{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YPQ4SC7LW5UQHDRXPNAYOSGI4R","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":"770420108413d1db8c46364c1cadcaab90e086d658da37967fad82fd865ddca0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T17:36:49Z","title_canon_sha256":"d905870b307728bfff727db706ea386608ef4fac3e8e508c7526d48307a9afe7"},"schema_version":"1.0","source":{"id":"2608.13515","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13515","created_at":"2026-08-14T01:24:55Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13515v1","created_at":"2026-08-14T01:24:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13515","created_at":"2026-08-14T01:24:55Z"},{"alias_kind":"pith_short_12","alias_value":"YPQ4SC7LW5UQ","created_at":"2026-08-14T01:24:55Z"},{"alias_kind":"pith_short_16","alias_value":"YPQ4SC7LW5UQHDRX","created_at":"2026-08-14T01:24:55Z"},{"alias_kind":"pith_short_8","alias_value":"YPQ4SC7L","created_at":"2026-08-14T01:24:55Z"}],"graph_snapshots":[{"event_id":"sha256:2b41c7112fd76ed34ca12d08dc575e13bd1fdc58c4c3b0bd069964dcc2cd7cd4","target":"graph","created_at":"2026-08-14T01:24:55Z","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/2608.13515/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Measuring training data influence consistently across language model pretraining is challenging. It is difficult to select downstream tasks or validation sets representative of a model's general capabilities, and reliance on task performance at intermediate checkpoints complicates comparisons across training. We propose a measure of training data influence that does not require selecting a downstream task or validation set as the attribution target. Specifically, we define an example's influence by how much its gradient update reduces the squared distance to the final parameters of a given pre","authors_text":"Chaoran Liu, Daisuke Kawahara, Hirokazu Kiyomaru, Masaru Isonuma, Max M\\\"uller-Eberstein, Takashi Kodama, Yusuke Miyao, Yusuke Oda, Yuto Nishida","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T17:36:49Z","title":"Measuring Task-Agnostic Training Data Influence Across Language Model Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13515","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:e6f0fe9bee597b123821e22d05aa545122234d4ec9715f4b1f8541bb8be00394","target":"record","created_at":"2026-08-14T01:24:55Z","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":"770420108413d1db8c46364c1cadcaab90e086d658da37967fad82fd865ddca0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T17:36:49Z","title_canon_sha256":"d905870b307728bfff727db706ea386608ef4fac3e8e508c7526d48307a9afe7"},"schema_version":"1.0","source":{"id":"2608.13515","kind":"arxiv","version":1}},"canonical_sha256":"c3e1c90bebb769038e377b418748c8e45eb74e5ed4ffba254d5aa5efdb7bf5be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3e1c90bebb769038e377b418748c8e45eb74e5ed4ffba254d5aa5efdb7bf5be","first_computed_at":"2026-08-14T01:24:55.851101Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T01:24:55.851101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EnCQYeZnA5ckkmFBqsgCd5OBwR8l4cAqAT4eODnGzPRh7wxjjybafwilCFh6LRKnWIxSDkvIeTDemJklUzPfBw==","signature_status":"signed_v1","signed_at":"2026-08-14T01:24:55.853349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.13515","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6f0fe9bee597b123821e22d05aa545122234d4ec9715f4b1f8541bb8be00394","sha256:2b41c7112fd76ed34ca12d08dc575e13bd1fdc58c4c3b0bd069964dcc2cd7cd4"],"state_sha256":"edf68f81c07c125cb3a22dd4176d69372607fa9b6122363e3ad91721f5f05951"}