{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6K5LVWVSOI3ZHOXVFVBIBHJ2TK","short_pith_number":"pith:6K5LVWVS","canonical_record":{"source":{"id":"2105.11321","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T14:57:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"225f947bdb7d780a8208dd17770fccd602a88626b692eb0960f124bd33bddd7f","abstract_canon_sha256":"d68e5ddbe3c3fb54f634016b573c311eff72ac724c117e5513a940ac185eaaca"},"schema_version":"1.0"},"canonical_sha256":"f2babadab2723793baf52d42809d3a9aa4a1d20965388cb66e722c5b4fefb315","source":{"kind":"arxiv","id":"2105.11321","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.11321","created_at":"2026-07-05T02:42:37Z"},{"alias_kind":"arxiv_version","alias_value":"2105.11321v1","created_at":"2026-07-05T02:42:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11321","created_at":"2026-07-05T02:42:37Z"},{"alias_kind":"pith_short_12","alias_value":"6K5LVWVSOI3Z","created_at":"2026-07-05T02:42:37Z"},{"alias_kind":"pith_short_16","alias_value":"6K5LVWVSOI3ZHOXV","created_at":"2026-07-05T02:42:37Z"},{"alias_kind":"pith_short_8","alias_value":"6K5LVWVS","created_at":"2026-07-05T02:42:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6K5LVWVSOI3ZHOXVFVBIBHJ2TK","target":"record","payload":{"canonical_record":{"source":{"id":"2105.11321","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T14:57:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"225f947bdb7d780a8208dd17770fccd602a88626b692eb0960f124bd33bddd7f","abstract_canon_sha256":"d68e5ddbe3c3fb54f634016b573c311eff72ac724c117e5513a940ac185eaaca"},"schema_version":"1.0"},"canonical_sha256":"f2babadab2723793baf52d42809d3a9aa4a1d20965388cb66e722c5b4fefb315","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:37.455141Z","signature_b64":"dZt3GOsGQJhgyB/xqHuX65HvHYUnASm8yF/vElvbCZXKlP5rGGuEIfqwcv0W6Dpa3M6i5pzrtodmPz7JsFRAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2babadab2723793baf52d42809d3a9aa4a1d20965388cb66e722c5b4fefb315","last_reissued_at":"2026-07-05T02:42:37.454707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:37.454707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.11321","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":"2026-07-05T02:42:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u2Vw1CZNtGDidKwZHAcnh+r2SKAf2r5IJ4/MklDX6KiDi/g7sMlVmWQiNSrWxHW2vwntwyMtClwtiXZw5wZvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:04:34.197702Z"},"content_sha256":"6faa86a52c15809260bd59aabe18586827cfee9d83bf94a3be84e06ff6c8b2b0","schema_version":"1.0","event_id":"sha256:6faa86a52c15809260bd59aabe18586827cfee9d83bf94a3be84e06ff6c8b2b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6K5LVWVSOI3ZHOXVFVBIBHJ2TK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Language Models for Nineteenth-Century English","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Giovanni Colavizza, Kaspar Beelen, Kasra Hosseini, Mariona Coll Ardanuy","submitted_at":"2021-05-24T14:57:34Z","abstract_excerpt":"We present four types of neural language models trained on a large historical dataset of books in English, published between 1760-1900 and comprised of ~5.1 billion tokens. The language model architectures include static (word2vec and fastText) and contextualized models (BERT and Flair). For each architecture, we trained a model instance using the whole dataset. Additionally, we trained separate instances on text published before 1850 for the two static models, and four instances considering different time slices for BERT. Our models have already been used in various downstream tasks where the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11321","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/2105.11321/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":"2026-07-05T02:42:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HxqRunW3Rw6AwBVqkpi9FRHj2TztlKeMRdgf0taneui4ByPhj5ZZHWAiJGhA2KAIJldS8q+89QNqhphjF4osAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:04:34.198182Z"},"content_sha256":"3735d03beadb87b1b6d53c5d4f1e07f17b496ab2ff7f4b7da5921a1fe90a77c3","schema_version":"1.0","event_id":"sha256:3735d03beadb87b1b6d53c5d4f1e07f17b496ab2ff7f4b7da5921a1fe90a77c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6K5LVWVSOI3ZHOXVFVBIBHJ2TK/bundle.json","state_url":"https://pith.science/pith/6K5LVWVSOI3ZHOXVFVBIBHJ2TK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6K5LVWVSOI3ZHOXVFVBIBHJ2TK/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":"2026-08-05T03:04:34Z","links":{"resolver":"https://pith.science/pith/6K5LVWVSOI3ZHOXVFVBIBHJ2TK","bundle":"https://pith.science/pith/6K5LVWVSOI3ZHOXVFVBIBHJ2TK/bundle.json","state":"https://pith.science/pith/6K5LVWVSOI3ZHOXVFVBIBHJ2TK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6K5LVWVSOI3ZHOXVFVBIBHJ2TK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6K5LVWVSOI3ZHOXVFVBIBHJ2TK","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":"d68e5ddbe3c3fb54f634016b573c311eff72ac724c117e5513a940ac185eaaca","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T14:57:34Z","title_canon_sha256":"225f947bdb7d780a8208dd17770fccd602a88626b692eb0960f124bd33bddd7f"},"schema_version":"1.0","source":{"id":"2105.11321","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.11321","created_at":"2026-07-05T02:42:37Z"},{"alias_kind":"arxiv_version","alias_value":"2105.11321v1","created_at":"2026-07-05T02:42:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11321","created_at":"2026-07-05T02:42:37Z"},{"alias_kind":"pith_short_12","alias_value":"6K5LVWVSOI3Z","created_at":"2026-07-05T02:42:37Z"},{"alias_kind":"pith_short_16","alias_value":"6K5LVWVSOI3ZHOXV","created_at":"2026-07-05T02:42:37Z"},{"alias_kind":"pith_short_8","alias_value":"6K5LVWVS","created_at":"2026-07-05T02:42:37Z"}],"graph_snapshots":[{"event_id":"sha256:3735d03beadb87b1b6d53c5d4f1e07f17b496ab2ff7f4b7da5921a1fe90a77c3","target":"graph","created_at":"2026-07-05T02:42:37Z","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/2105.11321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present four types of neural language models trained on a large historical dataset of books in English, published between 1760-1900 and comprised of ~5.1 billion tokens. The language model architectures include static (word2vec and fastText) and contextualized models (BERT and Flair). For each architecture, we trained a model instance using the whole dataset. Additionally, we trained separate instances on text published before 1850 for the two static models, and four instances considering different time slices for BERT. Our models have already been used in various downstream tasks where the","authors_text":"Giovanni Colavizza, Kaspar Beelen, Kasra Hosseini, Mariona Coll Ardanuy","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T14:57:34Z","title":"Neural Language Models for Nineteenth-Century English"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11321","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":"sha256:6faa86a52c15809260bd59aabe18586827cfee9d83bf94a3be84e06ff6c8b2b0","target":"record","created_at":"2026-07-05T02:42:37Z","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":"d68e5ddbe3c3fb54f634016b573c311eff72ac724c117e5513a940ac185eaaca","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T14:57:34Z","title_canon_sha256":"225f947bdb7d780a8208dd17770fccd602a88626b692eb0960f124bd33bddd7f"},"schema_version":"1.0","source":{"id":"2105.11321","kind":"arxiv","version":1}},"canonical_sha256":"f2babadab2723793baf52d42809d3a9aa4a1d20965388cb66e722c5b4fefb315","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2babadab2723793baf52d42809d3a9aa4a1d20965388cb66e722c5b4fefb315","first_computed_at":"2026-07-05T02:42:37.454707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:42:37.454707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dZt3GOsGQJhgyB/xqHuX65HvHYUnASm8yF/vElvbCZXKlP5rGGuEIfqwcv0W6Dpa3M6i5pzrtodmPz7JsFRAAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:42:37.455141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.11321","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6faa86a52c15809260bd59aabe18586827cfee9d83bf94a3be84e06ff6c8b2b0","sha256:3735d03beadb87b1b6d53c5d4f1e07f17b496ab2ff7f4b7da5921a1fe90a77c3"],"state_sha256":"f11fa2924283a8400e242a49ada6f540af2a923018d047754e163293a525d022"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nxq5s3758+LuE5vusY8AYC/kQOzH8um3JOhTIh4hnz1jSo4zVURw0ImVrtE8TxIX9binvUt2iFIuolxW2kp2Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T03:04:34.201759Z","bundle_sha256":"dde1c50c8cb77facd5728e7b4dd42f484fea78cab15e22845d2334d5aa3a38c1"}}