{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3VKKQVT75BHIQHFO64FRYPILIE","short_pith_number":"pith:3VKKQVT7","schema_version":"1.0","canonical_sha256":"dd54a8567fe84e881caef70b1c3d0b4112598d8f2b5d7ce31750a9fc90f6e5e4","source":{"kind":"arxiv","id":"2607.06140","version":1},"attestation_state":"computed","paper":{"title":"CurateEvo: Data-Curation Evolving for Agentic Post-Training","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dingzirui Wang, Keyan Xu, Qingfu Zhu, Wanxiang Che, Xuanliang Zhang","submitted_at":"2026-07-07T11:07:00Z","abstract_excerpt":"Large language model (LLM) agents require post-training methods that can improve long-horizon decision making from environment feedback. However, existing agentic post-training pipelines often treat data curation as a fixed preprocessing step, focusing mainly on data augmentation while neglecting filtering, refinement, and adaptation to downstream failures. We propose CurateEvo, a failure-driven dynamic evolution framework for agentic post-training data curation. CurateEvo represents the curation strategy as executable code and iteratively rewrites it using failed trajectories from a held-out "},"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":"2607.06140","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-07T11:07:00Z","cross_cats_sorted":[],"title_canon_sha256":"3301f9aae97d1a7c99a6604740217f88191d42eaf7ab46a1a1e75b0c8ef6a3c0","abstract_canon_sha256":"a150e9a56ac112073eac1a5c29805f9fc3fab4e2150428cfdddf826460c3bef2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:58.246156Z","signature_b64":"hj+ziezeCt1t+cI/sDnjRo2xnZnrD1xNk1uQajv0dRz6LP493TAm3bM40vjwi6nQ5k7JyCbShhwe2nCEhXa1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd54a8567fe84e881caef70b1c3d0b4112598d8f2b5d7ce31750a9fc90f6e5e4","last_reissued_at":"2026-07-08T01:18:58.245732Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:58.245732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CurateEvo: Data-Curation Evolving for Agentic Post-Training","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dingzirui Wang, Keyan Xu, Qingfu Zhu, Wanxiang Che, Xuanliang Zhang","submitted_at":"2026-07-07T11:07:00Z","abstract_excerpt":"Large language model (LLM) agents require post-training methods that can improve long-horizon decision making from environment feedback. However, existing agentic post-training pipelines often treat data curation as a fixed preprocessing step, focusing mainly on data augmentation while neglecting filtering, refinement, and adaptation to downstream failures. We propose CurateEvo, a failure-driven dynamic evolution framework for agentic post-training data curation. CurateEvo represents the curation strategy as executable code and iteratively rewrites it using failed trajectories from a held-out "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06140","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/2607.06140/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":"2607.06140","created_at":"2026-07-08T01:18:58.245792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06140v1","created_at":"2026-07-08T01:18:58.245792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06140","created_at":"2026-07-08T01:18:58.245792+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VKKQVT75BHI","created_at":"2026-07-08T01:18:58.245792+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VKKQVT75BHIQHFO","created_at":"2026-07-08T01:18:58.245792+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VKKQVT7","created_at":"2026-07-08T01:18:58.245792+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/3VKKQVT75BHIQHFO64FRYPILIE","json":"https://pith.science/pith/3VKKQVT75BHIQHFO64FRYPILIE.json","graph_json":"https://pith.science/api/pith-number/3VKKQVT75BHIQHFO64FRYPILIE/graph.json","events_json":"https://pith.science/api/pith-number/3VKKQVT75BHIQHFO64FRYPILIE/events.json","paper":"https://pith.science/paper/3VKKQVT7"},"agent_actions":{"view_html":"https://pith.science/pith/3VKKQVT75BHIQHFO64FRYPILIE","download_json":"https://pith.science/pith/3VKKQVT75BHIQHFO64FRYPILIE.json","view_paper":"https://pith.science/paper/3VKKQVT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06140&json=true","fetch_graph":"https://pith.science/api/pith-number/3VKKQVT75BHIQHFO64FRYPILIE/graph.json","fetch_events":"https://pith.science/api/pith-number/3VKKQVT75BHIQHFO64FRYPILIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VKKQVT75BHIQHFO64FRYPILIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VKKQVT75BHIQHFO64FRYPILIE/action/storage_attestation","attest_author":"https://pith.science/pith/3VKKQVT75BHIQHFO64FRYPILIE/action/author_attestation","sign_citation":"https://pith.science/pith/3VKKQVT75BHIQHFO64FRYPILIE/action/citation_signature","submit_replication":"https://pith.science/pith/3VKKQVT75BHIQHFO64FRYPILIE/action/replication_record"}},"created_at":"2026-07-08T01:18:58.245792+00:00","updated_at":"2026-07-08T01:18:58.245792+00:00"}