{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VGSTEGP4OTFPROW2GK2L4OUY6B","short_pith_number":"pith:VGSTEGP4","schema_version":"1.0","canonical_sha256":"a9a53219fc74caf8bada32b4be3a98f07ef500879e12371c87c1c026153ce563","source":{"kind":"arxiv","id":"2104.09653","version":1},"attestation_state":"computed","paper":{"title":"Modeling \"Newsworthiness\" for Lead-Generation Across Corpora","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Alexander Spangher, Emilio Ferrara, Jonathan May, Nanyun Peng","submitted_at":"2021-04-19T21:48:15Z","abstract_excerpt":"Journalists obtain \"leads\", or story ideas, by reading large corpora of government records: court cases, proposed bills, etc. However, only a small percentage of such records are interesting documents. We propose a model of \"newsworthiness\" aimed at surfacing interesting documents. We train models on automatically labeled corpora -- published newspaper articles -- to predict whether each article was a front-page article (i.e., \\textbf{newsworthy}) or not (i.e., \\textbf{less newsworthy}). We transfer these models to unlabeled corpora -- court cases, bills, city-council meeting minutes -- to ran"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2104.09653","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-19T21:48:15Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"060bb0b22650b846bda50e7385ab076d570cc71bbe337112e789b3bd464a2bc1","abstract_canon_sha256":"aee2f6f2949e88e9ee65609f9b6bc6d2fa579793c9ab0d765cb564accb8159aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:35.689837Z","signature_b64":"NZKXYkhX9eActk6ZBWvJdj6c5el62AKN21dRQZFaml0+5KMGhC8n/YW4nU2dNwM7evcxobsUfhHZD3RyrVLMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9a53219fc74caf8bada32b4be3a98f07ef500879e12371c87c1c026153ce563","last_reissued_at":"2026-07-05T02:33:35.689360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:35.689360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling \"Newsworthiness\" for Lead-Generation Across Corpora","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Alexander Spangher, Emilio Ferrara, Jonathan May, Nanyun Peng","submitted_at":"2021-04-19T21:48:15Z","abstract_excerpt":"Journalists obtain \"leads\", or story ideas, by reading large corpora of government records: court cases, proposed bills, etc. However, only a small percentage of such records are interesting documents. We propose a model of \"newsworthiness\" aimed at surfacing interesting documents. We train models on automatically labeled corpora -- published newspaper articles -- to predict whether each article was a front-page article (i.e., \\textbf{newsworthy}) or not (i.e., \\textbf{less newsworthy}). We transfer these models to unlabeled corpora -- court cases, bills, city-council meeting minutes -- to ran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09653","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/2104.09653/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2104.09653","created_at":"2026-07-05T02:33:35.689414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.09653v1","created_at":"2026-07-05T02:33:35.689414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09653","created_at":"2026-07-05T02:33:35.689414+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGSTEGP4OTFP","created_at":"2026-07-05T02:33:35.689414+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGSTEGP4OTFPROW2","created_at":"2026-07-05T02:33:35.689414+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGSTEGP4","created_at":"2026-07-05T02:33:35.689414+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGSTEGP4OTFPROW2GK2L4OUY6B","json":"https://pith.science/pith/VGSTEGP4OTFPROW2GK2L4OUY6B.json","graph_json":"https://pith.science/api/pith-number/VGSTEGP4OTFPROW2GK2L4OUY6B/graph.json","events_json":"https://pith.science/api/pith-number/VGSTEGP4OTFPROW2GK2L4OUY6B/events.json","paper":"https://pith.science/paper/VGSTEGP4"},"agent_actions":{"view_html":"https://pith.science/pith/VGSTEGP4OTFPROW2GK2L4OUY6B","download_json":"https://pith.science/pith/VGSTEGP4OTFPROW2GK2L4OUY6B.json","view_paper":"https://pith.science/paper/VGSTEGP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.09653&json=true","fetch_graph":"https://pith.science/api/pith-number/VGSTEGP4OTFPROW2GK2L4OUY6B/graph.json","fetch_events":"https://pith.science/api/pith-number/VGSTEGP4OTFPROW2GK2L4OUY6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGSTEGP4OTFPROW2GK2L4OUY6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGSTEGP4OTFPROW2GK2L4OUY6B/action/storage_attestation","attest_author":"https://pith.science/pith/VGSTEGP4OTFPROW2GK2L4OUY6B/action/author_attestation","sign_citation":"https://pith.science/pith/VGSTEGP4OTFPROW2GK2L4OUY6B/action/citation_signature","submit_replication":"https://pith.science/pith/VGSTEGP4OTFPROW2GK2L4OUY6B/action/replication_record"}},"created_at":"2026-07-05T02:33:35.689414+00:00","updated_at":"2026-07-05T02:33:35.689414+00:00"}