{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X6DTTVPIMQDG6OSL2JTXWOKGZD","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":"9c084c3a567f0b04f62e728e8df68cc8b0b8fa4594864e428fa10b6326010602","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T01:29:46Z","title_canon_sha256":"80b5fc96bf9fbb675cc5e4a5ee03e55b472f450dd94540d0946b27e40ba74739"},"schema_version":"1.0","source":{"id":"2403.17308","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.17308","created_at":"2026-07-05T08:00:48Z"},{"alias_kind":"arxiv_version","alias_value":"2403.17308v1","created_at":"2026-07-05T08:00:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17308","created_at":"2026-07-05T08:00:48Z"},{"alias_kind":"pith_short_12","alias_value":"X6DTTVPIMQDG","created_at":"2026-07-05T08:00:48Z"},{"alias_kind":"pith_short_16","alias_value":"X6DTTVPIMQDG6OSL","created_at":"2026-07-05T08:00:48Z"},{"alias_kind":"pith_short_8","alias_value":"X6DTTVPI","created_at":"2026-07-05T08:00:48Z"}],"graph_snapshots":[{"event_id":"sha256:5e49bad89e7404d6e5a8cb6e3ca6ace08db7f0451adfe2373eff70bc21cc8c2d","target":"graph","created_at":"2026-07-05T08:00:48Z","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/2403.17308/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural topic models can successfully find coherent and diverse topics in textual data. However, they are limited in dealing with multimodal datasets (e.g., images and text). This paper presents the first systematic and comprehensive evaluation of multimodal topic modeling of documents containing both text and images. In the process, we propose two novel topic modeling solutions and two novel evaluation metrics. Overall, our evaluation on an unprecedented rich and diverse collection of datasets indicates that both of our models generate coherent and diverse topics. Nevertheless, the extent to w","authors_text":"Felipe Gonz\\'alez-Pizarro, Giuseppe Carenini","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T01:29:46Z","title":"Neural Multimodal Topic Modeling: A Comprehensive Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17308","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":"sha256:2b9ac0cc562ea9803f399332cf63479e6537d6921b5efd74ec05d1689bbf9379","target":"record","created_at":"2026-07-05T08:00:48Z","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":"9c084c3a567f0b04f62e728e8df68cc8b0b8fa4594864e428fa10b6326010602","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T01:29:46Z","title_canon_sha256":"80b5fc96bf9fbb675cc5e4a5ee03e55b472f450dd94540d0946b27e40ba74739"},"schema_version":"1.0","source":{"id":"2403.17308","kind":"arxiv","version":1}},"canonical_sha256":"bf8739d5e864066f3a4bd2677b3946c8dec740a17559f9043103c639b5e9069c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf8739d5e864066f3a4bd2677b3946c8dec740a17559f9043103c639b5e9069c","first_computed_at":"2026-07-05T08:00:48.713376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:48.713376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gvBU+x5RXm1H+Cnhz27SYFlzRop2ckncqE4Lnwgt97JLKwtyXGJ+DSky52LnGbSLo32avNS3M3Z9ZhpgtiAnBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:48.713843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.17308","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b9ac0cc562ea9803f399332cf63479e6537d6921b5efd74ec05d1689bbf9379","sha256:5e49bad89e7404d6e5a8cb6e3ca6ace08db7f0451adfe2373eff70bc21cc8c2d"],"state_sha256":"3a90f687787597e9fda0efd1ccf3ed2003dfd6ec7af87e2045fc70656ea22776"}