{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XX3NXC3X3ZXMO3UXGEEFDVLPUO","short_pith_number":"pith:XX3NXC3X","schema_version":"1.0","canonical_sha256":"bdf6db8b77de6ec76e97310851d56fa3b94d7bb710ea033e888418ed709f68a8","source":{"kind":"arxiv","id":"2507.00828","version":1},"attestation_state":"computed","paper":{"title":"ProxAnn: Use-Oriented Evaluations of Topic Models and Document Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Hoyle, Jordan Boyd-Graber, Lorena Calvo-Bartolom\\'e, Philip Resnik","submitted_at":"2025-07-01T15:00:55Z","abstract_excerpt":"Topic model and document-clustering evaluations either use automated metrics that align poorly with human preferences or require expert labels that are intractable to scale. We design a scalable human evaluation protocol and a corresponding automated approximation that reflect practitioners' real-world usage of models. Annotators -- or an LLM-based proxy -- review text items assigned to a topic or cluster, infer a category for the group, then apply that category to other documents. Using this protocol, we collect extensive crowdworker annotations of outputs from a diverse set of topic models o"},"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":"2507.00828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T15:00:55Z","cross_cats_sorted":[],"title_canon_sha256":"55036543efd227d0692e708798da457101d5a8cd8a311849f4aa1eed57c90431","abstract_canon_sha256":"7273b16da983c8eec818692b7d1562a3a27e40c301cb585d94175f421e22637f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:15.262133Z","signature_b64":"Vz2MLsafXdpozXUPZc42xIIn6U0opG2CRvEx4LJ3OZ0AMerIYPbkO8rLyHQRN6aR4AZITPa4WqM6EW9OitGiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdf6db8b77de6ec76e97310851d56fa3b94d7bb710ea033e888418ed709f68a8","last_reissued_at":"2026-07-05T11:30:15.259951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:15.259951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProxAnn: Use-Oriented Evaluations of Topic Models and Document Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Hoyle, Jordan Boyd-Graber, Lorena Calvo-Bartolom\\'e, Philip Resnik","submitted_at":"2025-07-01T15:00:55Z","abstract_excerpt":"Topic model and document-clustering evaluations either use automated metrics that align poorly with human preferences or require expert labels that are intractable to scale. We design a scalable human evaluation protocol and a corresponding automated approximation that reflect practitioners' real-world usage of models. Annotators -- or an LLM-based proxy -- review text items assigned to a topic or cluster, infer a category for the group, then apply that category to other documents. Using this protocol, we collect extensive crowdworker annotations of outputs from a diverse set of topic models o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00828","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/2507.00828/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":"2507.00828","created_at":"2026-07-05T11:30:15.260012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00828v1","created_at":"2026-07-05T11:30:15.260012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00828","created_at":"2026-07-05T11:30:15.260012+00:00"},{"alias_kind":"pith_short_12","alias_value":"XX3NXC3X3ZXM","created_at":"2026-07-05T11:30:15.260012+00:00"},{"alias_kind":"pith_short_16","alias_value":"XX3NXC3X3ZXMO3UX","created_at":"2026-07-05T11:30:15.260012+00:00"},{"alias_kind":"pith_short_8","alias_value":"XX3NXC3X","created_at":"2026-07-05T11:30:15.260012+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/XX3NXC3X3ZXMO3UXGEEFDVLPUO","json":"https://pith.science/pith/XX3NXC3X3ZXMO3UXGEEFDVLPUO.json","graph_json":"https://pith.science/api/pith-number/XX3NXC3X3ZXMO3UXGEEFDVLPUO/graph.json","events_json":"https://pith.science/api/pith-number/XX3NXC3X3ZXMO3UXGEEFDVLPUO/events.json","paper":"https://pith.science/paper/XX3NXC3X"},"agent_actions":{"view_html":"https://pith.science/pith/XX3NXC3X3ZXMO3UXGEEFDVLPUO","download_json":"https://pith.science/pith/XX3NXC3X3ZXMO3UXGEEFDVLPUO.json","view_paper":"https://pith.science/paper/XX3NXC3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00828&json=true","fetch_graph":"https://pith.science/api/pith-number/XX3NXC3X3ZXMO3UXGEEFDVLPUO/graph.json","fetch_events":"https://pith.science/api/pith-number/XX3NXC3X3ZXMO3UXGEEFDVLPUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XX3NXC3X3ZXMO3UXGEEFDVLPUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XX3NXC3X3ZXMO3UXGEEFDVLPUO/action/storage_attestation","attest_author":"https://pith.science/pith/XX3NXC3X3ZXMO3UXGEEFDVLPUO/action/author_attestation","sign_citation":"https://pith.science/pith/XX3NXC3X3ZXMO3UXGEEFDVLPUO/action/citation_signature","submit_replication":"https://pith.science/pith/XX3NXC3X3ZXMO3UXGEEFDVLPUO/action/replication_record"}},"created_at":"2026-07-05T11:30:15.260012+00:00","updated_at":"2026-07-05T11:30:15.260012+00:00"}