{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NVJCIWALMUZ6WTT46TJLWMDYWN","short_pith_number":"pith:NVJCIWAL","canonical_record":{"source":{"id":"2402.18041","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T04:35:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e377a701893a4aa2169f6ca4e9b00d72c047fdceef1cda42cffc941943d5a7e7","abstract_canon_sha256":"04fc2ebc0bdadcfa83dbff4d781bec07ed7b6263e5c1ee318dd4c18f68cd3769"},"schema_version":"1.0"},"canonical_sha256":"6d5224580b6533eb4e7cf4d2bb3078b350d80dfece687284f36dc2b5c794645d","source":{"kind":"arxiv","id":"2402.18041","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18041","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18041v1","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18041","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"pith_short_12","alias_value":"NVJCIWALMUZ6","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"pith_short_16","alias_value":"NVJCIWALMUZ6WTT4","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"pith_short_8","alias_value":"NVJCIWAL","created_at":"2026-07-05T07:50:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NVJCIWALMUZ6WTT46TJLWMDYWN","target":"record","payload":{"canonical_record":{"source":{"id":"2402.18041","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T04:35:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e377a701893a4aa2169f6ca4e9b00d72c047fdceef1cda42cffc941943d5a7e7","abstract_canon_sha256":"04fc2ebc0bdadcfa83dbff4d781bec07ed7b6263e5c1ee318dd4c18f68cd3769"},"schema_version":"1.0"},"canonical_sha256":"6d5224580b6533eb4e7cf4d2bb3078b350d80dfece687284f36dc2b5c794645d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:11.320682Z","signature_b64":"FCyb2IuBbDpPGnIaNjPSBhR+ye+quR5Hhwg+rvjbkwwKbf6rSSJ84FwnwARtIJFa+n30/8ZY7fdJ/mRNtQaeAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d5224580b6533eb4e7cf4d2bb3078b350d80dfece687284f36dc2b5c794645d","last_reissued_at":"2026-07-05T07:50:11.320216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:11.320216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.18041","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":"2026-07-05T07:50:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wb8UUUDpi/jn/YRBg/n+85prGyRVsWI5NBvzAyuUp9s5txE2tv20SMJXidLFecKl1T3ua5oQ7Phnk8V0WKalAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:29:29.258264Z"},"content_sha256":"f8b2feba5a322adc25506b985c137eadf627c720f74cb9c37f24c3679826f799","schema_version":"1.0","event_id":"sha256:f8b2feba5a322adc25506b985c137eadf627c720f74cb9c37f24c3679826f799"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NVJCIWALMUZ6WTT46TJLWMDYWN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Datasets for Large Language Models: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chongyu Liu, Jiahuan Cao, Kai Ding, Lianwen Jin, Yang Liu","submitted_at":"2024-02-28T04:35:51Z","abstract_excerpt":"This paper embarks on an exploration into the Large Language Model (LLM) datasets, which play a crucial role in the remarkable advancements of LLMs. The datasets serve as the foundational infrastructure analogous to a root system that sustains and nurtures the development of LLMs. Consequently, examination of these datasets emerges as a critical topic in research. In order to address the current lack of a comprehensive overview and thorough analysis of LLM datasets, and to gain insights into their current status and future trends, this survey consolidates and categorizes the fundamental aspect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18041","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/2402.18041/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":"2026-07-05T07:50:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BB61zJFU+UtfPBHfWTmWdWBmLi07+pv+NXqS2sE/m5EHkUAvZy/9PKtFMzq4OVLyTWqwD4Yn2nYxw5b2P4vhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:29:29.258636Z"},"content_sha256":"6f2df4bbdb0205eb8ad0c1c5ebcbf47a81bfa883fcc801135a4cf7ac7f3eb654","schema_version":"1.0","event_id":"sha256:6f2df4bbdb0205eb8ad0c1c5ebcbf47a81bfa883fcc801135a4cf7ac7f3eb654"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NVJCIWALMUZ6WTT46TJLWMDYWN/bundle.json","state_url":"https://pith.science/pith/NVJCIWALMUZ6WTT46TJLWMDYWN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NVJCIWALMUZ6WTT46TJLWMDYWN/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":"2026-08-06T16:29:29Z","links":{"resolver":"https://pith.science/pith/NVJCIWALMUZ6WTT46TJLWMDYWN","bundle":"https://pith.science/pith/NVJCIWALMUZ6WTT46TJLWMDYWN/bundle.json","state":"https://pith.science/pith/NVJCIWALMUZ6WTT46TJLWMDYWN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NVJCIWALMUZ6WTT46TJLWMDYWN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NVJCIWALMUZ6WTT46TJLWMDYWN","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":"04fc2ebc0bdadcfa83dbff4d781bec07ed7b6263e5c1ee318dd4c18f68cd3769","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T04:35:51Z","title_canon_sha256":"e377a701893a4aa2169f6ca4e9b00d72c047fdceef1cda42cffc941943d5a7e7"},"schema_version":"1.0","source":{"id":"2402.18041","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18041","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18041v1","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18041","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"pith_short_12","alias_value":"NVJCIWALMUZ6","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"pith_short_16","alias_value":"NVJCIWALMUZ6WTT4","created_at":"2026-07-05T07:50:11Z"},{"alias_kind":"pith_short_8","alias_value":"NVJCIWAL","created_at":"2026-07-05T07:50:11Z"}],"graph_snapshots":[{"event_id":"sha256:6f2df4bbdb0205eb8ad0c1c5ebcbf47a81bfa883fcc801135a4cf7ac7f3eb654","target":"graph","created_at":"2026-07-05T07:50:11Z","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/2402.18041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper embarks on an exploration into the Large Language Model (LLM) datasets, which play a crucial role in the remarkable advancements of LLMs. The datasets serve as the foundational infrastructure analogous to a root system that sustains and nurtures the development of LLMs. Consequently, examination of these datasets emerges as a critical topic in research. In order to address the current lack of a comprehensive overview and thorough analysis of LLM datasets, and to gain insights into their current status and future trends, this survey consolidates and categorizes the fundamental aspect","authors_text":"Chongyu Liu, Jiahuan Cao, Kai Ding, Lianwen Jin, Yang Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T04:35:51Z","title":"Datasets for Large Language Models: A Comprehensive Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18041","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:f8b2feba5a322adc25506b985c137eadf627c720f74cb9c37f24c3679826f799","target":"record","created_at":"2026-07-05T07:50:11Z","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":"04fc2ebc0bdadcfa83dbff4d781bec07ed7b6263e5c1ee318dd4c18f68cd3769","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T04:35:51Z","title_canon_sha256":"e377a701893a4aa2169f6ca4e9b00d72c047fdceef1cda42cffc941943d5a7e7"},"schema_version":"1.0","source":{"id":"2402.18041","kind":"arxiv","version":1}},"canonical_sha256":"6d5224580b6533eb4e7cf4d2bb3078b350d80dfece687284f36dc2b5c794645d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d5224580b6533eb4e7cf4d2bb3078b350d80dfece687284f36dc2b5c794645d","first_computed_at":"2026-07-05T07:50:11.320216Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:11.320216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FCyb2IuBbDpPGnIaNjPSBhR+ye+quR5Hhwg+rvjbkwwKbf6rSSJ84FwnwARtIJFa+n30/8ZY7fdJ/mRNtQaeAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:11.320682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.18041","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8b2feba5a322adc25506b985c137eadf627c720f74cb9c37f24c3679826f799","sha256:6f2df4bbdb0205eb8ad0c1c5ebcbf47a81bfa883fcc801135a4cf7ac7f3eb654"],"state_sha256":"d494b9a03329e7584ec5fe1f039b131e81e6160541d1858b05150647735682a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pe8A4/+SXsotLwK7iUv2ppNsdte9KenE4evojh4KpyiOWXJK1s8LwRe8zlMGqm31kXiaAGHZTda0pNbhaKlaDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:29:29.261328Z","bundle_sha256":"b45b2b78ac2aa07b70f675772c3f43786f737be8b85051abecf3efb998251538"}}