{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TDJXDWZLTSGGGYW57YCLKO2JLG","short_pith_number":"pith:TDJXDWZL","canonical_record":{"source":{"id":"2405.13954","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T19:39:05Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b86c58f35ced1f34ad8c6b0b137f0bf836f10775a16dee8d0263c01fe170d977","abstract_canon_sha256":"83212063679467943bf47fd74bcaca59f422706cf75e4f6d27846d3bd1a5d5d1"},"schema_version":"1.0"},"canonical_sha256":"98d371db2b9c8c6362ddfe04b53b4959a10258847448b097e037aea225e26c2c","source":{"kind":"arxiv","id":"2405.13954","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.13954","created_at":"2026-07-05T08:22:08Z"},{"alias_kind":"arxiv_version","alias_value":"2405.13954v1","created_at":"2026-07-05T08:22:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13954","created_at":"2026-07-05T08:22:08Z"},{"alias_kind":"pith_short_12","alias_value":"TDJXDWZLTSGG","created_at":"2026-07-05T08:22:08Z"},{"alias_kind":"pith_short_16","alias_value":"TDJXDWZLTSGGGYW5","created_at":"2026-07-05T08:22:08Z"},{"alias_kind":"pith_short_8","alias_value":"TDJXDWZL","created_at":"2026-07-05T08:22:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TDJXDWZLTSGGGYW57YCLKO2JLG","target":"record","payload":{"canonical_record":{"source":{"id":"2405.13954","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T19:39:05Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b86c58f35ced1f34ad8c6b0b137f0bf836f10775a16dee8d0263c01fe170d977","abstract_canon_sha256":"83212063679467943bf47fd74bcaca59f422706cf75e4f6d27846d3bd1a5d5d1"},"schema_version":"1.0"},"canonical_sha256":"98d371db2b9c8c6362ddfe04b53b4959a10258847448b097e037aea225e26c2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:08.736516Z","signature_b64":"uy9/kZezyCSdyWg9/UTWIVwyZvQpKK10M08INybyZ7L8f5gu6BAXjDp+x/7MVdt9Pd4LO/wTiMpYK0pyDVU3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98d371db2b9c8c6362ddfe04b53b4959a10258847448b097e037aea225e26c2c","last_reissued_at":"2026-07-05T08:22:08.735981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:08.735981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.13954","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":"2026-07-05T08:22:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ADEU4IZjXzDnZjBDrMiHhVPsUN0ppMSaePvoYRroIG9zYulVL+uDdefmRP9AWu03UEijhd3jxB1k880xbP9qCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:29:37.675029Z"},"content_sha256":"4a374f3bb39c9e409877e148c22f84f92edeb6b56174b72fbe3276d9a7bab834","schema_version":"1.0","event_id":"sha256:4a374f3bb39c9e409877e148c22f84f92edeb6b56174b72fbe3276d9a7bab834"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TDJXDWZLTSGGGYW57YCLKO2JLG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Adithya Pratapa, Eduard Hovy, Emma Strubell, Eric Xing, Hwijeen Ahn, Jeff Schneider, Juhan Bae, Kewen Zhao, Minsoo Kang, Roger Grosse, Sang Keun Choe, Teruko Mitamura, Willie Neiswanger, Youngseog Chung","submitted_at":"2024-05-22T19:39:05Z","abstract_excerpt":"Large language models (LLMs) are trained on a vast amount of human-written data, but data providers often remain uncredited. In response to this issue, data valuation (or data attribution), which quantifies the contribution or value of each data to the model output, has been discussed as a potential solution. Nevertheless, applying existing data valuation methods to recent LLMs and their vast training datasets has been largely limited by prohibitive compute and memory costs. In this work, we focus on influence functions, a popular gradient-based data valuation method, and significantly improve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13954","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/2405.13954/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":"2026-07-05T08:22:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YztP6G2qK0Su+MLGcUrkouKoW5lqG0oHfjijOeLaf6DFUgKJi0tPfq/tX2IhAm/9Y/196mOWj02dBRLpZ14VAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:29:37.675578Z"},"content_sha256":"b83a7c4fdaee8085fc082a021c8fe201b1aa88cc31486d62be78fe8ea81a13cd","schema_version":"1.0","event_id":"sha256:b83a7c4fdaee8085fc082a021c8fe201b1aa88cc31486d62be78fe8ea81a13cd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TDJXDWZLTSGGGYW57YCLKO2JLG/bundle.json","state_url":"https://pith.science/pith/TDJXDWZLTSGGGYW57YCLKO2JLG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TDJXDWZLTSGGGYW57YCLKO2JLG/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":"2026-08-09T05:29:37Z","links":{"resolver":"https://pith.science/pith/TDJXDWZLTSGGGYW57YCLKO2JLG","bundle":"https://pith.science/pith/TDJXDWZLTSGGGYW57YCLKO2JLG/bundle.json","state":"https://pith.science/pith/TDJXDWZLTSGGGYW57YCLKO2JLG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TDJXDWZLTSGGGYW57YCLKO2JLG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TDJXDWZLTSGGGYW57YCLKO2JLG","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":"83212063679467943bf47fd74bcaca59f422706cf75e4f6d27846d3bd1a5d5d1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T19:39:05Z","title_canon_sha256":"b86c58f35ced1f34ad8c6b0b137f0bf836f10775a16dee8d0263c01fe170d977"},"schema_version":"1.0","source":{"id":"2405.13954","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.13954","created_at":"2026-07-05T08:22:08Z"},{"alias_kind":"arxiv_version","alias_value":"2405.13954v1","created_at":"2026-07-05T08:22:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13954","created_at":"2026-07-05T08:22:08Z"},{"alias_kind":"pith_short_12","alias_value":"TDJXDWZLTSGG","created_at":"2026-07-05T08:22:08Z"},{"alias_kind":"pith_short_16","alias_value":"TDJXDWZLTSGGGYW5","created_at":"2026-07-05T08:22:08Z"},{"alias_kind":"pith_short_8","alias_value":"TDJXDWZL","created_at":"2026-07-05T08:22:08Z"}],"graph_snapshots":[{"event_id":"sha256:b83a7c4fdaee8085fc082a021c8fe201b1aa88cc31486d62be78fe8ea81a13cd","target":"graph","created_at":"2026-07-05T08:22:08Z","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/2405.13954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are trained on a vast amount of human-written data, but data providers often remain uncredited. In response to this issue, data valuation (or data attribution), which quantifies the contribution or value of each data to the model output, has been discussed as a potential solution. Nevertheless, applying existing data valuation methods to recent LLMs and their vast training datasets has been largely limited by prohibitive compute and memory costs. In this work, we focus on influence functions, a popular gradient-based data valuation method, and significantly improve","authors_text":"Adithya Pratapa, Eduard Hovy, Emma Strubell, Eric Xing, Hwijeen Ahn, Jeff Schneider, Juhan Bae, Kewen Zhao, Minsoo Kang, Roger Grosse, Sang Keun Choe, Teruko Mitamura, Willie Neiswanger, Youngseog Chung","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T19:39:05Z","title":"What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13954","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":"sha256:4a374f3bb39c9e409877e148c22f84f92edeb6b56174b72fbe3276d9a7bab834","target":"record","created_at":"2026-07-05T08:22:08Z","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":"83212063679467943bf47fd74bcaca59f422706cf75e4f6d27846d3bd1a5d5d1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T19:39:05Z","title_canon_sha256":"b86c58f35ced1f34ad8c6b0b137f0bf836f10775a16dee8d0263c01fe170d977"},"schema_version":"1.0","source":{"id":"2405.13954","kind":"arxiv","version":1}},"canonical_sha256":"98d371db2b9c8c6362ddfe04b53b4959a10258847448b097e037aea225e26c2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98d371db2b9c8c6362ddfe04b53b4959a10258847448b097e037aea225e26c2c","first_computed_at":"2026-07-05T08:22:08.735981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:08.735981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uy9/kZezyCSdyWg9/UTWIVwyZvQpKK10M08INybyZ7L8f5gu6BAXjDp+x/7MVdt9Pd4LO/wTiMpYK0pyDVU3Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:08.736516Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.13954","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a374f3bb39c9e409877e148c22f84f92edeb6b56174b72fbe3276d9a7bab834","sha256:b83a7c4fdaee8085fc082a021c8fe201b1aa88cc31486d62be78fe8ea81a13cd"],"state_sha256":"0c662537f0882c8d574c3546ae4ee1e0b836cf32b59dfb8eed2d76bedd38a742"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vw2x8szKY8vXFM9mbmy7Swg4eq2zzRcqxMNaUaWp5K9VisAIgBjYvV3eQzyl19NYeHWnxJBCVbJbMN9eU+vhAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:29:37.680201Z","bundle_sha256":"5869fee0a2d2372f14574fd72bef2a8cac0628d06fd45937a5e670717fedbab4"}}