{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F6KUHHTLE5AGLROOTCGFBAON4A","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":"7af05e45b64f87c916da359f5ad9c8966dd34dcbe5c9c27edf0b8b0aa75ffd20","cross_cats_sorted":["econ.GN","q-fin.EC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T18:50:57Z","title_canon_sha256":"02d86908aaa3732f07626e8dcf802d151f799c2aab9ecaa9aafafff4e5031369"},"schema_version":"1.0","source":{"id":"2406.15593","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15593","created_at":"2026-07-05T09:52:12Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15593v2","created_at":"2026-07-05T09:52:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15593","created_at":"2026-07-05T09:52:12Z"},{"alias_kind":"pith_short_12","alias_value":"F6KUHHTLE5AG","created_at":"2026-07-05T09:52:12Z"},{"alias_kind":"pith_short_16","alias_value":"F6KUHHTLE5AGLROO","created_at":"2026-07-05T09:52:12Z"},{"alias_kind":"pith_short_8","alias_value":"F6KUHHTL","created_at":"2026-07-05T09:52:12Z"}],"graph_snapshots":[{"event_id":"sha256:794ff169363d709353c59bd09c4df0bfd530494bf679acb129ce800f8d26fa53","target":"graph","created_at":"2026-07-05T09:52:12Z","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/2406.15593/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Social scientists and the general public often analyze contemporary events by drawing parallels with the past, a process complicated by the vast, noisy, and unstructured nature of historical texts. For example, hundreds of millions of page scans from historical newspapers have been noisily transcribed. Traditional sparse methods for searching for relevant material in these vast corpora, e.g., with keywords, can be brittle given complex vocabularies and OCR noise. This study introduces News Deja Vu, a novel semantic search tool that leverages transformer large language models and a bi-encoder a","authors_text":"Abhishek Arora, Brevin Franklin, Emily Silcock, Melissa Dell, Tom Bryan","cross_cats":["econ.GN","q-fin.EC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T18:50:57Z","title":"News Deja Vu: Connecting Past and Present with Semantic Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15593","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":"sha256:5d197607e18aa7dae362b2203e1b0a2405cd901e3d456020a0f42a70b0abc5fe","target":"record","created_at":"2026-07-05T09:52:12Z","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":"7af05e45b64f87c916da359f5ad9c8966dd34dcbe5c9c27edf0b8b0aa75ffd20","cross_cats_sorted":["econ.GN","q-fin.EC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T18:50:57Z","title_canon_sha256":"02d86908aaa3732f07626e8dcf802d151f799c2aab9ecaa9aafafff4e5031369"},"schema_version":"1.0","source":{"id":"2406.15593","kind":"arxiv","version":2}},"canonical_sha256":"2f95439e6b274065c5ce988c5081cde01ed50823104b5bb4e7861729f56a80db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f95439e6b274065c5ce988c5081cde01ed50823104b5bb4e7861729f56a80db","first_computed_at":"2026-07-05T09:52:12.978265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:12.978265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ikJB3I8fO11j8RzGelpzeRGMzFbNz2wT+4YUjcmz8VscIlfkfwc47kOHaWo7ppCuUAkQKrCtl+QmOGQu+fzPBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:12.978746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15593","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d197607e18aa7dae362b2203e1b0a2405cd901e3d456020a0f42a70b0abc5fe","sha256:794ff169363d709353c59bd09c4df0bfd530494bf679acb129ce800f8d26fa53"],"state_sha256":"bdf4eb8ba06ee3a41fc9310054ef5da926052eeceb86275fbd80139bbe39692c"}