{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HABU3TQ2BO525LQS5RCFUH54BN","short_pith_number":"pith:HABU3TQ2","canonical_record":{"source":{"id":"2411.07715","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-12T11:09:58Z","cross_cats_sorted":[],"title_canon_sha256":"9886e45809dd64055aa30525524f375a148c9894dccdd6a29bb0fc09c39321d7","abstract_canon_sha256":"f16e3abaca47f7cdc22ecd232d63b625ce30151250339f2dc666d07ba70c6218"},"schema_version":"1.0"},"canonical_sha256":"38034dce1a0bbbaeae12ec445a1fbc0b6b86ff6289cbb5ec2067e0b091cf9576","source":{"kind":"arxiv","id":"2411.07715","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07715","created_at":"2026-07-05T09:34:27Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07715v1","created_at":"2026-07-05T09:34:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07715","created_at":"2026-07-05T09:34:27Z"},{"alias_kind":"pith_short_12","alias_value":"HABU3TQ2BO52","created_at":"2026-07-05T09:34:27Z"},{"alias_kind":"pith_short_16","alias_value":"HABU3TQ2BO525LQS","created_at":"2026-07-05T09:34:27Z"},{"alias_kind":"pith_short_8","alias_value":"HABU3TQ2","created_at":"2026-07-05T09:34:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HABU3TQ2BO525LQS5RCFUH54BN","target":"record","payload":{"canonical_record":{"source":{"id":"2411.07715","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-12T11:09:58Z","cross_cats_sorted":[],"title_canon_sha256":"9886e45809dd64055aa30525524f375a148c9894dccdd6a29bb0fc09c39321d7","abstract_canon_sha256":"f16e3abaca47f7cdc22ecd232d63b625ce30151250339f2dc666d07ba70c6218"},"schema_version":"1.0"},"canonical_sha256":"38034dce1a0bbbaeae12ec445a1fbc0b6b86ff6289cbb5ec2067e0b091cf9576","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:27.915651Z","signature_b64":"uBMDwQfDIHSc8Dj1LbLe7UOR5wuVT0Q5vZVS0/fsI6LlCXZowO5oYZW9FxUHdQbFlQbDLiO8jwvGGxlPAOutAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38034dce1a0bbbaeae12ec445a1fbc0b6b86ff6289cbb5ec2067e0b091cf9576","last_reissued_at":"2026-07-05T09:34:27.915232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:27.915232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.07715","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":"2026-07-05T09:34:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kfb7MYUxn2TZFewKNfM6sxrj/4S5uSR6uOXI1FXbc2gePoZj+gftUqCE3/yMr9lrpXRiv8G+esMXoKOyb7ffBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:01:59.249697Z"},"content_sha256":"3e09937b31c86d054135b037aed32202015ad723f5eee2b24c17b8b85450bd91","schema_version":"1.0","event_id":"sha256:3e09937b31c86d054135b037aed32202015ad723f5eee2b24c17b8b85450bd91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HABU3TQ2BO525LQS5RCFUH54BN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Data for Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Huanhuan Ma, Yiming Ju","submitted_at":"2024-11-12T11:09:58Z","abstract_excerpt":"In 2022, with the release of ChatGPT, large-scale language models gained widespread attention. ChatGPT not only surpassed previous models in terms of parameters and the scale of its pretraining corpus but also achieved revolutionary performance improvements through fine-tuning on a vast amount of high-quality, human-annotated data. This progress has led enterprises and research institutions to recognize that building smarter and more powerful models relies on rich and high-quality datasets. Consequently, the construction and optimization of datasets have become a critical focus in the field of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07715","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/2411.07715/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":"2026-07-05T09:34:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UjLKUBgLmyN8tEdT9Pps7jV2c9NsiQTjet7qINVmHDz0a7qV30QwRX1zCvarBzdLFhQRPp1MGU5NDGRznyS/CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:01:59.250215Z"},"content_sha256":"822e248eae2c013d153951e1ab67e81ebe3c5b8b0d0e6ea52dcdbad65f69ec39","schema_version":"1.0","event_id":"sha256:822e248eae2c013d153951e1ab67e81ebe3c5b8b0d0e6ea52dcdbad65f69ec39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HABU3TQ2BO525LQS5RCFUH54BN/bundle.json","state_url":"https://pith.science/pith/HABU3TQ2BO525LQS5RCFUH54BN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HABU3TQ2BO525LQS5RCFUH54BN/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":"2026-08-22T08:01:59Z","links":{"resolver":"https://pith.science/pith/HABU3TQ2BO525LQS5RCFUH54BN","bundle":"https://pith.science/pith/HABU3TQ2BO525LQS5RCFUH54BN/bundle.json","state":"https://pith.science/pith/HABU3TQ2BO525LQS5RCFUH54BN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HABU3TQ2BO525LQS5RCFUH54BN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HABU3TQ2BO525LQS5RCFUH54BN","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":"f16e3abaca47f7cdc22ecd232d63b625ce30151250339f2dc666d07ba70c6218","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-12T11:09:58Z","title_canon_sha256":"9886e45809dd64055aa30525524f375a148c9894dccdd6a29bb0fc09c39321d7"},"schema_version":"1.0","source":{"id":"2411.07715","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07715","created_at":"2026-07-05T09:34:27Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07715v1","created_at":"2026-07-05T09:34:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07715","created_at":"2026-07-05T09:34:27Z"},{"alias_kind":"pith_short_12","alias_value":"HABU3TQ2BO52","created_at":"2026-07-05T09:34:27Z"},{"alias_kind":"pith_short_16","alias_value":"HABU3TQ2BO525LQS","created_at":"2026-07-05T09:34:27Z"},{"alias_kind":"pith_short_8","alias_value":"HABU3TQ2","created_at":"2026-07-05T09:34:27Z"}],"graph_snapshots":[{"event_id":"sha256:822e248eae2c013d153951e1ab67e81ebe3c5b8b0d0e6ea52dcdbad65f69ec39","target":"graph","created_at":"2026-07-05T09:34:27Z","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/2411.07715/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In 2022, with the release of ChatGPT, large-scale language models gained widespread attention. ChatGPT not only surpassed previous models in terms of parameters and the scale of its pretraining corpus but also achieved revolutionary performance improvements through fine-tuning on a vast amount of high-quality, human-annotated data. This progress has led enterprises and research institutions to recognize that building smarter and more powerful models relies on rich and high-quality datasets. Consequently, the construction and optimization of datasets have become a critical focus in the field of","authors_text":"Huanhuan Ma, Yiming Ju","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-12T11:09:58Z","title":"Training Data for Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07715","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":"sha256:3e09937b31c86d054135b037aed32202015ad723f5eee2b24c17b8b85450bd91","target":"record","created_at":"2026-07-05T09:34:27Z","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":"f16e3abaca47f7cdc22ecd232d63b625ce30151250339f2dc666d07ba70c6218","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-12T11:09:58Z","title_canon_sha256":"9886e45809dd64055aa30525524f375a148c9894dccdd6a29bb0fc09c39321d7"},"schema_version":"1.0","source":{"id":"2411.07715","kind":"arxiv","version":1}},"canonical_sha256":"38034dce1a0bbbaeae12ec445a1fbc0b6b86ff6289cbb5ec2067e0b091cf9576","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38034dce1a0bbbaeae12ec445a1fbc0b6b86ff6289cbb5ec2067e0b091cf9576","first_computed_at":"2026-07-05T09:34:27.915232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:27.915232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uBMDwQfDIHSc8Dj1LbLe7UOR5wuVT0Q5vZVS0/fsI6LlCXZowO5oYZW9FxUHdQbFlQbDLiO8jwvGGxlPAOutAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:27.915651Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.07715","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e09937b31c86d054135b037aed32202015ad723f5eee2b24c17b8b85450bd91","sha256:822e248eae2c013d153951e1ab67e81ebe3c5b8b0d0e6ea52dcdbad65f69ec39"],"state_sha256":"be3ee9984ac58601d3d881cacd476e4db709aa39a10404aea1a526c559ef3612"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ECHL4GKWdzsS2FM20r/CfwcYQaPZx/yAUK+5ukzwQFBdnih4Su4+IObqyK8L4UmfYOHa56hxjiMCSRV1mnoABw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T08:01:59.254005Z","bundle_sha256":"d684ae5b39424007eebc1eb1e907e8f605f45655787bebf81b32ab7c153281f3"}}