{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5T53UCRZTHQQW3KU2TRTFV3QIF","short_pith_number":"pith:5T53UCRZ","canonical_record":{"source":{"id":"2201.07311","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-13T23:45:24Z","cross_cats_sorted":[],"title_canon_sha256":"a78b72d81614991cd5c6f968717a1d13eeb528524ab1c4c4fd63fb2e763f7de1","abstract_canon_sha256":"336e74dc5d6a9e2f36f05d18eec1c15dcaef99bb78eb14e94005cff4f84e2090"},"schema_version":"1.0"},"canonical_sha256":"ecfbba0a3999e10b6d54d4e332d770417840860e48a49caef082c8ba88ada1f7","source":{"kind":"arxiv","id":"2201.07311","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.07311","created_at":"2026-07-05T03:49:45Z"},{"alias_kind":"arxiv_version","alias_value":"2201.07311v1","created_at":"2026-07-05T03:49:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.07311","created_at":"2026-07-05T03:49:45Z"},{"alias_kind":"pith_short_12","alias_value":"5T53UCRZTHQQ","created_at":"2026-07-05T03:49:45Z"},{"alias_kind":"pith_short_16","alias_value":"5T53UCRZTHQQW3KU","created_at":"2026-07-05T03:49:45Z"},{"alias_kind":"pith_short_8","alias_value":"5T53UCRZ","created_at":"2026-07-05T03:49:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5T53UCRZTHQQW3KU2TRTFV3QIF","target":"record","payload":{"canonical_record":{"source":{"id":"2201.07311","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-13T23:45:24Z","cross_cats_sorted":[],"title_canon_sha256":"a78b72d81614991cd5c6f968717a1d13eeb528524ab1c4c4fd63fb2e763f7de1","abstract_canon_sha256":"336e74dc5d6a9e2f36f05d18eec1c15dcaef99bb78eb14e94005cff4f84e2090"},"schema_version":"1.0"},"canonical_sha256":"ecfbba0a3999e10b6d54d4e332d770417840860e48a49caef082c8ba88ada1f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:49:45.292027Z","signature_b64":"pjmaKvY68bIn9xje/g4KQuKpMNajeB7Xd5qkOesMN/MVf4NhGnp8lQP929/gLn2Y8uzcCoebLD5QMfc3a2A0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecfbba0a3999e10b6d54d4e332d770417840860e48a49caef082c8ba88ada1f7","last_reissued_at":"2026-07-05T03:49:45.291514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:49:45.291514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.07311","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":"2026-07-05T03:49:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CofVoO+98ZG8xd2O5mGTsbl5MMik8SumTi4w+f7Ln7paW/ugBBjoigU0ckDfzYkDrb73ylLcZCxhK73nrEigAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:19:44.126078Z"},"content_sha256":"fa610d4b2fb4fe6e6065e0f26fa9d4c395f70540c848219f6ca9b05704d24b39","schema_version":"1.0","event_id":"sha256:fa610d4b2fb4fe6e6065e0f26fa9d4c395f70540c848219f6ca9b05704d24b39"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5T53UCRZTHQQW3KU2TRTFV3QIF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Datasheet for the Pile","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kieran Bicheno, Leo Gao, Stella Biderman","submitted_at":"2022-01-13T23:45:24Z","abstract_excerpt":"This datasheet describes the Pile, a 825 GiB dataset of human-authored text compiled by EleutherAI for use in large-scale language modeling. The Pile is comprised of 22 different text sources, ranging from original scrapes done for this project, to text data made available by the data owners, to third-party scrapes available online."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.07311","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/2201.07311/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":"2026-07-05T03:49:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7fXbyLx5RQ8/ILISjvQ2bd5ueplMhpGw4HrX18/XS86K5FsvXWCUAz8OGihaOmCgVoli6VRvexzhzkYK8ceRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:19:44.126586Z"},"content_sha256":"c5216fe451645f3d5243fafe71409b0bace0d06841c2cec020590f6ed44b8890","schema_version":"1.0","event_id":"sha256:c5216fe451645f3d5243fafe71409b0bace0d06841c2cec020590f6ed44b8890"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5T53UCRZTHQQW3KU2TRTFV3QIF/bundle.json","state_url":"https://pith.science/pith/5T53UCRZTHQQW3KU2TRTFV3QIF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5T53UCRZTHQQW3KU2TRTFV3QIF/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":"2026-08-14T13:19:44Z","links":{"resolver":"https://pith.science/pith/5T53UCRZTHQQW3KU2TRTFV3QIF","bundle":"https://pith.science/pith/5T53UCRZTHQQW3KU2TRTFV3QIF/bundle.json","state":"https://pith.science/pith/5T53UCRZTHQQW3KU2TRTFV3QIF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5T53UCRZTHQQW3KU2TRTFV3QIF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5T53UCRZTHQQW3KU2TRTFV3QIF","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":"336e74dc5d6a9e2f36f05d18eec1c15dcaef99bb78eb14e94005cff4f84e2090","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-13T23:45:24Z","title_canon_sha256":"a78b72d81614991cd5c6f968717a1d13eeb528524ab1c4c4fd63fb2e763f7de1"},"schema_version":"1.0","source":{"id":"2201.07311","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.07311","created_at":"2026-07-05T03:49:45Z"},{"alias_kind":"arxiv_version","alias_value":"2201.07311v1","created_at":"2026-07-05T03:49:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.07311","created_at":"2026-07-05T03:49:45Z"},{"alias_kind":"pith_short_12","alias_value":"5T53UCRZTHQQ","created_at":"2026-07-05T03:49:45Z"},{"alias_kind":"pith_short_16","alias_value":"5T53UCRZTHQQW3KU","created_at":"2026-07-05T03:49:45Z"},{"alias_kind":"pith_short_8","alias_value":"5T53UCRZ","created_at":"2026-07-05T03:49:45Z"}],"graph_snapshots":[{"event_id":"sha256:c5216fe451645f3d5243fafe71409b0bace0d06841c2cec020590f6ed44b8890","target":"graph","created_at":"2026-07-05T03:49:45Z","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/2201.07311/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This datasheet describes the Pile, a 825 GiB dataset of human-authored text compiled by EleutherAI for use in large-scale language modeling. The Pile is comprised of 22 different text sources, ranging from original scrapes done for this project, to text data made available by the data owners, to third-party scrapes available online.","authors_text":"Kieran Bicheno, Leo Gao, Stella Biderman","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-13T23:45:24Z","title":"Datasheet for the Pile"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.07311","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:fa610d4b2fb4fe6e6065e0f26fa9d4c395f70540c848219f6ca9b05704d24b39","target":"record","created_at":"2026-07-05T03:49:45Z","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":"336e74dc5d6a9e2f36f05d18eec1c15dcaef99bb78eb14e94005cff4f84e2090","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-13T23:45:24Z","title_canon_sha256":"a78b72d81614991cd5c6f968717a1d13eeb528524ab1c4c4fd63fb2e763f7de1"},"schema_version":"1.0","source":{"id":"2201.07311","kind":"arxiv","version":1}},"canonical_sha256":"ecfbba0a3999e10b6d54d4e332d770417840860e48a49caef082c8ba88ada1f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecfbba0a3999e10b6d54d4e332d770417840860e48a49caef082c8ba88ada1f7","first_computed_at":"2026-07-05T03:49:45.291514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:49:45.291514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pjmaKvY68bIn9xje/g4KQuKpMNajeB7Xd5qkOesMN/MVf4NhGnp8lQP929/gLn2Y8uzcCoebLD5QMfc3a2A0Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:49:45.292027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.07311","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa610d4b2fb4fe6e6065e0f26fa9d4c395f70540c848219f6ca9b05704d24b39","sha256:c5216fe451645f3d5243fafe71409b0bace0d06841c2cec020590f6ed44b8890"],"state_sha256":"18084ab26d0aa730d8d37736ae610f9ada7b48e092e69fdf579c3ba139cf4d47"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"widxjsPdDQNQRUVMguSXAFAJr4DaXF080abLNC1AF84N9W2Wjae5OJ8a7SJyUPk9Z8PmpyBtsUen33lnxPHbBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T13:19:44.130658Z","bundle_sha256":"cae9095a55bcd5ee10084ba69b3048c1045a73cba1f756aea027b9d34735718a"}}