{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3VKKQVT75BHIQHFO64FRYPILIE","short_pith_number":"pith:3VKKQVT7","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"},"canonical_sha256":"dd54a8567fe84e881caef70b1c3d0b4112598d8f2b5d7ce31750a9fc90f6e5e4","source":{"kind":"arxiv","id":"2607.06140","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06140","created_at":"2026-07-08T01:18:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06140v1","created_at":"2026-07-08T01:18:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06140","created_at":"2026-07-08T01:18:58Z"},{"alias_kind":"pith_short_12","alias_value":"3VKKQVT75BHI","created_at":"2026-07-08T01:18:58Z"},{"alias_kind":"pith_short_16","alias_value":"3VKKQVT75BHIQHFO","created_at":"2026-07-08T01:18:58Z"},{"alias_kind":"pith_short_8","alias_value":"3VKKQVT7","created_at":"2026-07-08T01:18:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3VKKQVT75BHIQHFO64FRYPILIE","target":"record","payload":{"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"},"canonical_sha256":"dd54a8567fe84e881caef70b1c3d0b4112598d8f2b5d7ce31750a9fc90f6e5e4","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"},"source_kind":"arxiv","source_id":"2607.06140","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-08T01:18:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fLRQ6vJNN6ui1KM4DoynR5Y2zWu6L4NmQ1Ue09bcmzCHK8ncdpRdAbbZ4PYzWEPZm7jJuiZwRSenTmbCFbzeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T06:17:21.402636Z"},"content_sha256":"5c4b390551b390a358a89649b990624fd175f47d71eb61192e47d0285d87554a","schema_version":"1.0","event_id":"sha256:5c4b390551b390a358a89649b990624fd175f47d71eb61192e47d0285d87554a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3VKKQVT75BHIQHFO64FRYPILIE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-08T01:18:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m3bi2AO6+p2AHNFRU1wcpe40Zk5oOipYTmiX2Waj60VX1Wdj/B/WNGWputALvNyFoubY/u2Een1kCzUv7EOUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T06:17:21.403013Z"},"content_sha256":"6eb4ef8981757db0666721d9a33c12d5730a8b328c0cb24adce3d0ed157404da","schema_version":"1.0","event_id":"sha256:6eb4ef8981757db0666721d9a33c12d5730a8b328c0cb24adce3d0ed157404da"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:3VKKQVT75BHIQHFO64FRYPILIE","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2024.findings-acl.557.URL) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Zehui Chen, Kuikun Liu, Qiuchen Wang, Wenwei Zhang, Jiangning Liu, Dahua Lin, Kai Chen, and Feng Zhao. Agent-FLAN: Designing data and methods of effective agent tuning for large language models. In Lun-Wei Ku, Andre Martins, and Vivek Sriku","arxiv_id":"2607.06140","detector":"doi_compliance","evidence":{"ref_index":6,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Zehui Chen, Kuikun Liu, Qiuchen Wang, Wenwei Zhang, Jiangning Liu, Dahua Lin, Kai Chen, and Feng Zhao. Agent-FLAN: Designing data and methods of effective agent tuning for large language models. In Lun-Wei Ku, Andre Martins, and Vivek Sriku","reconstructed_doi":"10.18653/v1/2024.findings-acl.557.URL"},"severity":"advisory","ref_index":6,"audited_at":"2026-07-09T07:40:58.326755Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2024.findings-acl.557.URL","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"5ce45987d9124b4ab1d4b009f7bec8cf7e43eecd8eedb22884eca06cdb886afc","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":7814,"payload_sha256":"82ae2c425b9550dadd74f2e4041d4c14fb8a5ef4c14acfc7b110081b9326011d","signature_b64":"ALCraVtLMmCt7ej2jzsVunLMOswse1mm+495mKFST3QTqzSR2BQ5CJWt3ikM82fC4BsyHBZpWIZJH/OWfBfbDw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-09T07:42:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ETNmOU8yU7ldd1Meb/DS2rlJesoRvKQ+yzKKXb+y+I+XY8cApoL6aVLL8wr+wZbVOOFnWzV3k7gD8f3ahdLOCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T06:17:21.404893Z"},"content_sha256":"5895f8d59889a443ca845bc4851906aafe57ede54a6790357afa9746409db33c","schema_version":"1.0","event_id":"sha256:5895f8d59889a443ca845bc4851906aafe57ede54a6790357afa9746409db33c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3VKKQVT75BHIQHFO64FRYPILIE/bundle.json","state_url":"https://pith.science/pith/3VKKQVT75BHIQHFO64FRYPILIE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3VKKQVT75BHIQHFO64FRYPILIE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-25T06:17:21Z","links":{"resolver":"https://pith.science/pith/3VKKQVT75BHIQHFO64FRYPILIE","bundle":"https://pith.science/pith/3VKKQVT75BHIQHFO64FRYPILIE/bundle.json","state":"https://pith.science/pith/3VKKQVT75BHIQHFO64FRYPILIE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3VKKQVT75BHIQHFO64FRYPILIE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3VKKQVT75BHIQHFO64FRYPILIE","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a150e9a56ac112073eac1a5c29805f9fc3fab4e2150428cfdddf826460c3bef2","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-07T11:07:00Z","title_canon_sha256":"3301f9aae97d1a7c99a6604740217f88191d42eaf7ab46a1a1e75b0c8ef6a3c0"},"schema_version":"1.0","source":{"id":"2607.06140","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06140","created_at":"2026-07-08T01:18:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06140v1","created_at":"2026-07-08T01:18:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06140","created_at":"2026-07-08T01:18:58Z"},{"alias_kind":"pith_short_12","alias_value":"3VKKQVT75BHI","created_at":"2026-07-08T01:18:58Z"},{"alias_kind":"pith_short_16","alias_value":"3VKKQVT75BHIQHFO","created_at":"2026-07-08T01:18:58Z"},{"alias_kind":"pith_short_8","alias_value":"3VKKQVT7","created_at":"2026-07-08T01:18:58Z"}],"graph_snapshots":[{"event_id":"sha256:6eb4ef8981757db0666721d9a33c12d5730a8b328c0cb24adce3d0ed157404da","target":"graph","created_at":"2026-07-08T01:18:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.06140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Dingzirui Wang, Keyan Xu, Qingfu Zhu, Wanxiang Che, Xuanliang Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-07T11:07:00Z","title":"CurateEvo: Data-Curation Evolving for Agentic Post-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06140","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5c4b390551b390a358a89649b990624fd175f47d71eb61192e47d0285d87554a","target":"record","created_at":"2026-07-08T01:18:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a150e9a56ac112073eac1a5c29805f9fc3fab4e2150428cfdddf826460c3bef2","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-07T11:07:00Z","title_canon_sha256":"3301f9aae97d1a7c99a6604740217f88191d42eaf7ab46a1a1e75b0c8ef6a3c0"},"schema_version":"1.0","source":{"id":"2607.06140","kind":"arxiv","version":1}},"canonical_sha256":"dd54a8567fe84e881caef70b1c3d0b4112598d8f2b5d7ce31750a9fc90f6e5e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd54a8567fe84e881caef70b1c3d0b4112598d8f2b5d7ce31750a9fc90f6e5e4","first_computed_at":"2026-07-08T01:18:58.245732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:18:58.245732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hj+ziezeCt1t+cI/sDnjRo2xnZnrD1xNk1uQajv0dRz6LP493TAm3bM40vjwi6nQ5k7JyCbShhwe2nCEhXa1Cw==","signature_status":"signed_v1","signed_at":"2026-07-08T01:18:58.246156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.06140","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c4b390551b390a358a89649b990624fd175f47d71eb61192e47d0285d87554a","sha256:6eb4ef8981757db0666721d9a33c12d5730a8b328c0cb24adce3d0ed157404da","sha256:5895f8d59889a443ca845bc4851906aafe57ede54a6790357afa9746409db33c"],"state_sha256":"f75cd3da40059811e24f0bf9d2f14430c7e11d8241e03b282442602e0d6fb92a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X0q9iGHWYPYNCRkRSgMK6c0Ojx2IAdeWfjQ0ghIKwN/HOeDkM9uXysQUcc8K+JzOdUdURn6T1TJCWRyN3ETHDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T06:17:21.406295Z","bundle_sha256":"c9f54fa404ece70cb7f6a1b5908ade47e5c521c22bc3676b04af8fb61470ad0d"}}