{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MBSXNRFQBNW565XCYKTZBO2B7W","short_pith_number":"pith:MBSXNRFQ","schema_version":"1.0","canonical_sha256":"606576c4b00b6ddf76e2c2a790bb41fdb13412481c535476ff31408b61cc4bf3","source":{"kind":"arxiv","id":"2507.22080","version":1},"attestation_state":"computed","paper":{"title":"CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Fei Yuan, Jinyang Gong, Lei Li, Qipeng Guo, Qiushi Sun","submitted_at":"2025-07-25T16:12:51Z","abstract_excerpt":"Acquiring high-quality instruction-code pairs is essential for training Large Language Models (LLMs) for code generation. Manually curated data is expensive and inherently limited in scale, motivating the development of code-centric synthesis methods. Yet, current approaches either focus on augmenting existing code or rely on predefined heuristics, both lacking rigorous data validation, which results in synthetic data that is ungrounded, repetitive, or overly simplistic. Inspired by collaborative programming practices, we propose CodeEvo, a framework that synthesizes code data through iterativ"},"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":"2507.22080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-25T16:12:51Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"6e3389878744f3b980dd9d75058039b512f4f385253f12a26924a047606af659","abstract_canon_sha256":"142293b396f1685f29a754883d77aede58ccd0bf0137180529f884feb3184b9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:16.148010Z","signature_b64":"u1yzRfS9leU3Co39EX/o1FUm/LhHUDvvakUKOgtSwDIFl2SzC4wKoscEeifuon4vnRYa27z9FUldo8pfQ6H9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"606576c4b00b6ddf76e2c2a790bb41fdb13412481c535476ff31408b61cc4bf3","last_reissued_at":"2026-07-05T11:45:16.147586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:16.147586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Fei Yuan, Jinyang Gong, Lei Li, Qipeng Guo, Qiushi Sun","submitted_at":"2025-07-25T16:12:51Z","abstract_excerpt":"Acquiring high-quality instruction-code pairs is essential for training Large Language Models (LLMs) for code generation. Manually curated data is expensive and inherently limited in scale, motivating the development of code-centric synthesis methods. Yet, current approaches either focus on augmenting existing code or rely on predefined heuristics, both lacking rigorous data validation, which results in synthetic data that is ungrounded, repetitive, or overly simplistic. Inspired by collaborative programming practices, we propose CodeEvo, a framework that synthesizes code data through iterativ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22080","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/2507.22080/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":"2507.22080","created_at":"2026-07-05T11:45:16.147642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22080v1","created_at":"2026-07-05T11:45:16.147642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22080","created_at":"2026-07-05T11:45:16.147642+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBSXNRFQBNW5","created_at":"2026-07-05T11:45:16.147642+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBSXNRFQBNW565XC","created_at":"2026-07-05T11:45:16.147642+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBSXNRFQ","created_at":"2026-07-05T11:45:16.147642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.01286","citing_title":"BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MBSXNRFQBNW565XCYKTZBO2B7W","json":"https://pith.science/pith/MBSXNRFQBNW565XCYKTZBO2B7W.json","graph_json":"https://pith.science/api/pith-number/MBSXNRFQBNW565XCYKTZBO2B7W/graph.json","events_json":"https://pith.science/api/pith-number/MBSXNRFQBNW565XCYKTZBO2B7W/events.json","paper":"https://pith.science/paper/MBSXNRFQ"},"agent_actions":{"view_html":"https://pith.science/pith/MBSXNRFQBNW565XCYKTZBO2B7W","download_json":"https://pith.science/pith/MBSXNRFQBNW565XCYKTZBO2B7W.json","view_paper":"https://pith.science/paper/MBSXNRFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22080&json=true","fetch_graph":"https://pith.science/api/pith-number/MBSXNRFQBNW565XCYKTZBO2B7W/graph.json","fetch_events":"https://pith.science/api/pith-number/MBSXNRFQBNW565XCYKTZBO2B7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBSXNRFQBNW565XCYKTZBO2B7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBSXNRFQBNW565XCYKTZBO2B7W/action/storage_attestation","attest_author":"https://pith.science/pith/MBSXNRFQBNW565XCYKTZBO2B7W/action/author_attestation","sign_citation":"https://pith.science/pith/MBSXNRFQBNW565XCYKTZBO2B7W/action/citation_signature","submit_replication":"https://pith.science/pith/MBSXNRFQBNW565XCYKTZBO2B7W/action/replication_record"}},"created_at":"2026-07-05T11:45:16.147642+00:00","updated_at":"2026-07-05T11:45:16.147642+00:00"}