{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ULCBYIYKJM7FWETNYBVKIZEEUY","short_pith_number":"pith:ULCBYIYK","canonical_record":{"source":{"id":"2306.17810","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-30T17:16:04Z","cross_cats_sorted":["econ.GN","q-fin.EC"],"title_canon_sha256":"b9e58f29d90618476bf80c00f70f6bac75eb5bd05b6c34b081c0eb07aaac3a81","abstract_canon_sha256":"81bf740629f5f12e478b204978331160ce29f0bf9c6da3c20b1a87ccf9d566a8"},"schema_version":"1.0"},"canonical_sha256":"a2c41c230a4b3e5b126dc06aa46484a614394a7665b0f3bbd567af74f6149837","source":{"kind":"arxiv","id":"2306.17810","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17810","created_at":"2026-07-05T06:44:08Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17810v2","created_at":"2026-07-05T06:44:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17810","created_at":"2026-07-05T06:44:08Z"},{"alias_kind":"pith_short_12","alias_value":"ULCBYIYKJM7F","created_at":"2026-07-05T06:44:08Z"},{"alias_kind":"pith_short_16","alias_value":"ULCBYIYKJM7FWETN","created_at":"2026-07-05T06:44:08Z"},{"alias_kind":"pith_short_8","alias_value":"ULCBYIYK","created_at":"2026-07-05T06:44:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ULCBYIYKJM7FWETNYBVKIZEEUY","target":"record","payload":{"canonical_record":{"source":{"id":"2306.17810","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-30T17:16:04Z","cross_cats_sorted":["econ.GN","q-fin.EC"],"title_canon_sha256":"b9e58f29d90618476bf80c00f70f6bac75eb5bd05b6c34b081c0eb07aaac3a81","abstract_canon_sha256":"81bf740629f5f12e478b204978331160ce29f0bf9c6da3c20b1a87ccf9d566a8"},"schema_version":"1.0"},"canonical_sha256":"a2c41c230a4b3e5b126dc06aa46484a614394a7665b0f3bbd567af74f6149837","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:08.209164Z","signature_b64":"yfo0PFv/MtjJJHjo14ByrFEzQk4UuWuBCHuSuCIcIH1MAYGaHOzCBjqfyw3bLJUov3H01CcTpX0QwgFAtDw5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2c41c230a4b3e5b126dc06aa46484a614394a7665b0f3bbd567af74f6149837","last_reissued_at":"2026-07-05T06:44:08.208660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:08.208660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.17810","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:44:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mz9puF8GZcLnOsZnZ0g3w5uOXHhrqukJGRoo7ruJy6aw811T4WzEPRhZ6tlbmEqlGgaSe2zh8NFqP6inseclDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:38:50.238528Z"},"content_sha256":"313f661706102df0ab1854b1b51818ec07d528c22309162dbadb4a417fbdaa84","schema_version":"1.0","event_id":"sha256:313f661706102df0ab1854b1b51818ec07d528c22309162dbadb4a417fbdaa84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ULCBYIYKJM7FWETNYBVKIZEEUY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Massive Scale Semantic Similarity Dataset of Historical English","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["econ.GN","q-fin.EC"],"primary_cat":"cs.CL","authors_text":"Emily Silcock, Melissa Dell","submitted_at":"2023-06-30T17:16:04Z","abstract_excerpt":"A diversity of tasks use language models trained on semantic similarity data. While there are a variety of datasets that capture semantic similarity, they are either constructed from modern web data or are relatively small datasets created in the past decade by human annotators. This study utilizes a novel source, newly digitized articles from off-copyright, local U.S. newspapers, to assemble a massive-scale semantic similarity dataset spanning 70 years from 1920 to 1989 and containing nearly 400M positive semantic similarity pairs. Historically, around half of articles in U.S. local newspaper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17810","kind":"arxiv","version":2},"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/2306.17810/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":"2026-07-05T06:44:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+6JR51wzdXBFaKqrAhdFqSv5k3jtKY7O7vyyV62y4OGFDDTkIVNexviVs7qjKLCCudMDqqGr8YeEqL6yM3pSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:38:50.239183Z"},"content_sha256":"965f9bf3bccf9c13e7a017b80e71549327b9e7883a32e5cfcc816d6c1c67ffd5","schema_version":"1.0","event_id":"sha256:965f9bf3bccf9c13e7a017b80e71549327b9e7883a32e5cfcc816d6c1c67ffd5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ULCBYIYKJM7FWETNYBVKIZEEUY/bundle.json","state_url":"https://pith.science/pith/ULCBYIYKJM7FWETNYBVKIZEEUY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ULCBYIYKJM7FWETNYBVKIZEEUY/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":"2026-08-03T22:38:50Z","links":{"resolver":"https://pith.science/pith/ULCBYIYKJM7FWETNYBVKIZEEUY","bundle":"https://pith.science/pith/ULCBYIYKJM7FWETNYBVKIZEEUY/bundle.json","state":"https://pith.science/pith/ULCBYIYKJM7FWETNYBVKIZEEUY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ULCBYIYKJM7FWETNYBVKIZEEUY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ULCBYIYKJM7FWETNYBVKIZEEUY","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":"81bf740629f5f12e478b204978331160ce29f0bf9c6da3c20b1a87ccf9d566a8","cross_cats_sorted":["econ.GN","q-fin.EC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-30T17:16:04Z","title_canon_sha256":"b9e58f29d90618476bf80c00f70f6bac75eb5bd05b6c34b081c0eb07aaac3a81"},"schema_version":"1.0","source":{"id":"2306.17810","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17810","created_at":"2026-07-05T06:44:08Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17810v2","created_at":"2026-07-05T06:44:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17810","created_at":"2026-07-05T06:44:08Z"},{"alias_kind":"pith_short_12","alias_value":"ULCBYIYKJM7F","created_at":"2026-07-05T06:44:08Z"},{"alias_kind":"pith_short_16","alias_value":"ULCBYIYKJM7FWETN","created_at":"2026-07-05T06:44:08Z"},{"alias_kind":"pith_short_8","alias_value":"ULCBYIYK","created_at":"2026-07-05T06:44:08Z"}],"graph_snapshots":[{"event_id":"sha256:965f9bf3bccf9c13e7a017b80e71549327b9e7883a32e5cfcc816d6c1c67ffd5","target":"graph","created_at":"2026-07-05T06:44:08Z","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/2306.17810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A diversity of tasks use language models trained on semantic similarity data. While there are a variety of datasets that capture semantic similarity, they are either constructed from modern web data or are relatively small datasets created in the past decade by human annotators. This study utilizes a novel source, newly digitized articles from off-copyright, local U.S. newspapers, to assemble a massive-scale semantic similarity dataset spanning 70 years from 1920 to 1989 and containing nearly 400M positive semantic similarity pairs. Historically, around half of articles in U.S. local newspaper","authors_text":"Emily Silcock, Melissa Dell","cross_cats":["econ.GN","q-fin.EC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-30T17:16:04Z","title":"A Massive Scale Semantic Similarity Dataset of Historical English"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17810","kind":"arxiv","version":2},"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":"sha256:313f661706102df0ab1854b1b51818ec07d528c22309162dbadb4a417fbdaa84","target":"record","created_at":"2026-07-05T06:44:08Z","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":"81bf740629f5f12e478b204978331160ce29f0bf9c6da3c20b1a87ccf9d566a8","cross_cats_sorted":["econ.GN","q-fin.EC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-30T17:16:04Z","title_canon_sha256":"b9e58f29d90618476bf80c00f70f6bac75eb5bd05b6c34b081c0eb07aaac3a81"},"schema_version":"1.0","source":{"id":"2306.17810","kind":"arxiv","version":2}},"canonical_sha256":"a2c41c230a4b3e5b126dc06aa46484a614394a7665b0f3bbd567af74f6149837","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2c41c230a4b3e5b126dc06aa46484a614394a7665b0f3bbd567af74f6149837","first_computed_at":"2026-07-05T06:44:08.208660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:44:08.208660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yfo0PFv/MtjJJHjo14ByrFEzQk4UuWuBCHuSuCIcIH1MAYGaHOzCBjqfyw3bLJUov3H01CcTpX0QwgFAtDw5CA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:44:08.209164Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.17810","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:313f661706102df0ab1854b1b51818ec07d528c22309162dbadb4a417fbdaa84","sha256:965f9bf3bccf9c13e7a017b80e71549327b9e7883a32e5cfcc816d6c1c67ffd5"],"state_sha256":"a0ffd164a1fdcfce3311a94b8dae9654e2f5def1a1d50109b17b01ebfc193d08"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H0qwcoQe+linxz7siLb+/Vu5FDSsGQWXtplvF1xat0gqPZn/QU4U5TOjwHcmBgiA3htt5BbO5vnml3ARwMwQDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:38:50.243899Z","bundle_sha256":"3b105d7e1e5114936d89a6a427264cb459ac958554307b2fa03010d944599e61"}}