{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FNTIHQFI3PC5KEJJYUHJWVQHVH","short_pith_number":"pith:FNTIHQFI","canonical_record":{"source":{"id":"2308.12477","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-24T00:24:42Z","cross_cats_sorted":["cs.CV","econ.GN","q-fin.EC"],"title_canon_sha256":"8dc962dc3eb182260631691c2063c22122438dc2eef9808dee69cd445c1e5cf9","abstract_canon_sha256":"cfa96c8f405d02fb9adf9901409bef503e2571a67b712b732d0fbf0dabc16c24"},"schema_version":"1.0"},"canonical_sha256":"2b6683c0a8dbc5d51129c50e9b5607a9cd0a8792f204d293229c1162cfe2702b","source":{"kind":"arxiv","id":"2308.12477","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12477","created_at":"2026-07-05T06:44:13Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12477v1","created_at":"2026-07-05T06:44:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12477","created_at":"2026-07-05T06:44:13Z"},{"alias_kind":"pith_short_12","alias_value":"FNTIHQFI3PC5","created_at":"2026-07-05T06:44:13Z"},{"alias_kind":"pith_short_16","alias_value":"FNTIHQFI3PC5KEJJ","created_at":"2026-07-05T06:44:13Z"},{"alias_kind":"pith_short_8","alias_value":"FNTIHQFI","created_at":"2026-07-05T06:44:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FNTIHQFI3PC5KEJJYUHJWVQHVH","target":"record","payload":{"canonical_record":{"source":{"id":"2308.12477","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-24T00:24:42Z","cross_cats_sorted":["cs.CV","econ.GN","q-fin.EC"],"title_canon_sha256":"8dc962dc3eb182260631691c2063c22122438dc2eef9808dee69cd445c1e5cf9","abstract_canon_sha256":"cfa96c8f405d02fb9adf9901409bef503e2571a67b712b732d0fbf0dabc16c24"},"schema_version":"1.0"},"canonical_sha256":"2b6683c0a8dbc5d51129c50e9b5607a9cd0a8792f204d293229c1162cfe2702b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:13.283566Z","signature_b64":"t8QC+3tKzmhnUOemFaxha2JQ3WjfToSeTZyS/ctp+fOBsdE5SsR+gCvEX0BPX3ghQ/M37VcUxBB0BNMnSF00Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b6683c0a8dbc5d51129c50e9b5607a9cd0a8792f204d293229c1162cfe2702b","last_reissued_at":"2026-07-05T06:44:13.283065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:13.283065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.12477","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":"2026-07-05T06:44:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2KztP+W7B5qyTs5Io+YX1Pe08Ns7SDD32t5SWLh4yP6RViRvMuUxkiHMHZ00+QiP/H1Md0/ivhS1vsD0LeWSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T11:47:32.130098Z"},"content_sha256":"7ffc70376890b57cb7ee1bb7bd9a70fa5982440af547a916910112f2d591b7f7","schema_version":"1.0","event_id":"sha256:7ffc70376890b57cb7ee1bb7bd9a70fa5982440af547a916910112f2d591b7f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FNTIHQFI3PC5KEJJYUHJWVQHVH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","econ.GN","q-fin.EC"],"primary_cat":"cs.CL","authors_text":"Abhishek Arora, Emily Silcock, Jacob Carlson, Leander Heldring, Luca D'Amico-Wong, Melissa Dell, Pablo Querubin, Quan Le, Tom Bryan, Zejiang Shen","submitted_at":"2023-08-24T00:24:42Z","abstract_excerpt":"Existing full text datasets of U.S. public domain newspapers do not recognize the often complex layouts of newspaper scans, and as a result the digitized content scrambles texts from articles, headlines, captions, advertisements, and other layout regions. OCR quality can also be low. This study develops a novel, deep learning pipeline for extracting full article texts from newspaper images and applies it to the nearly 20 million scans in Library of Congress's public domain Chronicling America collection. The pipeline includes layout detection, legibility classification, custom OCR, and associa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12477","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/2308.12477/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":"2026-07-05T06:44:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ti1cQfTkF44TTDMf4YJtI3E93QC0wm4zE9QOJzk7yDCbdupAXn9ZFmIwyshqigwKtOXApzwy4Hok/q8ERsvxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T11:47:32.130431Z"},"content_sha256":"265fa3b7ebe0f52d3d8069e524344650153b5f5e6ca2bd22e11857059a7ddac3","schema_version":"1.0","event_id":"sha256:265fa3b7ebe0f52d3d8069e524344650153b5f5e6ca2bd22e11857059a7ddac3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FNTIHQFI3PC5KEJJYUHJWVQHVH/bundle.json","state_url":"https://pith.science/pith/FNTIHQFI3PC5KEJJYUHJWVQHVH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FNTIHQFI3PC5KEJJYUHJWVQHVH/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":"2026-08-23T11:47:32Z","links":{"resolver":"https://pith.science/pith/FNTIHQFI3PC5KEJJYUHJWVQHVH","bundle":"https://pith.science/pith/FNTIHQFI3PC5KEJJYUHJWVQHVH/bundle.json","state":"https://pith.science/pith/FNTIHQFI3PC5KEJJYUHJWVQHVH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FNTIHQFI3PC5KEJJYUHJWVQHVH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FNTIHQFI3PC5KEJJYUHJWVQHVH","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":"cfa96c8f405d02fb9adf9901409bef503e2571a67b712b732d0fbf0dabc16c24","cross_cats_sorted":["cs.CV","econ.GN","q-fin.EC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-24T00:24:42Z","title_canon_sha256":"8dc962dc3eb182260631691c2063c22122438dc2eef9808dee69cd445c1e5cf9"},"schema_version":"1.0","source":{"id":"2308.12477","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12477","created_at":"2026-07-05T06:44:13Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12477v1","created_at":"2026-07-05T06:44:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12477","created_at":"2026-07-05T06:44:13Z"},{"alias_kind":"pith_short_12","alias_value":"FNTIHQFI3PC5","created_at":"2026-07-05T06:44:13Z"},{"alias_kind":"pith_short_16","alias_value":"FNTIHQFI3PC5KEJJ","created_at":"2026-07-05T06:44:13Z"},{"alias_kind":"pith_short_8","alias_value":"FNTIHQFI","created_at":"2026-07-05T06:44:13Z"}],"graph_snapshots":[{"event_id":"sha256:265fa3b7ebe0f52d3d8069e524344650153b5f5e6ca2bd22e11857059a7ddac3","target":"graph","created_at":"2026-07-05T06:44:13Z","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/2308.12477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing full text datasets of U.S. public domain newspapers do not recognize the often complex layouts of newspaper scans, and as a result the digitized content scrambles texts from articles, headlines, captions, advertisements, and other layout regions. OCR quality can also be low. This study develops a novel, deep learning pipeline for extracting full article texts from newspaper images and applies it to the nearly 20 million scans in Library of Congress's public domain Chronicling America collection. The pipeline includes layout detection, legibility classification, custom OCR, and associa","authors_text":"Abhishek Arora, Emily Silcock, Jacob Carlson, Leander Heldring, Luca D'Amico-Wong, Melissa Dell, Pablo Querubin, Quan Le, Tom Bryan, Zejiang Shen","cross_cats":["cs.CV","econ.GN","q-fin.EC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-24T00:24:42Z","title":"American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12477","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":"sha256:7ffc70376890b57cb7ee1bb7bd9a70fa5982440af547a916910112f2d591b7f7","target":"record","created_at":"2026-07-05T06:44:13Z","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":"cfa96c8f405d02fb9adf9901409bef503e2571a67b712b732d0fbf0dabc16c24","cross_cats_sorted":["cs.CV","econ.GN","q-fin.EC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-24T00:24:42Z","title_canon_sha256":"8dc962dc3eb182260631691c2063c22122438dc2eef9808dee69cd445c1e5cf9"},"schema_version":"1.0","source":{"id":"2308.12477","kind":"arxiv","version":1}},"canonical_sha256":"2b6683c0a8dbc5d51129c50e9b5607a9cd0a8792f204d293229c1162cfe2702b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b6683c0a8dbc5d51129c50e9b5607a9cd0a8792f204d293229c1162cfe2702b","first_computed_at":"2026-07-05T06:44:13.283065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:44:13.283065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t8QC+3tKzmhnUOemFaxha2JQ3WjfToSeTZyS/ctp+fOBsdE5SsR+gCvEX0BPX3ghQ/M37VcUxBB0BNMnSF00Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:44:13.283566Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.12477","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ffc70376890b57cb7ee1bb7bd9a70fa5982440af547a916910112f2d591b7f7","sha256:265fa3b7ebe0f52d3d8069e524344650153b5f5e6ca2bd22e11857059a7ddac3"],"state_sha256":"6f6fbf6c3c616bc8b0566d874be3570d33edc223013baf458fb878046a975fff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZdrD4LY9kDNQCqZR98sy3yxS1hClpSTfXnp1FGJt2PVccDJKbV5HMl8L5mVK9AndLZKesIZHx0AGIParqI4NDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T11:47:32.134127Z","bundle_sha256":"fc127ce0216ba6f29208a1330cc3e9837a25ca679d8105375253b828fce3e3ba"}}