{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DHKKTGVD2EBBMIE4ZTF4CFULXW","short_pith_number":"pith:DHKKTGVD","schema_version":"1.0","canonical_sha256":"19d4a99aa3d10216209ccccbc1168bbd815e6275e52f05350871e36672a00144","source":{"kind":"arxiv","id":"2507.00014","version":1},"attestation_state":"computed","paper":{"title":"SWE-Bench-CL: Continual Learning for Coding Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.LG","authors_text":"Fatih Uysal, Shayan Chowdhury, Thomas Joshi","submitted_at":"2025-06-13T07:11:14Z","abstract_excerpt":"Large Language Models (LLMs) have achieved impressive results on static code-generation benchmarks, but real-world software development unfolds as a continuous stream of evolving issues, fixes, and feature requests. We introduce SWE-Bench-CL, a novel continual learning benchmark built on the human-verified SWE-Bench Verified dataset introduced by OpenAI and Princeton-NLP in 2024. By organizing GitHub issues into chronologically ordered sequences that reflect natural repository evolution, SWE-Bench-CL enables direct evaluation of an agent's ability to accumulate experience, transfer knowledge a"},"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":"2507.00014","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-13T07:11:14Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"c44665155b6ed135d3094db6fa4754ef836f452acaef94fdda300ce926103254","abstract_canon_sha256":"620f4864e282793297fae36adbff97752a9095f5af216bbe902f3c3f3cc47f2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:04.436680Z","signature_b64":"W8iCXJOqs5WBxSlqiwvKg2gtj3rmdvJtZX5atB6iJppAu1LFbS4rIoq0jcvDPJZQg8UL13oadfz6lXvqBWrtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19d4a99aa3d10216209ccccbc1168bbd815e6275e52f05350871e36672a00144","last_reissued_at":"2026-07-05T11:30:04.436184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:04.436184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SWE-Bench-CL: Continual Learning for Coding Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.LG","authors_text":"Fatih Uysal, Shayan Chowdhury, Thomas Joshi","submitted_at":"2025-06-13T07:11:14Z","abstract_excerpt":"Large Language Models (LLMs) have achieved impressive results on static code-generation benchmarks, but real-world software development unfolds as a continuous stream of evolving issues, fixes, and feature requests. We introduce SWE-Bench-CL, a novel continual learning benchmark built on the human-verified SWE-Bench Verified dataset introduced by OpenAI and Princeton-NLP in 2024. By organizing GitHub issues into chronologically ordered sequences that reflect natural repository evolution, SWE-Bench-CL enables direct evaluation of an agent's ability to accumulate experience, transfer knowledge a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00014","kind":"arxiv","version":1},"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/2507.00014/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":"2507.00014","created_at":"2026-07-05T11:30:04.436242+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00014v1","created_at":"2026-07-05T11:30:04.436242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00014","created_at":"2026-07-05T11:30:04.436242+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHKKTGVD2EBB","created_at":"2026-07-05T11:30:04.436242+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHKKTGVD2EBBMIE4","created_at":"2026-07-05T11:30:04.436242+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHKKTGVD","created_at":"2026-07-05T11:30:04.436242+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05661","citing_title":"Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02461","citing_title":"AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26275","citing_title":"Agentic AI in the Software Development Lifecycle: Architecture, Empirical Evidence, and the Reshaping of Software Engineering","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09315","citing_title":"Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DHKKTGVD2EBBMIE4ZTF4CFULXW","json":"https://pith.science/pith/DHKKTGVD2EBBMIE4ZTF4CFULXW.json","graph_json":"https://pith.science/api/pith-number/DHKKTGVD2EBBMIE4ZTF4CFULXW/graph.json","events_json":"https://pith.science/api/pith-number/DHKKTGVD2EBBMIE4ZTF4CFULXW/events.json","paper":"https://pith.science/paper/DHKKTGVD"},"agent_actions":{"view_html":"https://pith.science/pith/DHKKTGVD2EBBMIE4ZTF4CFULXW","download_json":"https://pith.science/pith/DHKKTGVD2EBBMIE4ZTF4CFULXW.json","view_paper":"https://pith.science/paper/DHKKTGVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00014&json=true","fetch_graph":"https://pith.science/api/pith-number/DHKKTGVD2EBBMIE4ZTF4CFULXW/graph.json","fetch_events":"https://pith.science/api/pith-number/DHKKTGVD2EBBMIE4ZTF4CFULXW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHKKTGVD2EBBMIE4ZTF4CFULXW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHKKTGVD2EBBMIE4ZTF4CFULXW/action/storage_attestation","attest_author":"https://pith.science/pith/DHKKTGVD2EBBMIE4ZTF4CFULXW/action/author_attestation","sign_citation":"https://pith.science/pith/DHKKTGVD2EBBMIE4ZTF4CFULXW/action/citation_signature","submit_replication":"https://pith.science/pith/DHKKTGVD2EBBMIE4ZTF4CFULXW/action/replication_record"}},"created_at":"2026-07-05T11:30:04.436242+00:00","updated_at":"2026-07-05T11:30:04.436242+00:00"}