{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TTFDTLQCDPEVGVZNOP67WAXJDM","short_pith_number":"pith:TTFDTLQC","canonical_record":{"source":{"id":"2309.10818","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T17:59:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c33e708f0677ddf592c361a7fe7e0739750328a6f50131aad4d123ce3f64a2e","abstract_canon_sha256":"b8399c163c6d413a76b10fa64cd6290a147d2b0ee67221992de46b448c02defe"},"schema_version":"1.0"},"canonical_sha256":"9cca39ae021bc953572d73fdfb02e91b1c8f410eacd7b799be4f617be216e1b3","source":{"kind":"arxiv","id":"2309.10818","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10818","created_at":"2026-07-05T08:17:10Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10818v3","created_at":"2026-07-05T08:17:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10818","created_at":"2026-07-05T08:17:10Z"},{"alias_kind":"pith_short_12","alias_value":"TTFDTLQCDPEV","created_at":"2026-07-05T08:17:10Z"},{"alias_kind":"pith_short_16","alias_value":"TTFDTLQCDPEVGVZN","created_at":"2026-07-05T08:17:10Z"},{"alias_kind":"pith_short_8","alias_value":"TTFDTLQC","created_at":"2026-07-05T08:17:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TTFDTLQCDPEVGVZNOP67WAXJDM","target":"record","payload":{"canonical_record":{"source":{"id":"2309.10818","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T17:59:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c33e708f0677ddf592c361a7fe7e0739750328a6f50131aad4d123ce3f64a2e","abstract_canon_sha256":"b8399c163c6d413a76b10fa64cd6290a147d2b0ee67221992de46b448c02defe"},"schema_version":"1.0"},"canonical_sha256":"9cca39ae021bc953572d73fdfb02e91b1c8f410eacd7b799be4f617be216e1b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:10.676999Z","signature_b64":"HqKQkgXMP8ZrI355CzwUiOM9oRm0gTvbbf7HjSs97+N5rCmko11Dwj/NBsklLEz1/1QQ9t5aTwpzA5Up0ySCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cca39ae021bc953572d73fdfb02e91b1c8f410eacd7b799be4f617be216e1b3","last_reissued_at":"2026-07-05T08:17:10.676274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:10.676274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.10818","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":"2026-07-05T08:17:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qaV/t28Xqq9S6Y3UW/kevmWLQCINzBd8v1PbCM16taejY4+X/FtzF0S8QducGVd5ffinNad7Pv9MInguhKs8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:54:49.546609Z"},"content_sha256":"6850a01997a36be9d3b030e80269684cca0973bc7a4f6ce57550e61ced402b1e","schema_version":"1.0","event_id":"sha256:6850a01997a36be9d3b030e80269684cca0973bc7a4f6ce57550e61ced402b1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TTFDTLQCDPEVGVZNOP67WAXJDM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SlimPajama-DC: Understanding Data Combinations for LLM Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bowen Tan, Daria Soboleva, Eric Xing, Hongyi Wang, Joel Hestness, Liqun Ma, Natalia Vassilieva, Tianhua Tao, Willie Neiswanger, Zhengzhong Liu, Zhiqiang Shen","submitted_at":"2023-09-19T17:59:54Z","abstract_excerpt":"This paper aims to understand the impacts of various data combinations (e.g., web text, Wikipedia, GitHub, books) on the pretraining of large language models using SlimPajama. SlimPajama is a rigorously deduplicated, multi-source dataset, which has been refined and further deduplicated to 627B tokens from the extensive 1.2T token RedPajama dataset contributed by Together. We have termed our research as SlimPajama-DC, an empirical analysis designed to uncover fundamental characteristics and best practices associated with employing SlimPajama in the training of large language models. During our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10818","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/2309.10818/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":"2026-07-05T08:17:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qo+C4IufgcP3+Kw7aJ0ggV6fDZ4VOX331yjzcKGJo6YAZ4LjpclNlnUQ07MyQWgOQJC49D59I0CfBz4VwBIrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:54:49.546995Z"},"content_sha256":"38e30b1478b277dc302402734ed85b5661a2dac9566d9dca622747fd7423851c","schema_version":"1.0","event_id":"sha256:38e30b1478b277dc302402734ed85b5661a2dac9566d9dca622747fd7423851c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TTFDTLQCDPEVGVZNOP67WAXJDM/bundle.json","state_url":"https://pith.science/pith/TTFDTLQCDPEVGVZNOP67WAXJDM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TTFDTLQCDPEVGVZNOP67WAXJDM/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":"2026-07-08T23:54:49Z","links":{"resolver":"https://pith.science/pith/TTFDTLQCDPEVGVZNOP67WAXJDM","bundle":"https://pith.science/pith/TTFDTLQCDPEVGVZNOP67WAXJDM/bundle.json","state":"https://pith.science/pith/TTFDTLQCDPEVGVZNOP67WAXJDM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TTFDTLQCDPEVGVZNOP67WAXJDM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TTFDTLQCDPEVGVZNOP67WAXJDM","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":"b8399c163c6d413a76b10fa64cd6290a147d2b0ee67221992de46b448c02defe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T17:59:54Z","title_canon_sha256":"2c33e708f0677ddf592c361a7fe7e0739750328a6f50131aad4d123ce3f64a2e"},"schema_version":"1.0","source":{"id":"2309.10818","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10818","created_at":"2026-07-05T08:17:10Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10818v3","created_at":"2026-07-05T08:17:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10818","created_at":"2026-07-05T08:17:10Z"},{"alias_kind":"pith_short_12","alias_value":"TTFDTLQCDPEV","created_at":"2026-07-05T08:17:10Z"},{"alias_kind":"pith_short_16","alias_value":"TTFDTLQCDPEVGVZN","created_at":"2026-07-05T08:17:10Z"},{"alias_kind":"pith_short_8","alias_value":"TTFDTLQC","created_at":"2026-07-05T08:17:10Z"}],"graph_snapshots":[{"event_id":"sha256:38e30b1478b277dc302402734ed85b5661a2dac9566d9dca622747fd7423851c","target":"graph","created_at":"2026-07-05T08:17:10Z","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/2309.10818/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper aims to understand the impacts of various data combinations (e.g., web text, Wikipedia, GitHub, books) on the pretraining of large language models using SlimPajama. SlimPajama is a rigorously deduplicated, multi-source dataset, which has been refined and further deduplicated to 627B tokens from the extensive 1.2T token RedPajama dataset contributed by Together. We have termed our research as SlimPajama-DC, an empirical analysis designed to uncover fundamental characteristics and best practices associated with employing SlimPajama in the training of large language models. During our ","authors_text":"Bowen Tan, Daria Soboleva, Eric Xing, Hongyi Wang, Joel Hestness, Liqun Ma, Natalia Vassilieva, Tianhua Tao, Willie Neiswanger, Zhengzhong Liu, Zhiqiang Shen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T17:59:54Z","title":"SlimPajama-DC: Understanding Data Combinations for LLM Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10818","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":"sha256:6850a01997a36be9d3b030e80269684cca0973bc7a4f6ce57550e61ced402b1e","target":"record","created_at":"2026-07-05T08:17:10Z","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":"b8399c163c6d413a76b10fa64cd6290a147d2b0ee67221992de46b448c02defe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T17:59:54Z","title_canon_sha256":"2c33e708f0677ddf592c361a7fe7e0739750328a6f50131aad4d123ce3f64a2e"},"schema_version":"1.0","source":{"id":"2309.10818","kind":"arxiv","version":3}},"canonical_sha256":"9cca39ae021bc953572d73fdfb02e91b1c8f410eacd7b799be4f617be216e1b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cca39ae021bc953572d73fdfb02e91b1c8f410eacd7b799be4f617be216e1b3","first_computed_at":"2026-07-05T08:17:10.676274Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:17:10.676274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HqKQkgXMP8ZrI355CzwUiOM9oRm0gTvbbf7HjSs97+N5rCmko11Dwj/NBsklLEz1/1QQ9t5aTwpzA5Up0ySCAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:17:10.676999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.10818","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6850a01997a36be9d3b030e80269684cca0973bc7a4f6ce57550e61ced402b1e","sha256:38e30b1478b277dc302402734ed85b5661a2dac9566d9dca622747fd7423851c"],"state_sha256":"a8ae21f2569b8a46e3313e5c4400313a1a212e03640715f511e175e2748bf3cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"me6EX6QqxjZb4NjWiop/Kx04JcH5D98O3aDcrG469LQ5FMgXBkWwrqVQUOv75Xw6K8398dihsxpE0xX54q85AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T23:54:49.549514Z","bundle_sha256":"839042f5abfbab00e7bcd0eb6ac7253ab6ddf67c1ff3cc4eddd9c2e6050ec679"}}