{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:K4FDPMPEH34N4SN4BY7EEUHRZ4","short_pith_number":"pith:K4FDPMPE","canonical_record":{"source":{"id":"2411.12372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-19T09:35:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5e8bb4ec97398d196c1d1d259b5ac4485720ae90d75319eeeead76d85fe4e939","abstract_canon_sha256":"a9c2f4675be8b1e2853ae714abd64aa85fddde1d5017d9210a7eb39035f39c43"},"schema_version":"1.0"},"canonical_sha256":"570a37b1e43ef8de49bc0e3e4250f1cf19c8ff4382dbce6f24d21687601ebc98","source":{"kind":"arxiv","id":"2411.12372","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12372","created_at":"2026-07-05T09:37:20Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12372v1","created_at":"2026-07-05T09:37:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12372","created_at":"2026-07-05T09:37:20Z"},{"alias_kind":"pith_short_12","alias_value":"K4FDPMPEH34N","created_at":"2026-07-05T09:37:20Z"},{"alias_kind":"pith_short_16","alias_value":"K4FDPMPEH34N4SN4","created_at":"2026-07-05T09:37:20Z"},{"alias_kind":"pith_short_8","alias_value":"K4FDPMPE","created_at":"2026-07-05T09:37:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:K4FDPMPEH34N4SN4BY7EEUHRZ4","target":"record","payload":{"canonical_record":{"source":{"id":"2411.12372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-19T09:35:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5e8bb4ec97398d196c1d1d259b5ac4485720ae90d75319eeeead76d85fe4e939","abstract_canon_sha256":"a9c2f4675be8b1e2853ae714abd64aa85fddde1d5017d9210a7eb39035f39c43"},"schema_version":"1.0"},"canonical_sha256":"570a37b1e43ef8de49bc0e3e4250f1cf19c8ff4382dbce6f24d21687601ebc98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:20.413106Z","signature_b64":"8hv20Fa9bpwpmojQ1aUYQvkC/S/RiUj2lR+i6bS/TYJGfmypdDWgNVUCBNQ6rA1SOea9ldyPdg4eZYDdRmEkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"570a37b1e43ef8de49bc0e3e4250f1cf19c8ff4382dbce6f24d21687601ebc98","last_reissued_at":"2026-07-05T09:37:20.412700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:20.412700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.12372","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":"2026-07-05T09:37:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZePNuouPvdX0lJfFrZfov1piBZv61TuuOQ5VgXYlnnDXmwbgAaF6HWo4OJORpKxEMTmUlN2Z/DXxtDeUHBFQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:23:49.669174Z"},"content_sha256":"58616e4595627ddf189dced3c752d106207b24a0c394befb9cebde7df133290b","schema_version":"1.0","event_id":"sha256:58616e4595627ddf189dced3c752d106207b24a0c394befb9cebde7df133290b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:K4FDPMPEH34N4SN4BY7EEUHRZ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RedPajama: an Open Dataset for Training Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anton Alexandrov, Ben Athiwaratkun, Ce Zhang, Christopher R\\'e, Daniel Fu, Huu Nguyen, Irina Rish, Kezhen Chen, Maurice Weber, Max Ryabinin, Percy Liang, Quentin Anthony, Rahul Chalamala, Shane Adams, Tri Dao, Virginia Adams, Xiaozhe Yao, Xiaozhong Lyu, Yonatan Oren","submitted_at":"2024-11-19T09:35:28Z","abstract_excerpt":"Large language models are increasingly becoming a cornerstone technology in artificial intelligence, the sciences, and society as a whole, yet the optimal strategies for dataset composition and filtering remain largely elusive. Many of the top-performing models lack transparency in their dataset curation and model development processes, posing an obstacle to the development of fully open language models. In this paper, we identify three core data-related challenges that must be addressed to advance open-source language models. These include (1) transparency in model development, including the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12372","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/2411.12372/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":"2026-07-05T09:37:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rG6oUx06o0Jof8vmG4slHdsy6DNKMQlEqHOvI4pwIAvRUTEOvCqLIRht+U9sq11Ap9kR3jY2hi+9u6ImkUvSBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:23:49.669588Z"},"content_sha256":"3e2d0ba446a638b81e3fc85c9261c7169ac9eb438190ffac1c6ed191aee707f9","schema_version":"1.0","event_id":"sha256:3e2d0ba446a638b81e3fc85c9261c7169ac9eb438190ffac1c6ed191aee707f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K4FDPMPEH34N4SN4BY7EEUHRZ4/bundle.json","state_url":"https://pith.science/pith/K4FDPMPEH34N4SN4BY7EEUHRZ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K4FDPMPEH34N4SN4BY7EEUHRZ4/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":"2026-07-06T16:23:49Z","links":{"resolver":"https://pith.science/pith/K4FDPMPEH34N4SN4BY7EEUHRZ4","bundle":"https://pith.science/pith/K4FDPMPEH34N4SN4BY7EEUHRZ4/bundle.json","state":"https://pith.science/pith/K4FDPMPEH34N4SN4BY7EEUHRZ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K4FDPMPEH34N4SN4BY7EEUHRZ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K4FDPMPEH34N4SN4BY7EEUHRZ4","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":"a9c2f4675be8b1e2853ae714abd64aa85fddde1d5017d9210a7eb39035f39c43","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-19T09:35:28Z","title_canon_sha256":"5e8bb4ec97398d196c1d1d259b5ac4485720ae90d75319eeeead76d85fe4e939"},"schema_version":"1.0","source":{"id":"2411.12372","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12372","created_at":"2026-07-05T09:37:20Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12372v1","created_at":"2026-07-05T09:37:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12372","created_at":"2026-07-05T09:37:20Z"},{"alias_kind":"pith_short_12","alias_value":"K4FDPMPEH34N","created_at":"2026-07-05T09:37:20Z"},{"alias_kind":"pith_short_16","alias_value":"K4FDPMPEH34N4SN4","created_at":"2026-07-05T09:37:20Z"},{"alias_kind":"pith_short_8","alias_value":"K4FDPMPE","created_at":"2026-07-05T09:37:20Z"}],"graph_snapshots":[{"event_id":"sha256:3e2d0ba446a638b81e3fc85c9261c7169ac9eb438190ffac1c6ed191aee707f9","target":"graph","created_at":"2026-07-05T09:37:20Z","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/2411.12372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are increasingly becoming a cornerstone technology in artificial intelligence, the sciences, and society as a whole, yet the optimal strategies for dataset composition and filtering remain largely elusive. Many of the top-performing models lack transparency in their dataset curation and model development processes, posing an obstacle to the development of fully open language models. In this paper, we identify three core data-related challenges that must be addressed to advance open-source language models. These include (1) transparency in model development, including the ","authors_text":"Anton Alexandrov, Ben Athiwaratkun, Ce Zhang, Christopher R\\'e, Daniel Fu, Huu Nguyen, Irina Rish, Kezhen Chen, Maurice Weber, Max Ryabinin, Percy Liang, Quentin Anthony, Rahul Chalamala, Shane Adams, Tri Dao, Virginia Adams, Xiaozhe Yao, Xiaozhong Lyu, Yonatan Oren","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-19T09:35:28Z","title":"RedPajama: an Open Dataset for Training Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12372","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":"sha256:58616e4595627ddf189dced3c752d106207b24a0c394befb9cebde7df133290b","target":"record","created_at":"2026-07-05T09:37:20Z","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":"a9c2f4675be8b1e2853ae714abd64aa85fddde1d5017d9210a7eb39035f39c43","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-19T09:35:28Z","title_canon_sha256":"5e8bb4ec97398d196c1d1d259b5ac4485720ae90d75319eeeead76d85fe4e939"},"schema_version":"1.0","source":{"id":"2411.12372","kind":"arxiv","version":1}},"canonical_sha256":"570a37b1e43ef8de49bc0e3e4250f1cf19c8ff4382dbce6f24d21687601ebc98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"570a37b1e43ef8de49bc0e3e4250f1cf19c8ff4382dbce6f24d21687601ebc98","first_computed_at":"2026-07-05T09:37:20.412700Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:37:20.412700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8hv20Fa9bpwpmojQ1aUYQvkC/S/RiUj2lR+i6bS/TYJGfmypdDWgNVUCBNQ6rA1SOea9ldyPdg4eZYDdRmEkBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:37:20.413106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.12372","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58616e4595627ddf189dced3c752d106207b24a0c394befb9cebde7df133290b","sha256:3e2d0ba446a638b81e3fc85c9261c7169ac9eb438190ffac1c6ed191aee707f9"],"state_sha256":"c6abdd0dba56964f05c85a236e79ee29965c0b11a9b3a69df4b1b9d53c725b78"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UuGBOQCuuahnOp22fd1QexhAHubu5Cs4j6G6/QL1wMtREPowq3Hs7R4uGP9YL9PDKhODW2eVghWjloJ+/xivBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:23:49.671589Z","bundle_sha256":"d8818082d43428c71e7ca20850ece3563cb1ec119279364f4965d9e975776605"}}