{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4VXRV7TME7TH6LGQPDKEGPSR2N","short_pith_number":"pith:4VXRV7TM","schema_version":"1.0","canonical_sha256":"e56f1afe6c27e67f2cd078d4433e51d372e81a11232e723acae74fd700f72dcd","source":{"kind":"arxiv","id":"2608.03764","version":1},"attestation_state":"computed","paper":{"title":"GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Buyue Qian, Chenxu Liu, Jingzhe Xu, Junhao Hu, Leijun Zhou, Xiang Qu, Xi Chen, Xuejun Wu, Yanke Yu, Yaowei Zheng, Yifei Liu, Zhihao Liu","submitted_at":"2026-08-04T14:51:56Z","abstract_excerpt":"Agent self-evolution updates an agent's persistent state from prior experience and reuses it to solve related tasks more effectively. Evaluating self-evolution is difficult: existing benchmarks provide limited coverage of economically valuable task domains, do not always design training and test tasks such that test-time gains can be attributed to training experience, and remain vulnerable to data contamination. We present GDPevo, an evolution-native benchmark grounded in GDP-related enterprise workflows, together with the fully automated data pipeline that generates it. Its core mechanism, ru"},"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":"2608.03764","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T14:51:56Z","cross_cats_sorted":[],"title_canon_sha256":"a4b1a05380ddb04b96e05123235dbad6f4e02be86cf864fbf5bbc6dd520b5fc7","abstract_canon_sha256":"c110f08d7d7c3d78ae8e62c4bdcb751997de2ebaf1d471748acabd827fbdc8d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:37:03.092476Z","signature_b64":"YVqLAJsGhSx7uZ0ZmlhtaywgKKjQuUxMtXWaMrBfHJmOGf9RcOKzNhvuAMO1VQY+qCjOW6EH/SDyxJbOOFA+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e56f1afe6c27e67f2cd078d4433e51d372e81a11232e723acae74fd700f72dcd","last_reissued_at":"2026-08-05T01:37:03.090999Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:37:03.090999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Buyue Qian, Chenxu Liu, Jingzhe Xu, Junhao Hu, Leijun Zhou, Xiang Qu, Xi Chen, Xuejun Wu, Yanke Yu, Yaowei Zheng, Yifei Liu, Zhihao Liu","submitted_at":"2026-08-04T14:51:56Z","abstract_excerpt":"Agent self-evolution updates an agent's persistent state from prior experience and reuses it to solve related tasks more effectively. Evaluating self-evolution is difficult: existing benchmarks provide limited coverage of economically valuable task domains, do not always design training and test tasks such that test-time gains can be attributed to training experience, and remain vulnerable to data contamination. We present GDPevo, an evolution-native benchmark grounded in GDP-related enterprise workflows, together with the fully automated data pipeline that generates it. Its core mechanism, ru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03764","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/2608.03764/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":"2608.03764","created_at":"2026-08-05T01:37:03.091516+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03764v1","created_at":"2026-08-05T01:37:03.091516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03764","created_at":"2026-08-05T01:37:03.091516+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VXRV7TME7TH","created_at":"2026-08-05T01:37:03.091516+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VXRV7TME7TH6LGQ","created_at":"2026-08-05T01:37:03.091516+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VXRV7TM","created_at":"2026-08-05T01:37:03.091516+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/4VXRV7TME7TH6LGQPDKEGPSR2N","json":"https://pith.science/pith/4VXRV7TME7TH6LGQPDKEGPSR2N.json","graph_json":"https://pith.science/api/pith-number/4VXRV7TME7TH6LGQPDKEGPSR2N/graph.json","events_json":"https://pith.science/api/pith-number/4VXRV7TME7TH6LGQPDKEGPSR2N/events.json","paper":"https://pith.science/paper/4VXRV7TM"},"agent_actions":{"view_html":"https://pith.science/pith/4VXRV7TME7TH6LGQPDKEGPSR2N","download_json":"https://pith.science/pith/4VXRV7TME7TH6LGQPDKEGPSR2N.json","view_paper":"https://pith.science/paper/4VXRV7TM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03764&json=true","fetch_graph":"https://pith.science/api/pith-number/4VXRV7TME7TH6LGQPDKEGPSR2N/graph.json","fetch_events":"https://pith.science/api/pith-number/4VXRV7TME7TH6LGQPDKEGPSR2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VXRV7TME7TH6LGQPDKEGPSR2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VXRV7TME7TH6LGQPDKEGPSR2N/action/storage_attestation","attest_author":"https://pith.science/pith/4VXRV7TME7TH6LGQPDKEGPSR2N/action/author_attestation","sign_citation":"https://pith.science/pith/4VXRV7TME7TH6LGQPDKEGPSR2N/action/citation_signature","submit_replication":"https://pith.science/pith/4VXRV7TME7TH6LGQPDKEGPSR2N/action/replication_record"}},"created_at":"2026-08-05T01:37:03.091516+00:00","updated_at":"2026-08-05T01:37:03.091516+00:00"}