{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YUAH3OCLOVZLPLUTGVOJN6Y2K4","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":"24600a4a4acee2f675050984c2ae09e97626e7101f4e8fda054fb43c2196c80b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T07:26:24Z","title_canon_sha256":"4f9955f9c99e5a12ee4da5940282bbce83066a7a9ae13e7d999c38b16541fe09"},"schema_version":"1.0","source":{"id":"2310.13008","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13008","created_at":"2026-07-05T09:51:29Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13008v2","created_at":"2026-07-05T09:51:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13008","created_at":"2026-07-05T09:51:29Z"},{"alias_kind":"pith_short_12","alias_value":"YUAH3OCLOVZL","created_at":"2026-07-05T09:51:29Z"},{"alias_kind":"pith_short_16","alias_value":"YUAH3OCLOVZLPLUT","created_at":"2026-07-05T09:51:29Z"},{"alias_kind":"pith_short_8","alias_value":"YUAH3OCL","created_at":"2026-07-05T09:51:29Z"}],"graph_snapshots":[{"event_id":"sha256:2dbc7a6f59060c26858dc1ed09005795a2c2efb9a483b9bf4e77f0e4a047f28d","target":"graph","created_at":"2026-07-05T09:51:29Z","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/2310.13008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce DavIR, a model-based data selection method for post-training Large Language Models. DavIR generalizes Reducible Holdout Loss to core-set selection problem of causal language modeling, and quantifies the learnability of a given datum with respect to a pre-trained LLM based on relative reduction in loss during fine-tuning, a metric we show to be closely related to the implicit reward model described in Direct Preference Optimization (DPO). We show that 6% of Alpaca dataset selected with DavIR can steer both the LLaMA and Gemma model family to produce superior performance compared to","authors_text":"Haotian Zhou, Hongxia Yang, Jianbo Yuan, Pengfei Liu, Qianli Ma, Tingkai Liu, Yang You, Yufeng Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T07:26:24Z","title":"DavIR: Data Selection via Implicit Reward for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13008","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:f12b7281af435944745fee12a6cf5da8f13ddb93c6a5826229334431fb0cacd9","target":"record","created_at":"2026-07-05T09:51:29Z","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":"24600a4a4acee2f675050984c2ae09e97626e7101f4e8fda054fb43c2196c80b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T07:26:24Z","title_canon_sha256":"4f9955f9c99e5a12ee4da5940282bbce83066a7a9ae13e7d999c38b16541fe09"},"schema_version":"1.0","source":{"id":"2310.13008","kind":"arxiv","version":2}},"canonical_sha256":"c5007db84b7572b7ae93355c96fb1a5731b03584eaf21b9561a6939e784d5565","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5007db84b7572b7ae93355c96fb1a5731b03584eaf21b9561a6939e784d5565","first_computed_at":"2026-07-05T09:51:29.225679Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:29.225679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J8n59ZotZ26nyOg1qCwPlOCgmow4VHYJovGVmctPGxolmFtO1cRaJVgOIzUCT2RxiwGlbQyeWiXPMpJu+upuAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:29.226290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.13008","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f12b7281af435944745fee12a6cf5da8f13ddb93c6a5826229334431fb0cacd9","sha256:2dbc7a6f59060c26858dc1ed09005795a2c2efb9a483b9bf4e77f0e4a047f28d"],"state_sha256":"c94de9e3bd7ecc120546a3b1afd9d68506a6f9559ce7edeff8f9df6e6d60db80"}