{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BML64WOIWTIYY2QNLH457DAN37","short_pith_number":"pith:BML64WOI","canonical_record":{"source":{"id":"2404.07840","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T15:27:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e60c5735044a31cdb8447336b32ed189c0a30761954a186c4d7e2d3ed9e66e0a","abstract_canon_sha256":"3899b651f48c5402cfe3084f295ad46769e44e65feab444b822ead3faaa4bd07"},"schema_version":"1.0"},"canonical_sha256":"0b17ee59c8b4d18c6a0d59f9df8c0ddfda73111716274bfa1f4de0c0a5a7331d","source":{"kind":"arxiv","id":"2404.07840","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07840","created_at":"2026-07-05T09:15:09Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07840v3","created_at":"2026-07-05T09:15:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07840","created_at":"2026-07-05T09:15:09Z"},{"alias_kind":"pith_short_12","alias_value":"BML64WOIWTIY","created_at":"2026-07-05T09:15:09Z"},{"alias_kind":"pith_short_16","alias_value":"BML64WOIWTIYY2QN","created_at":"2026-07-05T09:15:09Z"},{"alias_kind":"pith_short_8","alias_value":"BML64WOI","created_at":"2026-07-05T09:15:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BML64WOIWTIYY2QNLH457DAN37","target":"record","payload":{"canonical_record":{"source":{"id":"2404.07840","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T15:27:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e60c5735044a31cdb8447336b32ed189c0a30761954a186c4d7e2d3ed9e66e0a","abstract_canon_sha256":"3899b651f48c5402cfe3084f295ad46769e44e65feab444b822ead3faaa4bd07"},"schema_version":"1.0"},"canonical_sha256":"0b17ee59c8b4d18c6a0d59f9df8c0ddfda73111716274bfa1f4de0c0a5a7331d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:09.652542Z","signature_b64":"4081ckvB/tPhFFYJIZYdVRlDuqUi57lvPygy+cjvTxnt6Jbtz3rnix9crGQxuAIbCF+Qx77ZbsYOkJsvLA3iDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b17ee59c8b4d18c6a0d59f9df8c0ddfda73111716274bfa1f4de0c0a5a7331d","last_reissued_at":"2026-07-05T09:15:09.652059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:09.652059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.07840","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:15:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uUxmVivrQv6nrDZU/xLiZC6dhqQnqvCbhxv9Bp45Bl3CltWJmCx5GNr847/BPfy5qqvbKpYBvPX1desZRZ1CAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:52:00.100264Z"},"content_sha256":"8db35615e65b5e5239fe1ca7a57160d554726d0f57c6cd14a2cbf5f6bce1b0a7","schema_version":"1.0","event_id":"sha256:8db35615e65b5e5239fe1ca7a57160d554726d0f57c6cd14a2cbf5f6bce1b0a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BML64WOIWTIYY2QNLH457DAN37","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Training Data Influence of GPT Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hua Wu, Qingyi Liu, Qiwei Peng, Shuohuan Wang, Yekun Chai, Yu Sun","submitted_at":"2024-04-11T15:27:56Z","abstract_excerpt":"Amidst the rapid advancements in generative language models, the investigation of how training data shapes the performance of GPT models is still emerging. This paper presents GPTfluence, a novel approach that leverages a featurized simulation to assess the impact of training examples on the training dynamics of GPT models. Our approach not only traces the influence of individual training instances on performance trajectories, such as loss and other key metrics, on targeted test points but also enables a comprehensive comparison with existing methods across various training scenarios in GPT mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07840","kind":"arxiv","version":3},"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/2404.07840/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":"2026-07-05T09:15:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bnx8Y3lnUOuTVTBT3WfpQoJxASo1gdUuRgk+GAFPk+MsOTiGEJgCemTV/AJgdEE2wAXVW4ch3AvazccF/QPxAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:52:00.100647Z"},"content_sha256":"c085a11c026cb64f99a1c985423a592283a1c6103187aaf62b1e572a6074dabb","schema_version":"1.0","event_id":"sha256:c085a11c026cb64f99a1c985423a592283a1c6103187aaf62b1e572a6074dabb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BML64WOIWTIYY2QNLH457DAN37/bundle.json","state_url":"https://pith.science/pith/BML64WOIWTIYY2QNLH457DAN37/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BML64WOIWTIYY2QNLH457DAN37/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":"2026-07-07T06:52:00Z","links":{"resolver":"https://pith.science/pith/BML64WOIWTIYY2QNLH457DAN37","bundle":"https://pith.science/pith/BML64WOIWTIYY2QNLH457DAN37/bundle.json","state":"https://pith.science/pith/BML64WOIWTIYY2QNLH457DAN37/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BML64WOIWTIYY2QNLH457DAN37/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BML64WOIWTIYY2QNLH457DAN37","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":"3899b651f48c5402cfe3084f295ad46769e44e65feab444b822ead3faaa4bd07","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T15:27:56Z","title_canon_sha256":"e60c5735044a31cdb8447336b32ed189c0a30761954a186c4d7e2d3ed9e66e0a"},"schema_version":"1.0","source":{"id":"2404.07840","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07840","created_at":"2026-07-05T09:15:09Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07840v3","created_at":"2026-07-05T09:15:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07840","created_at":"2026-07-05T09:15:09Z"},{"alias_kind":"pith_short_12","alias_value":"BML64WOIWTIY","created_at":"2026-07-05T09:15:09Z"},{"alias_kind":"pith_short_16","alias_value":"BML64WOIWTIYY2QN","created_at":"2026-07-05T09:15:09Z"},{"alias_kind":"pith_short_8","alias_value":"BML64WOI","created_at":"2026-07-05T09:15:09Z"}],"graph_snapshots":[{"event_id":"sha256:c085a11c026cb64f99a1c985423a592283a1c6103187aaf62b1e572a6074dabb","target":"graph","created_at":"2026-07-05T09:15:09Z","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/2404.07840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Amidst the rapid advancements in generative language models, the investigation of how training data shapes the performance of GPT models is still emerging. This paper presents GPTfluence, a novel approach that leverages a featurized simulation to assess the impact of training examples on the training dynamics of GPT models. Our approach not only traces the influence of individual training instances on performance trajectories, such as loss and other key metrics, on targeted test points but also enables a comprehensive comparison with existing methods across various training scenarios in GPT mo","authors_text":"Hua Wu, Qingyi Liu, Qiwei Peng, Shuohuan Wang, Yekun Chai, Yu Sun","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T15:27:56Z","title":"On Training Data Influence of GPT Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07840","kind":"arxiv","version":3},"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":"sha256:8db35615e65b5e5239fe1ca7a57160d554726d0f57c6cd14a2cbf5f6bce1b0a7","target":"record","created_at":"2026-07-05T09:15:09Z","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":"3899b651f48c5402cfe3084f295ad46769e44e65feab444b822ead3faaa4bd07","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T15:27:56Z","title_canon_sha256":"e60c5735044a31cdb8447336b32ed189c0a30761954a186c4d7e2d3ed9e66e0a"},"schema_version":"1.0","source":{"id":"2404.07840","kind":"arxiv","version":3}},"canonical_sha256":"0b17ee59c8b4d18c6a0d59f9df8c0ddfda73111716274bfa1f4de0c0a5a7331d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b17ee59c8b4d18c6a0d59f9df8c0ddfda73111716274bfa1f4de0c0a5a7331d","first_computed_at":"2026-07-05T09:15:09.652059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:09.652059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4081ckvB/tPhFFYJIZYdVRlDuqUi57lvPygy+cjvTxnt6Jbtz3rnix9crGQxuAIbCF+Qx77ZbsYOkJsvLA3iDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:09.652542Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.07840","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8db35615e65b5e5239fe1ca7a57160d554726d0f57c6cd14a2cbf5f6bce1b0a7","sha256:c085a11c026cb64f99a1c985423a592283a1c6103187aaf62b1e572a6074dabb"],"state_sha256":"1baa5e65a02ebc7b9eb3912f05148662d47e8a712338e51bb876d5475506692d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gyu11hGryk4BzfZY886zPxmksAK7Gj+p13bpyl3OxBg2OmgoAZJ8YRbyjg+OjpxFTx9YKy9QbQaldhYgE6vODw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:52:00.102666Z","bundle_sha256":"6897daf880e6580fb425151d9613c69831dc0fb38ebb314837f9909ab4b887f2"}}