{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YIFB5KQZ5POIKFTJ62SBNLPTNB","short_pith_number":"pith:YIFB5KQZ","schema_version":"1.0","canonical_sha256":"c20a1eaa19ebdc851669f6a416adf3684732763bd9dbb2517c93cc4801c9026f","source":{"kind":"arxiv","id":"2605.29765","version":1},"attestation_state":"computed","paper":{"title":"MMTM: Tri-Modal Topic Modeling for Long-Form Video via Similarity-Gated Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Mehler, Ali Abusaleh, Bhuvanesh Verma","submitted_at":"2026-05-28T11:12:30Z","abstract_excerpt":"We introduce MMTM, a modular pipeline for topic discovery in long-form video that integrates speech recognition, audio and visual embeddings, and BERTopic clustering through a deterministic similarity-gated fusion. Evaluated cross-lingually on German (Tagesschau) and English (NBC) broadcast news, joint tri-modal modeling substantially improves topic quality: noise drops from 0.27 to 0.06, transition rate from 0.70 to 0.21, and normalized entropy rises from 0.84 to 0.92, indicating more coherent and temporally stable topics. Cluster validity (Calinski-Harabasz) improves by 5-12X across embeddin"},"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":"2605.29765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T11:12:30Z","cross_cats_sorted":[],"title_canon_sha256":"9c87e77c5290dd8976698766e96efe0dc05101c2c989de2be3c892ed4c75b53a","abstract_canon_sha256":"a080be3e8689ce82400ee3e7abacaf31b7ea7364d3b88fdef0192950201d2cc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:25.531088Z","signature_b64":"coyzllrVsvLJR+ch09Z3KLgiTUCgqN40vbli5HCgbOEjZu+aj7HtOmsOJu/n2gRJ+8yLsZQOig+Dqdx6CdvzAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c20a1eaa19ebdc851669f6a416adf3684732763bd9dbb2517c93cc4801c9026f","last_reissued_at":"2026-05-29T02:05:25.530571Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:25.530571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMTM: Tri-Modal Topic Modeling for Long-Form Video via Similarity-Gated Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Mehler, Ali Abusaleh, Bhuvanesh Verma","submitted_at":"2026-05-28T11:12:30Z","abstract_excerpt":"We introduce MMTM, a modular pipeline for topic discovery in long-form video that integrates speech recognition, audio and visual embeddings, and BERTopic clustering through a deterministic similarity-gated fusion. Evaluated cross-lingually on German (Tagesschau) and English (NBC) broadcast news, joint tri-modal modeling substantially improves topic quality: noise drops from 0.27 to 0.06, transition rate from 0.70 to 0.21, and normalized entropy rises from 0.84 to 0.92, indicating more coherent and temporally stable topics. Cluster validity (Calinski-Harabasz) improves by 5-12X across embeddin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29765","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/2605.29765/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":"2605.29765","created_at":"2026-05-29T02:05:25.530630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29765v1","created_at":"2026-05-29T02:05:25.530630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29765","created_at":"2026-05-29T02:05:25.530630+00:00"},{"alias_kind":"pith_short_12","alias_value":"YIFB5KQZ5POI","created_at":"2026-05-29T02:05:25.530630+00:00"},{"alias_kind":"pith_short_16","alias_value":"YIFB5KQZ5POIKFTJ","created_at":"2026-05-29T02:05:25.530630+00:00"},{"alias_kind":"pith_short_8","alias_value":"YIFB5KQZ","created_at":"2026-05-29T02:05:25.530630+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/YIFB5KQZ5POIKFTJ62SBNLPTNB","json":"https://pith.science/pith/YIFB5KQZ5POIKFTJ62SBNLPTNB.json","graph_json":"https://pith.science/api/pith-number/YIFB5KQZ5POIKFTJ62SBNLPTNB/graph.json","events_json":"https://pith.science/api/pith-number/YIFB5KQZ5POIKFTJ62SBNLPTNB/events.json","paper":"https://pith.science/paper/YIFB5KQZ"},"agent_actions":{"view_html":"https://pith.science/pith/YIFB5KQZ5POIKFTJ62SBNLPTNB","download_json":"https://pith.science/pith/YIFB5KQZ5POIKFTJ62SBNLPTNB.json","view_paper":"https://pith.science/paper/YIFB5KQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29765&json=true","fetch_graph":"https://pith.science/api/pith-number/YIFB5KQZ5POIKFTJ62SBNLPTNB/graph.json","fetch_events":"https://pith.science/api/pith-number/YIFB5KQZ5POIKFTJ62SBNLPTNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YIFB5KQZ5POIKFTJ62SBNLPTNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YIFB5KQZ5POIKFTJ62SBNLPTNB/action/storage_attestation","attest_author":"https://pith.science/pith/YIFB5KQZ5POIKFTJ62SBNLPTNB/action/author_attestation","sign_citation":"https://pith.science/pith/YIFB5KQZ5POIKFTJ62SBNLPTNB/action/citation_signature","submit_replication":"https://pith.science/pith/YIFB5KQZ5POIKFTJ62SBNLPTNB/action/replication_record"}},"created_at":"2026-05-29T02:05:25.530630+00:00","updated_at":"2026-05-29T02:05:25.530630+00:00"}