{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E3I7G66JVO7CBEVCCVSGAGZ3UX","short_pith_number":"pith:E3I7G66J","schema_version":"1.0","canonical_sha256":"26d1f37bc9abbe2092a21564601b3ba5c686d07c6016e55b8c1af899eb9e98d4","source":{"kind":"arxiv","id":"2509.17446","version":3},"attestation_state":"computed","paper":{"title":"MVCL-DAF++: Enhancing Multimodal Intent Recognition via Prototype-Aware Contrastive Alignment and Coarse-to-Fine Dynamic Attention Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Li, Haofeng Huang, Long Zhang, Yangfan He, Yaxin Xue, Yifei Han","submitted_at":"2025-09-22T07:38:53Z","abstract_excerpt":"Multimodal intent recognition (MMIR) suffers from weak semantic grounding and poor robustness under noisy or rare-class conditions. We propose MVCL-DAF++, which extends MVCL-DAF with two key modules: (1) Prototype-aware contrastive alignment, aligning instances to class-level prototypes to enhance semantic consistency; and (2) Coarse-to-fine attention fusion, integrating global modality summaries with token-level features for hierarchical cross-modal interaction. On MIntRec and MIntRec2.0, MVCL-DAF++ achieves new state-of-the-art results, improving rare-class recognition by +1.05\\% and +4.18\\%"},"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":"2509.17446","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-22T07:38:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4eca7d569224b394f67ee1a8f75ca5d419145246464f7c7bf0e3f9531b593c33","abstract_canon_sha256":"0630e082de408eebfa6a39b3ed579336c7acbfd222fe4a5de40fefad25222f8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:03:48.535231Z","signature_b64":"BQQ8RzcOLfFP0OXG9mbUIZF2u7MbeNKvgogkMXYV6XOMpE0z3oQzFy+BOno/rXIONLix0RyZsFjtzyhKISvQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26d1f37bc9abbe2092a21564601b3ba5c686d07c6016e55b8c1af899eb9e98d4","last_reissued_at":"2026-06-08T01:03:48.534146Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:03:48.534146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVCL-DAF++: Enhancing Multimodal Intent Recognition via Prototype-Aware Contrastive Alignment and Coarse-to-Fine Dynamic Attention Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Li, Haofeng Huang, Long Zhang, Yangfan He, Yaxin Xue, Yifei Han","submitted_at":"2025-09-22T07:38:53Z","abstract_excerpt":"Multimodal intent recognition (MMIR) suffers from weak semantic grounding and poor robustness under noisy or rare-class conditions. We propose MVCL-DAF++, which extends MVCL-DAF with two key modules: (1) Prototype-aware contrastive alignment, aligning instances to class-level prototypes to enhance semantic consistency; and (2) Coarse-to-fine attention fusion, integrating global modality summaries with token-level features for hierarchical cross-modal interaction. On MIntRec and MIntRec2.0, MVCL-DAF++ achieves new state-of-the-art results, improving rare-class recognition by +1.05\\% and +4.18\\%"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.17446","kind":"arxiv","version":3},"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/2509.17446/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":"2509.17446","created_at":"2026-06-08T01:03:48.534297+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.17446v3","created_at":"2026-06-08T01:03:48.534297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.17446","created_at":"2026-06-08T01:03:48.534297+00:00"},{"alias_kind":"pith_short_12","alias_value":"E3I7G66JVO7C","created_at":"2026-06-08T01:03:48.534297+00:00"},{"alias_kind":"pith_short_16","alias_value":"E3I7G66JVO7CBEVC","created_at":"2026-06-08T01:03:48.534297+00:00"},{"alias_kind":"pith_short_8","alias_value":"E3I7G66J","created_at":"2026-06-08T01:03:48.534297+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04054","citing_title":"Modality Agreement- and Conflict-Aware Prototype Hypergraph Learning for Multimodal Intent Understanding","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E3I7G66JVO7CBEVCCVSGAGZ3UX","json":"https://pith.science/pith/E3I7G66JVO7CBEVCCVSGAGZ3UX.json","graph_json":"https://pith.science/api/pith-number/E3I7G66JVO7CBEVCCVSGAGZ3UX/graph.json","events_json":"https://pith.science/api/pith-number/E3I7G66JVO7CBEVCCVSGAGZ3UX/events.json","paper":"https://pith.science/paper/E3I7G66J"},"agent_actions":{"view_html":"https://pith.science/pith/E3I7G66JVO7CBEVCCVSGAGZ3UX","download_json":"https://pith.science/pith/E3I7G66JVO7CBEVCCVSGAGZ3UX.json","view_paper":"https://pith.science/paper/E3I7G66J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.17446&json=true","fetch_graph":"https://pith.science/api/pith-number/E3I7G66JVO7CBEVCCVSGAGZ3UX/graph.json","fetch_events":"https://pith.science/api/pith-number/E3I7G66JVO7CBEVCCVSGAGZ3UX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E3I7G66JVO7CBEVCCVSGAGZ3UX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E3I7G66JVO7CBEVCCVSGAGZ3UX/action/storage_attestation","attest_author":"https://pith.science/pith/E3I7G66JVO7CBEVCCVSGAGZ3UX/action/author_attestation","sign_citation":"https://pith.science/pith/E3I7G66JVO7CBEVCCVSGAGZ3UX/action/citation_signature","submit_replication":"https://pith.science/pith/E3I7G66JVO7CBEVCCVSGAGZ3UX/action/replication_record"}},"created_at":"2026-06-08T01:03:48.534297+00:00","updated_at":"2026-06-08T01:03:48.534297+00:00"}