{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TCXGBUXNUZJ347MZ7U65T6V4OK","short_pith_number":"pith:TCXGBUXN","canonical_record":{"source":{"id":"2304.08442","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-17T17:03:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"27c34d5ec0e50b6191b8ca1d35d56e5300817005da24b93606e7269df02fc034","abstract_canon_sha256":"7481870a98bab4ee970039a74dc35924f87befe4073d937558eb341e2a6783d2"},"schema_version":"1.0"},"canonical_sha256":"98ae60d2eda653be7d99fd3dd9fabc72b77094904008b173d149da8311a39344","source":{"kind":"arxiv","id":"2304.08442","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08442","created_at":"2026-07-05T06:01:52Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08442v1","created_at":"2026-07-05T06:01:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08442","created_at":"2026-07-05T06:01:52Z"},{"alias_kind":"pith_short_12","alias_value":"TCXGBUXNUZJ3","created_at":"2026-07-05T06:01:52Z"},{"alias_kind":"pith_short_16","alias_value":"TCXGBUXNUZJ347MZ","created_at":"2026-07-05T06:01:52Z"},{"alias_kind":"pith_short_8","alias_value":"TCXGBUXN","created_at":"2026-07-05T06:01:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TCXGBUXNUZJ347MZ7U65T6V4OK","target":"record","payload":{"canonical_record":{"source":{"id":"2304.08442","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-17T17:03:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"27c34d5ec0e50b6191b8ca1d35d56e5300817005da24b93606e7269df02fc034","abstract_canon_sha256":"7481870a98bab4ee970039a74dc35924f87befe4073d937558eb341e2a6783d2"},"schema_version":"1.0"},"canonical_sha256":"98ae60d2eda653be7d99fd3dd9fabc72b77094904008b173d149da8311a39344","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:52.512477Z","signature_b64":"obWwxBkbOADkHtg4wa1d+GEzhnvhAGMRdwu9xyll/UT9UwfvrKw67G23fnJ0qTzI2nHOK+BjQ7QyIN0aFkPHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98ae60d2eda653be7d99fd3dd9fabc72b77094904008b173d149da8311a39344","last_reissued_at":"2026-07-05T06:01:52.512104Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:52.512104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.08442","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":"2026-07-05T06:01:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Cm/wKXpKJElIb4HbIGh+KutGbULa6k/6KgVYCjxY18EmC1hdRL53XLyNB8SfPPkBt2m2pniEIpBJxuPCvjVCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:29:26.898352Z"},"content_sha256":"3c7477974b20cdf4a67556e2570b7e555d2e2e9ac70c50d06dc42f9f438000b0","schema_version":"1.0","event_id":"sha256:3c7477974b20cdf4a67556e2570b7e555d2e2e9ac70c50d06dc42f9f438000b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TCXGBUXNUZJ347MZ7U65T6V4OK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The MiniPile Challenge for Data-Efficient Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jean Kaddour","submitted_at":"2023-04-17T17:03:56Z","abstract_excerpt":"The ever-growing diversity of pre-training text corpora has equipped language models with generalization capabilities across various downstream tasks. However, such diverse datasets are often too large for academic budgets; hence, most research on Transformer architectures, training procedures, optimizers, etc. gets conducted on smaller, homogeneous datasets. To this end, we present The MiniPile Challenge, where one pre-trains a language model on a diverse text corpus containing at most 1M documents. MiniPile is a 6GB subset of the deduplicated 825GB The Pile corpus. To curate MiniPile, we per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08442","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/2304.08442/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":"2026-07-05T06:01:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s+GNsaVY1y+8yhkZAbrDnEQjl3XD5bq1Da/YGbGy1mrCk5lh6beDzjCTxBmbqspZ9wg/5DDFEDRe9b4+39tCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:29:26.898864Z"},"content_sha256":"09f998515e4c0247bafc56d1fc1484354b8ccb628ca72af7bb51c43a7ebdffc7","schema_version":"1.0","event_id":"sha256:09f998515e4c0247bafc56d1fc1484354b8ccb628ca72af7bb51c43a7ebdffc7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TCXGBUXNUZJ347MZ7U65T6V4OK/bundle.json","state_url":"https://pith.science/pith/TCXGBUXNUZJ347MZ7U65T6V4OK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TCXGBUXNUZJ347MZ7U65T6V4OK/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":"2026-08-10T23:29:26Z","links":{"resolver":"https://pith.science/pith/TCXGBUXNUZJ347MZ7U65T6V4OK","bundle":"https://pith.science/pith/TCXGBUXNUZJ347MZ7U65T6V4OK/bundle.json","state":"https://pith.science/pith/TCXGBUXNUZJ347MZ7U65T6V4OK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TCXGBUXNUZJ347MZ7U65T6V4OK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TCXGBUXNUZJ347MZ7U65T6V4OK","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":"7481870a98bab4ee970039a74dc35924f87befe4073d937558eb341e2a6783d2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-17T17:03:56Z","title_canon_sha256":"27c34d5ec0e50b6191b8ca1d35d56e5300817005da24b93606e7269df02fc034"},"schema_version":"1.0","source":{"id":"2304.08442","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08442","created_at":"2026-07-05T06:01:52Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08442v1","created_at":"2026-07-05T06:01:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08442","created_at":"2026-07-05T06:01:52Z"},{"alias_kind":"pith_short_12","alias_value":"TCXGBUXNUZJ3","created_at":"2026-07-05T06:01:52Z"},{"alias_kind":"pith_short_16","alias_value":"TCXGBUXNUZJ347MZ","created_at":"2026-07-05T06:01:52Z"},{"alias_kind":"pith_short_8","alias_value":"TCXGBUXN","created_at":"2026-07-05T06:01:52Z"}],"graph_snapshots":[{"event_id":"sha256:09f998515e4c0247bafc56d1fc1484354b8ccb628ca72af7bb51c43a7ebdffc7","target":"graph","created_at":"2026-07-05T06:01:52Z","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/2304.08442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ever-growing diversity of pre-training text corpora has equipped language models with generalization capabilities across various downstream tasks. However, such diverse datasets are often too large for academic budgets; hence, most research on Transformer architectures, training procedures, optimizers, etc. gets conducted on smaller, homogeneous datasets. To this end, we present The MiniPile Challenge, where one pre-trains a language model on a diverse text corpus containing at most 1M documents. MiniPile is a 6GB subset of the deduplicated 825GB The Pile corpus. To curate MiniPile, we per","authors_text":"Jean Kaddour","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-17T17:03:56Z","title":"The MiniPile Challenge for Data-Efficient Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08442","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":"sha256:3c7477974b20cdf4a67556e2570b7e555d2e2e9ac70c50d06dc42f9f438000b0","target":"record","created_at":"2026-07-05T06:01:52Z","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":"7481870a98bab4ee970039a74dc35924f87befe4073d937558eb341e2a6783d2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-17T17:03:56Z","title_canon_sha256":"27c34d5ec0e50b6191b8ca1d35d56e5300817005da24b93606e7269df02fc034"},"schema_version":"1.0","source":{"id":"2304.08442","kind":"arxiv","version":1}},"canonical_sha256":"98ae60d2eda653be7d99fd3dd9fabc72b77094904008b173d149da8311a39344","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98ae60d2eda653be7d99fd3dd9fabc72b77094904008b173d149da8311a39344","first_computed_at":"2026-07-05T06:01:52.512104Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:01:52.512104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"obWwxBkbOADkHtg4wa1d+GEzhnvhAGMRdwu9xyll/UT9UwfvrKw67G23fnJ0qTzI2nHOK+BjQ7QyIN0aFkPHDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:01:52.512477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.08442","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c7477974b20cdf4a67556e2570b7e555d2e2e9ac70c50d06dc42f9f438000b0","sha256:09f998515e4c0247bafc56d1fc1484354b8ccb628ca72af7bb51c43a7ebdffc7"],"state_sha256":"a731e1be0125dba03bd9e6b30a7104fcf83323b4a8dafc06a18640a583fec733"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6irccEXC+/hBqG1TU5B13BNtW6hO9GQZezdDZzTvL2FIP1OjBFN6SXt57CNA+Mdl1oiu6S9n8dILej16e1caAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T23:29:26.903635Z","bundle_sha256":"5815cbce9e611df31d75c93acbb10b75dd316c0bcf5042c71458d3d7ca90c344"}}