{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2EN5SFX37SOYDGCALPOK2SJT7N","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"783298585e6f890ae235f900a06960b87ede3901e61ba72139a6335e8622dd56","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-02T22:51:12Z","title_canon_sha256":"55b1277c091e6a549f87e7fc1fec39f497835aa99f5d2afe33829163e8f4ba57"},"schema_version":"1.0","source":{"id":"2503.01052","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01052","created_at":"2026-07-05T11:01:56Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01052v2","created_at":"2026-07-05T11:01:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01052","created_at":"2026-07-05T11:01:56Z"},{"alias_kind":"pith_short_12","alias_value":"2EN5SFX37SOY","created_at":"2026-07-05T11:01:56Z"},{"alias_kind":"pith_short_16","alias_value":"2EN5SFX37SOYDGCA","created_at":"2026-07-05T11:01:56Z"},{"alias_kind":"pith_short_8","alias_value":"2EN5SFX3","created_at":"2026-07-05T11:01:56Z"}],"graph_snapshots":[{"event_id":"sha256:11fa8d27f488914334817e9c86cb380fa6f4bc81a151bff05d5d0f9ef46153da","target":"graph","created_at":"2026-07-05T11:01:56Z","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/2503.01052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) heavily rely on high-quality training data, making data valuation crucial for optimizing model performance, especially when working within a limited budget. In this work, we aim to offer a third-party data valuation approach that benefits both data providers and model developers. We introduce a linearized future influence kernel (LinFiK), which assesses the value of individual data samples in improving LLM performance during training. We further propose ALinFiK, a learning strategy to approximate LinFiK, enabling scalable data valuation. Our comprehensive evaluatio","authors_text":"Denghui Zhang, Huawei Lin, Jiamin Chen, Weijie Zhao, Xiaodong Yu, Yanzhou Pan, Yide Ran, Zhaozhuo Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-02T22:51:12Z","title":"ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Party LLM Data Valuation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01052","kind":"arxiv","version":2},"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":"sha256:0db6bc0a8f4164c7ef424e02e6ff1dc1de8b95e82c88dd5f5ec57cc80538aa25","target":"record","created_at":"2026-07-05T11:01:56Z","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":"783298585e6f890ae235f900a06960b87ede3901e61ba72139a6335e8622dd56","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-02T22:51:12Z","title_canon_sha256":"55b1277c091e6a549f87e7fc1fec39f497835aa99f5d2afe33829163e8f4ba57"},"schema_version":"1.0","source":{"id":"2503.01052","kind":"arxiv","version":2}},"canonical_sha256":"d11bd916fbfc9d8198405bdcad4933fb74d0ecd839540308a3c2ed41ae9386bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d11bd916fbfc9d8198405bdcad4933fb74d0ecd839540308a3c2ed41ae9386bf","first_computed_at":"2026-07-05T11:01:56.884956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:56.884956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rg2szGZEIggQojrIuEiHl1J5RwO6fUAEOWTo1gxODVK6ZC11mItN33TcAM0KNVgKA7cCUIJNRjK/iQwMSvZNBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:56.885470Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01052","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0db6bc0a8f4164c7ef424e02e6ff1dc1de8b95e82c88dd5f5ec57cc80538aa25","sha256:11fa8d27f488914334817e9c86cb380fa6f4bc81a151bff05d5d0f9ef46153da"],"state_sha256":"cb5501f40afcc43871a4942c3c9b84cff5ae7b88b231542938845559bdbe3656"}