{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VGSTEGP4OTFPROW2GK2L4OUY6B","short_pith_number":"pith:VGSTEGP4","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"},"canonical_sha256":"a9a53219fc74caf8bada32b4be3a98f07ef500879e12371c87c1c026153ce563","source":{"kind":"arxiv","id":"2104.09653","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.09653","created_at":"2026-07-05T02:33:35Z"},{"alias_kind":"arxiv_version","alias_value":"2104.09653v1","created_at":"2026-07-05T02:33:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09653","created_at":"2026-07-05T02:33:35Z"},{"alias_kind":"pith_short_12","alias_value":"VGSTEGP4OTFP","created_at":"2026-07-05T02:33:35Z"},{"alias_kind":"pith_short_16","alias_value":"VGSTEGP4OTFPROW2","created_at":"2026-07-05T02:33:35Z"},{"alias_kind":"pith_short_8","alias_value":"VGSTEGP4","created_at":"2026-07-05T02:33:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VGSTEGP4OTFPROW2GK2L4OUY6B","target":"record","payload":{"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"},"canonical_sha256":"a9a53219fc74caf8bada32b4be3a98f07ef500879e12371c87c1c026153ce563","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"},"source_kind":"arxiv","source_id":"2104.09653","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":"2026-07-05T02:33:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x/z+pQGqy8mone6bENboSaGHe8pZiDRQLAPgmTrKfXJWJFs3NoMCro+hJ8p9IajJZQNlD4zHg/TNfKfIY/dtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:02:07.824580Z"},"content_sha256":"11098d1c461bd1425ac2fdad4f6d088f4e3840560d1f10b9ee3a167c4550bb95","schema_version":"1.0","event_id":"sha256:11098d1c461bd1425ac2fdad4f6d088f4e3840560d1f10b9ee3a167c4550bb95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VGSTEGP4OTFPROW2GK2L4OUY6B","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:33:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MzpYNtgQeALz0SYHrgSJDv5aSNCtEWgUqUzpFZF/6wEpYuvxOlAyQUnQV0BCXEFOTSZcLto2x4IwJwB/8n2VDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:02:07.826439Z"},"content_sha256":"3f6138e08e5caa72903cc8b64844a744a82447dca16a634e7568d565b5b11b58","schema_version":"1.0","event_id":"sha256:3f6138e08e5caa72903cc8b64844a744a82447dca16a634e7568d565b5b11b58"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VGSTEGP4OTFPROW2GK2L4OUY6B/bundle.json","state_url":"https://pith.science/pith/VGSTEGP4OTFPROW2GK2L4OUY6B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VGSTEGP4OTFPROW2GK2L4OUY6B/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":"2026-08-05T14:02:07Z","links":{"resolver":"https://pith.science/pith/VGSTEGP4OTFPROW2GK2L4OUY6B","bundle":"https://pith.science/pith/VGSTEGP4OTFPROW2GK2L4OUY6B/bundle.json","state":"https://pith.science/pith/VGSTEGP4OTFPROW2GK2L4OUY6B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VGSTEGP4OTFPROW2GK2L4OUY6B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VGSTEGP4OTFPROW2GK2L4OUY6B","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":"aee2f6f2949e88e9ee65609f9b6bc6d2fa579793c9ab0d765cb564accb8159aa","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-19T21:48:15Z","title_canon_sha256":"060bb0b22650b846bda50e7385ab076d570cc71bbe337112e789b3bd464a2bc1"},"schema_version":"1.0","source":{"id":"2104.09653","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.09653","created_at":"2026-07-05T02:33:35Z"},{"alias_kind":"arxiv_version","alias_value":"2104.09653v1","created_at":"2026-07-05T02:33:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09653","created_at":"2026-07-05T02:33:35Z"},{"alias_kind":"pith_short_12","alias_value":"VGSTEGP4OTFP","created_at":"2026-07-05T02:33:35Z"},{"alias_kind":"pith_short_16","alias_value":"VGSTEGP4OTFPROW2","created_at":"2026-07-05T02:33:35Z"},{"alias_kind":"pith_short_8","alias_value":"VGSTEGP4","created_at":"2026-07-05T02:33:35Z"}],"graph_snapshots":[{"event_id":"sha256:3f6138e08e5caa72903cc8b64844a744a82447dca16a634e7568d565b5b11b58","target":"graph","created_at":"2026-07-05T02:33:35Z","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/2104.09653/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexander Spangher, Emilio Ferrara, Jonathan May, Nanyun Peng","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-19T21:48:15Z","title":"Modeling \"Newsworthiness\" for Lead-Generation Across Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09653","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":"sha256:11098d1c461bd1425ac2fdad4f6d088f4e3840560d1f10b9ee3a167c4550bb95","target":"record","created_at":"2026-07-05T02:33:35Z","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":"aee2f6f2949e88e9ee65609f9b6bc6d2fa579793c9ab0d765cb564accb8159aa","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-19T21:48:15Z","title_canon_sha256":"060bb0b22650b846bda50e7385ab076d570cc71bbe337112e789b3bd464a2bc1"},"schema_version":"1.0","source":{"id":"2104.09653","kind":"arxiv","version":1}},"canonical_sha256":"a9a53219fc74caf8bada32b4be3a98f07ef500879e12371c87c1c026153ce563","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9a53219fc74caf8bada32b4be3a98f07ef500879e12371c87c1c026153ce563","first_computed_at":"2026-07-05T02:33:35.689360Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:33:35.689360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NZKXYkhX9eActk6ZBWvJdj6c5el62AKN21dRQZFaml0+5KMGhC8n/YW4nU2dNwM7evcxobsUfhHZD3RyrVLMDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:33:35.689837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.09653","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11098d1c461bd1425ac2fdad4f6d088f4e3840560d1f10b9ee3a167c4550bb95","sha256:3f6138e08e5caa72903cc8b64844a744a82447dca16a634e7568d565b5b11b58"],"state_sha256":"96e986584cd98287b435dfea2460678522ffa9328f1e60466fffec152f203e32"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VMfDuGnDXx/rN5MPX3AZrvus/26mPGaBuHsnjnbD8j/V86JGbnYH5KmZSzbkCr56pxJWWV4BYDLY9O3koGzjCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T14:02:07.841891Z","bundle_sha256":"f147f509979fb44186cf6b9b340a9a2744cbeecd59cbe05794acf0216997625f"}}