{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:424OQJZREJFB6BIS6DVBQA4A5O","short_pith_number":"pith:424OQJZR","schema_version":"1.0","canonical_sha256":"e6b8e82731224a1f0512f0ea180380ebad0a6314c7dfab24718640afd7df21cc","source":{"kind":"arxiv","id":"2405.00982","version":2},"attestation_state":"computed","paper":{"title":"On the Evaluation of Machine-Generated Reports","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Dawn Lawrie, Douglas W. Oard, Efsun Kayi, Eugene Yang, Ian Soboroff, James Mayfield, Kate Sanders, Luca Soldaini, Marc Mason, Noah Hibbler, Orion Weller, Paul McNamee, Sean MacAvaney","submitted_at":"2024-05-02T03:35:23Z","abstract_excerpt":"Large Language Models (LLMs) have enabled new ways to satisfy information needs. Although great strides have been made in applying them to settings like document ranking and short-form text generation, they still struggle to compose complete, accurate, and verifiable long-form reports. Reports with these qualities are necessary to satisfy the complex, nuanced, or multi-faceted information needs of users. In this perspective paper, we draw together opinions from industry and academia, and from a variety of related research areas, to present our vision for automatic report generation, and -- cri"},"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":"2405.00982","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-02T03:35:23Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"f64ffa752df1ccf48c1a7d5b47066459680ff38209cfd6d6642127c2bcdf445c","abstract_canon_sha256":"2bb40b0af97e5e02c6b678d12075795316f9c84bcb020c304eeee76da6b46b0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:32.758231Z","signature_b64":"rt72xQ9S7NSm+BfkaGJvptL89NvO//rTX2T7nsXjQ4bfSKNS7VBNZmqVnlkubuxD58rh1CYkvZq+SOMOwWNMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6b8e82731224a1f0512f0ea180380ebad0a6314c7dfab24718640afd7df21cc","last_reissued_at":"2026-07-05T08:17:32.757736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:32.757736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Evaluation of Machine-Generated Reports","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Dawn Lawrie, Douglas W. Oard, Efsun Kayi, Eugene Yang, Ian Soboroff, James Mayfield, Kate Sanders, Luca Soldaini, Marc Mason, Noah Hibbler, Orion Weller, Paul McNamee, Sean MacAvaney","submitted_at":"2024-05-02T03:35:23Z","abstract_excerpt":"Large Language Models (LLMs) have enabled new ways to satisfy information needs. Although great strides have been made in applying them to settings like document ranking and short-form text generation, they still struggle to compose complete, accurate, and verifiable long-form reports. Reports with these qualities are necessary to satisfy the complex, nuanced, or multi-faceted information needs of users. In this perspective paper, we draw together opinions from industry and academia, and from a variety of related research areas, to present our vision for automatic report generation, and -- cri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00982","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/2405.00982/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":"2405.00982","created_at":"2026-07-05T08:17:32.757788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.00982v2","created_at":"2026-07-05T08:17:32.757788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00982","created_at":"2026-07-05T08:17:32.757788+00:00"},{"alias_kind":"pith_short_12","alias_value":"424OQJZREJFB","created_at":"2026-07-05T08:17:32.757788+00:00"},{"alias_kind":"pith_short_16","alias_value":"424OQJZREJFB6BIS","created_at":"2026-07-05T08:17:32.757788+00:00"},{"alias_kind":"pith_short_8","alias_value":"424OQJZR","created_at":"2026-07-05T08:17:32.757788+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/424OQJZREJFB6BIS6DVBQA4A5O","json":"https://pith.science/pith/424OQJZREJFB6BIS6DVBQA4A5O.json","graph_json":"https://pith.science/api/pith-number/424OQJZREJFB6BIS6DVBQA4A5O/graph.json","events_json":"https://pith.science/api/pith-number/424OQJZREJFB6BIS6DVBQA4A5O/events.json","paper":"https://pith.science/paper/424OQJZR"},"agent_actions":{"view_html":"https://pith.science/pith/424OQJZREJFB6BIS6DVBQA4A5O","download_json":"https://pith.science/pith/424OQJZREJFB6BIS6DVBQA4A5O.json","view_paper":"https://pith.science/paper/424OQJZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.00982&json=true","fetch_graph":"https://pith.science/api/pith-number/424OQJZREJFB6BIS6DVBQA4A5O/graph.json","fetch_events":"https://pith.science/api/pith-number/424OQJZREJFB6BIS6DVBQA4A5O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/424OQJZREJFB6BIS6DVBQA4A5O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/424OQJZREJFB6BIS6DVBQA4A5O/action/storage_attestation","attest_author":"https://pith.science/pith/424OQJZREJFB6BIS6DVBQA4A5O/action/author_attestation","sign_citation":"https://pith.science/pith/424OQJZREJFB6BIS6DVBQA4A5O/action/citation_signature","submit_replication":"https://pith.science/pith/424OQJZREJFB6BIS6DVBQA4A5O/action/replication_record"}},"created_at":"2026-07-05T08:17:32.757788+00:00","updated_at":"2026-07-05T08:17:32.757788+00:00"}