{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FDKE6Y2J5KKSRKB7NHSNPSJMZB","short_pith_number":"pith:FDKE6Y2J","schema_version":"1.0","canonical_sha256":"28d44f6349ea9528a83f69e4d7c92cc85cc357e5672f95166591ef0ce7a1afb4","source":{"kind":"arxiv","id":"2208.08100","version":2},"attestation_state":"computed","paper":{"title":"CommitBART: A Large Pre-trained Model for GitHub Commits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Shangqing Liu, Xiaofei Xie, Yang Liu, Yanzhou Li","submitted_at":"2022-08-17T06:35:57Z","abstract_excerpt":"GitHub commits, which record the code changes with natural language messages for description, play a critical role for software developers to comprehend the software evolution. To promote the development of the open-source software community, we collect a commit benchmark including over 7.99 million commits across 7 programming languages. Based on this benchmark, we present CommitBART, a large pre-trained encoder-decoder Transformer model for GitHub commits. The model is pre-trained by three categories (i.e., denoising objectives, cross-modal generation and contrastive learning) for six pre-tr"},"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":"2208.08100","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-08-17T06:35:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"79cd540633047d586da5b6294152de8f265ece50fcca3787381a82c0cd029417","abstract_canon_sha256":"e2afdb9178287be8382ceddf3aa5a2cabf2bd7ed5afd8f0a191253c327c76649"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:48.692305Z","signature_b64":"qICjAcRcYIq0jRjQHsmkEONcp3YJjAvmBqD9M5ah5taPLKBviM4b3b+cfCYV++qI9T43Ru/bWiLNHSkLBSsnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28d44f6349ea9528a83f69e4d7c92cc85cc357e5672f95166591ef0ce7a1afb4","last_reissued_at":"2026-07-05T05:34:48.691691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:48.691691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CommitBART: A Large Pre-trained Model for GitHub Commits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Shangqing Liu, Xiaofei Xie, Yang Liu, Yanzhou Li","submitted_at":"2022-08-17T06:35:57Z","abstract_excerpt":"GitHub commits, which record the code changes with natural language messages for description, play a critical role for software developers to comprehend the software evolution. To promote the development of the open-source software community, we collect a commit benchmark including over 7.99 million commits across 7 programming languages. Based on this benchmark, we present CommitBART, a large pre-trained encoder-decoder Transformer model for GitHub commits. The model is pre-trained by three categories (i.e., denoising objectives, cross-modal generation and contrastive learning) for six pre-tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.08100","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/2208.08100/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":"2208.08100","created_at":"2026-07-05T05:34:48.691770+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.08100v2","created_at":"2026-07-05T05:34:48.691770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.08100","created_at":"2026-07-05T05:34:48.691770+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDKE6Y2J5KKS","created_at":"2026-07-05T05:34:48.691770+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDKE6Y2J5KKSRKB7","created_at":"2026-07-05T05:34:48.691770+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDKE6Y2J","created_at":"2026-07-05T05:34:48.691770+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13138","citing_title":"A Comprehensive Evaluation of Code Language Models for Security Patch Detection","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDKE6Y2J5KKSRKB7NHSNPSJMZB","json":"https://pith.science/pith/FDKE6Y2J5KKSRKB7NHSNPSJMZB.json","graph_json":"https://pith.science/api/pith-number/FDKE6Y2J5KKSRKB7NHSNPSJMZB/graph.json","events_json":"https://pith.science/api/pith-number/FDKE6Y2J5KKSRKB7NHSNPSJMZB/events.json","paper":"https://pith.science/paper/FDKE6Y2J"},"agent_actions":{"view_html":"https://pith.science/pith/FDKE6Y2J5KKSRKB7NHSNPSJMZB","download_json":"https://pith.science/pith/FDKE6Y2J5KKSRKB7NHSNPSJMZB.json","view_paper":"https://pith.science/paper/FDKE6Y2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.08100&json=true","fetch_graph":"https://pith.science/api/pith-number/FDKE6Y2J5KKSRKB7NHSNPSJMZB/graph.json","fetch_events":"https://pith.science/api/pith-number/FDKE6Y2J5KKSRKB7NHSNPSJMZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDKE6Y2J5KKSRKB7NHSNPSJMZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDKE6Y2J5KKSRKB7NHSNPSJMZB/action/storage_attestation","attest_author":"https://pith.science/pith/FDKE6Y2J5KKSRKB7NHSNPSJMZB/action/author_attestation","sign_citation":"https://pith.science/pith/FDKE6Y2J5KKSRKB7NHSNPSJMZB/action/citation_signature","submit_replication":"https://pith.science/pith/FDKE6Y2J5KKSRKB7NHSNPSJMZB/action/replication_record"}},"created_at":"2026-07-05T05:34:48.691770+00:00","updated_at":"2026-07-05T05:34:48.691770+00:00"}