{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y5RPZWCKO7WIBYGO6AWB7E2RCH","short_pith_number":"pith:Y5RPZWCK","schema_version":"1.0","canonical_sha256":"c762fcd84a77ec80e0cef02c1f935111e10c59f38a2094119106d5e2b0dff5a9","source":{"kind":"arxiv","id":"2606.07412","version":1},"attestation_state":"computed","paper":{"title":"Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Bing Zhao, Chuan Xiao, Hu Wei, Linfeng Zhang, Lin Qu, Shaobo Wang, Wei Wang, Zhengbo Jiao","submitted_at":"2026-06-05T16:00:17Z","abstract_excerpt":"LLM-driven software engineering agents have become a central testbed for real-world language-model capability, yet their training remains limited by the availability of high-quality SWE tasks. Existing synthetic data methods typically create tasks through fixed mutation or bug-injection procedures, making the resulting distributions largely independent of the agent's own weaknesses and training progress. We introduce Socratic-SWE, a closed-loop self-evolution framework that reuses the agent's historical solving traces as a source of training signal. Rather than treating traces only as evidence"},"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":"2606.07412","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-05T16:00:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"792507a85b03cd47befc114c6095563030caa084a95be47983a801309c05a10b","abstract_canon_sha256":"20c51ed76844d539c80b19a0787e0772fb49a5dcb590a62e2a7bdcb53b4c5787"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:25.524705Z","signature_b64":"KNZUF48wvPEzsyxPI1jb4PTU06nKxx8nsQejMn6YaDGUeroGT3jPVW0v8lC5shOX8oDQvBASmTO5pKEkLSsWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c762fcd84a77ec80e0cef02c1f935111e10c59f38a2094119106d5e2b0dff5a9","last_reissued_at":"2026-06-08T01:05:25.523839Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:25.523839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Bing Zhao, Chuan Xiao, Hu Wei, Linfeng Zhang, Lin Qu, Shaobo Wang, Wei Wang, Zhengbo Jiao","submitted_at":"2026-06-05T16:00:17Z","abstract_excerpt":"LLM-driven software engineering agents have become a central testbed for real-world language-model capability, yet their training remains limited by the availability of high-quality SWE tasks. Existing synthetic data methods typically create tasks through fixed mutation or bug-injection procedures, making the resulting distributions largely independent of the agent's own weaknesses and training progress. We introduce Socratic-SWE, a closed-loop self-evolution framework that reuses the agent's historical solving traces as a source of training signal. Rather than treating traces only as evidence"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07412","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/2606.07412/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":"2606.07412","created_at":"2026-06-08T01:05:25.523993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07412v1","created_at":"2026-06-08T01:05:25.523993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07412","created_at":"2026-06-08T01:05:25.523993+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5RPZWCKO7WI","created_at":"2026-06-08T01:05:25.523993+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5RPZWCKO7WIBYGO","created_at":"2026-06-08T01:05:25.523993+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5RPZWCK","created_at":"2026-06-08T01:05:25.523993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y5RPZWCKO7WIBYGO6AWB7E2RCH","json":"https://pith.science/pith/Y5RPZWCKO7WIBYGO6AWB7E2RCH.json","graph_json":"https://pith.science/api/pith-number/Y5RPZWCKO7WIBYGO6AWB7E2RCH/graph.json","events_json":"https://pith.science/api/pith-number/Y5RPZWCKO7WIBYGO6AWB7E2RCH/events.json","paper":"https://pith.science/paper/Y5RPZWCK"},"agent_actions":{"view_html":"https://pith.science/pith/Y5RPZWCKO7WIBYGO6AWB7E2RCH","download_json":"https://pith.science/pith/Y5RPZWCKO7WIBYGO6AWB7E2RCH.json","view_paper":"https://pith.science/paper/Y5RPZWCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07412&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5RPZWCKO7WIBYGO6AWB7E2RCH/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5RPZWCKO7WIBYGO6AWB7E2RCH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5RPZWCKO7WIBYGO6AWB7E2RCH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5RPZWCKO7WIBYGO6AWB7E2RCH/action/storage_attestation","attest_author":"https://pith.science/pith/Y5RPZWCKO7WIBYGO6AWB7E2RCH/action/author_attestation","sign_citation":"https://pith.science/pith/Y5RPZWCKO7WIBYGO6AWB7E2RCH/action/citation_signature","submit_replication":"https://pith.science/pith/Y5RPZWCKO7WIBYGO6AWB7E2RCH/action/replication_record"}},"created_at":"2026-06-08T01:05:25.523993+00:00","updated_at":"2026-06-08T01:05:25.523993+00:00"}