{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XX3NXC3X3ZXMO3UXGEEFDVLPUO","short_pith_number":"pith:XX3NXC3X","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"},"canonical_sha256":"bdf6db8b77de6ec76e97310851d56fa3b94d7bb710ea033e888418ed709f68a8","source":{"kind":"arxiv","id":"2507.00828","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00828","created_at":"2026-07-05T11:30:15Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00828v1","created_at":"2026-07-05T11:30:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00828","created_at":"2026-07-05T11:30:15Z"},{"alias_kind":"pith_short_12","alias_value":"XX3NXC3X3ZXM","created_at":"2026-07-05T11:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"XX3NXC3X3ZXMO3UX","created_at":"2026-07-05T11:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"XX3NXC3X","created_at":"2026-07-05T11:30:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XX3NXC3X3ZXMO3UXGEEFDVLPUO","target":"record","payload":{"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"},"canonical_sha256":"bdf6db8b77de6ec76e97310851d56fa3b94d7bb710ea033e888418ed709f68a8","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"},"source_kind":"arxiv","source_id":"2507.00828","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":"2026-07-05T11:30:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wqs+kDJHaM6//YldWCY9M4+v+2kQ3x3/rLPtx8Pxm2xFuJXc2gAIMudImhZk/mFpHnIAfiih+8S0A5lsoSSsBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:54:07.403061Z"},"content_sha256":"e6aba6ef5d98c5cafd658dff48c76e8864f1409a1380194d8965b8fbe5e0e9ae","schema_version":"1.0","event_id":"sha256:e6aba6ef5d98c5cafd658dff48c76e8864f1409a1380194d8965b8fbe5e0e9ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XX3NXC3X3ZXMO3UXGEEFDVLPUO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:30:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fNWsNC/aF3dO8KrXdE204SeJS8RLHhnvnV0h7IcTx1yYb3TYrcU3l/kEK4PEYulNNWlNlgFySt18rFdlDc5VCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:54:07.403555Z"},"content_sha256":"c9ea66b5674b96b20d32bc4f1235350d8e6620696712c676d9be2e30538ccba7","schema_version":"1.0","event_id":"sha256:c9ea66b5674b96b20d32bc4f1235350d8e6620696712c676d9be2e30538ccba7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XX3NXC3X3ZXMO3UXGEEFDVLPUO/bundle.json","state_url":"https://pith.science/pith/XX3NXC3X3ZXMO3UXGEEFDVLPUO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XX3NXC3X3ZXMO3UXGEEFDVLPUO/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":"2026-08-04T17:54:07Z","links":{"resolver":"https://pith.science/pith/XX3NXC3X3ZXMO3UXGEEFDVLPUO","bundle":"https://pith.science/pith/XX3NXC3X3ZXMO3UXGEEFDVLPUO/bundle.json","state":"https://pith.science/pith/XX3NXC3X3ZXMO3UXGEEFDVLPUO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XX3NXC3X3ZXMO3UXGEEFDVLPUO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XX3NXC3X3ZXMO3UXGEEFDVLPUO","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":"7273b16da983c8eec818692b7d1562a3a27e40c301cb585d94175f421e22637f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T15:00:55Z","title_canon_sha256":"55036543efd227d0692e708798da457101d5a8cd8a311849f4aa1eed57c90431"},"schema_version":"1.0","source":{"id":"2507.00828","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00828","created_at":"2026-07-05T11:30:15Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00828v1","created_at":"2026-07-05T11:30:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00828","created_at":"2026-07-05T11:30:15Z"},{"alias_kind":"pith_short_12","alias_value":"XX3NXC3X3ZXM","created_at":"2026-07-05T11:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"XX3NXC3X3ZXMO3UX","created_at":"2026-07-05T11:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"XX3NXC3X","created_at":"2026-07-05T11:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:c9ea66b5674b96b20d32bc4f1235350d8e6620696712c676d9be2e30538ccba7","target":"graph","created_at":"2026-07-05T11:30:15Z","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/2507.00828/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexander Hoyle, Jordan Boyd-Graber, Lorena Calvo-Bartolom\\'e, Philip Resnik","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T15:00:55Z","title":"ProxAnn: Use-Oriented Evaluations of Topic Models and Document Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00828","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:e6aba6ef5d98c5cafd658dff48c76e8864f1409a1380194d8965b8fbe5e0e9ae","target":"record","created_at":"2026-07-05T11:30:15Z","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":"7273b16da983c8eec818692b7d1562a3a27e40c301cb585d94175f421e22637f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T15:00:55Z","title_canon_sha256":"55036543efd227d0692e708798da457101d5a8cd8a311849f4aa1eed57c90431"},"schema_version":"1.0","source":{"id":"2507.00828","kind":"arxiv","version":1}},"canonical_sha256":"bdf6db8b77de6ec76e97310851d56fa3b94d7bb710ea033e888418ed709f68a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bdf6db8b77de6ec76e97310851d56fa3b94d7bb710ea033e888418ed709f68a8","first_computed_at":"2026-07-05T11:30:15.259951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:15.259951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vz2MLsafXdpozXUPZc42xIIn6U0opG2CRvEx4LJ3OZ0AMerIYPbkO8rLyHQRN6aR4AZITPa4WqM6EW9OitGiBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:15.262133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00828","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6aba6ef5d98c5cafd658dff48c76e8864f1409a1380194d8965b8fbe5e0e9ae","sha256:c9ea66b5674b96b20d32bc4f1235350d8e6620696712c676d9be2e30538ccba7"],"state_sha256":"cbba69c344785ef24edda98ab38a0ac35a41e31d2e387a9b19e4e61cdcf93c1a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gEqaYZmTYtsVxGcefYfbdZsLiLlmRWpYDv0LdqOFHwi1ranQz1YqGcoCabB2UwBxGl5Rv++GZHwy41711YmRCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:54:07.408610Z","bundle_sha256":"a08f93698790c5bc89ba872b0526ed43db211a6f8ec07ff8f2fe0454dc0e94e4"}}