{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OTPIGV5MQSNMHE2D76GPU2DCJD","short_pith_number":"pith:OTPIGV5M","schema_version":"1.0","canonical_sha256":"74de8357ac849ac39343ff8cfa686248f45590ac629fc08ee6cf0832e83ff813","source":{"kind":"arxiv","id":"2607.29468","version":1},"attestation_state":"computed","paper":{"title":"Self-Play Meets Skill Evolution: Self-Evolving Search Agents that Pose, Solve, and Remember","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ante Wang, Changwei Wang, Chenxu Zhao, Guannan He, Haoyu Wu, Minghui Wu, Qiuyuan Ai, Zenghuang Fu, Zhaoyang Li","submitted_at":"2026-07-31T14:32:52Z","abstract_excerpt":"Self-play agents can generate training problems without questions from target benchmarks, but their curricula lack persistent state: failures affect gradients yet do not explicitly shape future practice. External skill memories preserve procedural experience but are typically learned from fixed task distributions. We introduce \\textbf{SESA} (Self-Evolving Skill-Augmented Agent), which makes procedural memory an evolving state of tool-augmented search self-play. A challenger poses problems, while a separately parameterized solver alone retrieves skills. Informative failures are distilled into r"},"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":"2607.29468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-31T14:32:52Z","cross_cats_sorted":[],"title_canon_sha256":"1b4137bba26b70ba1f3be1362f7e9aa2ff0a737a8df70075eebdf7619607541a","abstract_canon_sha256":"7412c28fc84b761eaf86e1fcd3d76632e4ee50939b15f5abf19faab5cef7b418"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:35:17.571575Z","signature_b64":"ZHedST4Kqo6dzueF+DY9bKe3cVlGktsjuPi0NoVj0J8/N+FKzfFMOKwv1VXSO/iBIdfeKWhpd7Fhwe20iEPfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74de8357ac849ac39343ff8cfa686248f45590ac629fc08ee6cf0832e83ff813","last_reissued_at":"2026-08-03T01:35:17.569874Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:35:17.569874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Play Meets Skill Evolution: Self-Evolving Search Agents that Pose, Solve, and Remember","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ante Wang, Changwei Wang, Chenxu Zhao, Guannan He, Haoyu Wu, Minghui Wu, Qiuyuan Ai, Zenghuang Fu, Zhaoyang Li","submitted_at":"2026-07-31T14:32:52Z","abstract_excerpt":"Self-play agents can generate training problems without questions from target benchmarks, but their curricula lack persistent state: failures affect gradients yet do not explicitly shape future practice. External skill memories preserve procedural experience but are typically learned from fixed task distributions. We introduce \\textbf{SESA} (Self-Evolving Skill-Augmented Agent), which makes procedural memory an evolving state of tool-augmented search self-play. A challenger poses problems, while a separately parameterized solver alone retrieves skills. Informative failures are distilled into r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29468","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/2607.29468/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":"2607.29468","created_at":"2026-08-03T01:35:17.570814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.29468v1","created_at":"2026-08-03T01:35:17.570814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29468","created_at":"2026-08-03T01:35:17.570814+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTPIGV5MQSNM","created_at":"2026-08-03T01:35:17.570814+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTPIGV5MQSNMHE2D","created_at":"2026-08-03T01:35:17.570814+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTPIGV5M","created_at":"2026-08-03T01:35:17.570814+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/OTPIGV5MQSNMHE2D76GPU2DCJD","json":"https://pith.science/pith/OTPIGV5MQSNMHE2D76GPU2DCJD.json","graph_json":"https://pith.science/api/pith-number/OTPIGV5MQSNMHE2D76GPU2DCJD/graph.json","events_json":"https://pith.science/api/pith-number/OTPIGV5MQSNMHE2D76GPU2DCJD/events.json","paper":"https://pith.science/paper/OTPIGV5M"},"agent_actions":{"view_html":"https://pith.science/pith/OTPIGV5MQSNMHE2D76GPU2DCJD","download_json":"https://pith.science/pith/OTPIGV5MQSNMHE2D76GPU2DCJD.json","view_paper":"https://pith.science/paper/OTPIGV5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.29468&json=true","fetch_graph":"https://pith.science/api/pith-number/OTPIGV5MQSNMHE2D76GPU2DCJD/graph.json","fetch_events":"https://pith.science/api/pith-number/OTPIGV5MQSNMHE2D76GPU2DCJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTPIGV5MQSNMHE2D76GPU2DCJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTPIGV5MQSNMHE2D76GPU2DCJD/action/storage_attestation","attest_author":"https://pith.science/pith/OTPIGV5MQSNMHE2D76GPU2DCJD/action/author_attestation","sign_citation":"https://pith.science/pith/OTPIGV5MQSNMHE2D76GPU2DCJD/action/citation_signature","submit_replication":"https://pith.science/pith/OTPIGV5MQSNMHE2D76GPU2DCJD/action/replication_record"}},"created_at":"2026-08-03T01:35:17.570814+00:00","updated_at":"2026-08-03T01:35:17.570814+00:00"}