://pith.science/api/pith-number/6AGVVCFIGZ3524FQJSB62OUMKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6AGVVCFIGZ3524FQJSB62OUMKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6AGVVCFIGZ3524FQJSB62OUMKA/action/storage_attestation","attest_author":"https://pith.science/pith/6AGVVCFIGZ3524FQJSB62OUMKA/action/author_attestation","sign_citation":"https://pith.science/pith/6AGVVCFIGZ3524FQJSB62OUMKA/action/citation_signature","submit_replication":"https://pith.science/pith/6AGVVCFIGZ3524FQJSB62OUMKA/action/replication_record"}},"created_at":"2026-07-05T09:29:29.818417+00:00","updated_at":"2026-07-05T09:29:29.818417+00:00"}