{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5VJO5CX6STWOBXEPYGZA4LUWZR","short_pith_number":"pith:5VJO5CX6","schema_version":"1.0","canonical_sha256":"ed52ee8afe94ece0dc8fc1b20e2e96cc6e185d861fedae342f6f32094e733c98","source":{"kind":"arxiv","id":"2508.12232","version":5},"attestation_state":"computed","paper":{"title":"LinkAnchor: An Autonomous LLM-Based Agent for Issue-to-Commit Link Recovery","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"LinkAnchor recovers issue-to-commit links using an LLM agent that lazily fetches only needed context instead of checking every pair.","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Abbas Heydarnoori, Alireza Hoseinpour, Arshia Akhavan, Hamid Bagheri, Mehdi Keshani","submitted_at":"2025-08-17T04:21:44Z","abstract_excerpt":"Issue-to-commit link recovery in software repositories is fundamental to software traceability and project management, yet it remains a challenging task. Prior studies show that only about 42.2% of issues on GitHub are correctly linked to their commits, highlighting the need for more effective solutions. Existing work has explored a range of ML/DL approaches, and more recently, large language models (LLMs) have been applied to this problem. However, these methods face two major limitations. First, LLMs are restricted by limited context windows and cannot simultaneously process all available da"},"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":true},"canonical_record":{"source":{"id":"2508.12232","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-08-17T04:21:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"781438f21c297246ef34f796fdccce148fcebbe779b5aeb41013c90379529516","abstract_canon_sha256":"fe219c0fcf90060eeb67c2fa6b088e082b524eb4e29d8d3f1315cc560a6cae8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:15:03.005756Z","signature_b64":"YKZzI/QF5GvaTIzcYd1RCsq8D3eP0b3JzPgolfmi4FiFQ3bK1KUqLeJD4/BeSrNIr0VrE+yx4NAwcT3H5cHeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed52ee8afe94ece0dc8fc1b20e2e96cc6e185d861fedae342f6f32094e733c98","last_reissued_at":"2026-06-29T01:15:03.005286Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:15:03.005286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LinkAnchor: An Autonomous LLM-Based Agent for Issue-to-Commit Link Recovery","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"LinkAnchor recovers issue-to-commit links using an LLM agent that lazily fetches only needed context instead of checking every pair.","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Abbas Heydarnoori, Alireza Hoseinpour, Arshia Akhavan, Hamid Bagheri, Mehdi Keshani","submitted_at":"2025-08-17T04:21:44Z","abstract_excerpt":"Issue-to-commit link recovery in software repositories is fundamental to software traceability and project management, yet it remains a challenging task. Prior studies show that only about 42.2% of issues on GitHub are correctly linked to their commits, highlighting the need for more effective solutions. Existing work has explored a range of ML/DL approaches, and more recently, large language models (LLMs) have been applied to this problem. However, these methods face two major limitations. First, LLMs are restricted by limited context windows and cannot simultaneously process all available da"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"LinkAnchor is the first autonomous LLM-based agent designed specifically for issue-to-commit link recovery that uses a lazy-access architecture to dynamically retrieve relevant contextual data without exceeding token limits.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that an LLM agent can reliably decide which commits, comments, or code files are relevant to fetch next and that this selective retrieval will capture the complete resolution logic better than exhaustive pairwise evaluation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LinkAnchor is an LLM-based autonomous agent with lazy-access architecture for recovering issue-to-commit links in software repositories.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LinkAnchor recovers issue-to-commit links using an LLM agent that lazily fetches only needed context instead of checking every pair.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fa61e779ccb50e19441f18142537c8e478d83c687f9f8ba4681da9f1ca43ab80"},"source":{"id":"2508.12232","kind":"arxiv","version":5},"verdict":{"id":"ff050520-cf34-4a26-b39c-8e6eec731111","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T22:37:26.088545Z","strongest_claim":"LinkAnchor is the first autonomous LLM-based agent designed specifically for issue-to-commit link recovery that uses a lazy-access architecture to dynamically retrieve relevant contextual data without exceeding token limits.","one_line_summary":"LinkAnchor is an LLM-based autonomous agent with lazy-access architecture for recovering issue-to-commit links in software repositories.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that an LLM agent can reliably decide which commits, comments, or code files are relevant to fetch next and that this selective retrieval will capture the complete resolution logic better than exhaustive pairwise evaluation.","pith_extraction_headline":"LinkAnchor recovers issue-to-commit links using an LLM agent that lazily fetches only needed context instead of checking every pair."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.12232/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":2,"snapshot_sha256":"53e26bf8606cb3d76eb93672f8233bac6c7f96631ab35c12e3848d2a3e73e8ee"},"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":"2508.12232","created_at":"2026-06-29T01:15:03.005346+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.12232v5","created_at":"2026-06-29T01:15:03.005346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12232","created_at":"2026-06-29T01:15:03.005346+00:00"},{"alias_kind":"pith_short_12","alias_value":"5VJO5CX6STWO","created_at":"2026-06-29T01:15:03.005346+00:00"},{"alias_kind":"pith_short_16","alias_value":"5VJO5CX6STWOBXEP","created_at":"2026-06-29T01:15:03.005346+00:00"},{"alias_kind":"pith_short_8","alias_value":"5VJO5CX6","created_at":"2026-06-29T01:15:03.005346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5VJO5CX6STWOBXEPYGZA4LUWZR","json":"https://pith.science/pith/5VJO5CX6STWOBXEPYGZA4LUWZR.json","graph_json":"https://pith.science/api/pith-number/5VJO5CX6STWOBXEPYGZA4LUWZR/graph.json","events_json":"https://pith.science/api/pith-number/5VJO5CX6STWOBXEPYGZA4LUWZR/events.json","paper":"https://pith.science/paper/5VJO5CX6"},"agent_actions":{"view_html":"https://pith.science/pith/5VJO5CX6STWOBXEPYGZA4LUWZR","download_json":"https://pith.science/pith/5VJO5CX6STWOBXEPYGZA4LUWZR.json","view_paper":"https://pith.science/paper/5VJO5CX6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.12232&json=true","fetch_graph":"https://pith.science/api/pith-number/5VJO5CX6STWOBXEPYGZA4LUWZR/graph.json","fetch_events":"https://pith.science/api/pith-number/5VJO5CX6STWOBXEPYGZA4LUWZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5VJO5CX6STWOBXEPYGZA4LUWZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5VJO5CX6STWOBXEPYGZA4LUWZR/action/storage_attestation","attest_author":"https://pith.science/pith/5VJO5CX6STWOBXEPYGZA4LUWZR/action/author_attestation","sign_citation":"https://pith.science/pith/5VJO5CX6STWOBXEPYGZA4LUWZR/action/citation_signature","submit_replication":"https://pith.science/pith/5VJO5CX6STWOBXEPYGZA4LUWZR/action/replication_record"}},"created_at":"2026-06-29T01:15:03.005346+00:00","updated_at":"2026-06-29T01:15:03.005346+00:00"}