{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R5O3T43L32WZIBWEEB35TKHYBR","short_pith_number":"pith:R5O3T43L","schema_version":"1.0","canonical_sha256":"8f5db9f36bdead9406c42077d9a8f80c5c40550cba30238d1ec5412ea685eb9e","source":{"kind":"arxiv","id":"2405.18014","version":2},"attestation_state":"computed","paper":{"title":"Coupled Mamba: Enhanced Multi-modal Fusion with Coupled State Space Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hang Zhou, Junqing Yu, Wei Yang, Wenbing Li, Zikai Song","submitted_at":"2024-05-28T09:57:03Z","abstract_excerpt":"The essence of multi-modal fusion lies in exploiting the complementary information inherent in diverse modalities. However, prevalent fusion methods rely on traditional neural architectures and are inadequately equipped to capture the dynamics of interactions across modalities, particularly in presence of complex intra- and inter-modality correlations. Recent advancements in State Space Models (SSMs), notably exemplified by the Mamba model, have emerged as promising contenders. Particularly, its state evolving process implies stronger modality fusion paradigm, making multi-modal fusion on SSMs"},"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":"2405.18014","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-28T09:57:03Z","cross_cats_sorted":[],"title_canon_sha256":"cf0e502bb35132bf622961d6cb89fd1354faa10f99af3d9977078557719e5439","abstract_canon_sha256":"94e1a9d54e5b4a6cebdc00f53aa32d45ca28a37d810deddcc132344c9ec7a1c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:16.266141Z","signature_b64":"NPI/Zwk9MV13JN49/BR6nU1mlsOvvjFDUFJ7NYPD5UFiDCoGaJEoxKodh3BBzAJYB5VQl6+I2Ui5TJU+oyYoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f5db9f36bdead9406c42077d9a8f80c5c40550cba30238d1ec5412ea685eb9e","last_reissued_at":"2026-07-05T11:23:16.265610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:16.265610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coupled Mamba: Enhanced Multi-modal Fusion with Coupled State Space Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hang Zhou, Junqing Yu, Wei Yang, Wenbing Li, Zikai Song","submitted_at":"2024-05-28T09:57:03Z","abstract_excerpt":"The essence of multi-modal fusion lies in exploiting the complementary information inherent in diverse modalities. However, prevalent fusion methods rely on traditional neural architectures and are inadequately equipped to capture the dynamics of interactions across modalities, particularly in presence of complex intra- and inter-modality correlations. Recent advancements in State Space Models (SSMs), notably exemplified by the Mamba model, have emerged as promising contenders. Particularly, its state evolving process implies stronger modality fusion paradigm, making multi-modal fusion on SSMs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18014","kind":"arxiv","version":2},"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/2405.18014/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":"2405.18014","created_at":"2026-07-05T11:23:16.265676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18014v2","created_at":"2026-07-05T11:23:16.265676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18014","created_at":"2026-07-05T11:23:16.265676+00:00"},{"alias_kind":"pith_short_12","alias_value":"R5O3T43L32WZ","created_at":"2026-07-05T11:23:16.265676+00:00"},{"alias_kind":"pith_short_16","alias_value":"R5O3T43L32WZIBWE","created_at":"2026-07-05T11:23:16.265676+00:00"},{"alias_kind":"pith_short_8","alias_value":"R5O3T43L","created_at":"2026-07-05T11:23:16.265676+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.18970","citing_title":"Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State-Space Architectures from S4 to Mamba","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00029","citing_title":"LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24765","citing_title":"Semantic-Aware Logical Reasoning via a Semiotic Framework","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20311","citing_title":"Seeing Further and Wider: Joint Spatio-Temporal Enlargement for Micro-Video Popularity Prediction","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R5O3T43L32WZIBWEEB35TKHYBR","json":"https://pith.science/pith/R5O3T43L32WZIBWEEB35TKHYBR.json","graph_json":"https://pith.science/api/pith-number/R5O3T43L32WZIBWEEB35TKHYBR/graph.json","events_json":"https://pith.science/api/pith-number/R5O3T43L32WZIBWEEB35TKHYBR/events.json","paper":"https://pith.science/paper/R5O3T43L"},"agent_actions":{"view_html":"https://pith.science/pith/R5O3T43L32WZIBWEEB35TKHYBR","download_json":"https://pith.science/pith/R5O3T43L32WZIBWEEB35TKHYBR.json","view_paper":"https://pith.science/paper/R5O3T43L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18014&json=true","fetch_graph":"https://pith.science/api/pith-number/R5O3T43L32WZIBWEEB35TKHYBR/graph.json","fetch_events":"https://pith.science/api/pith-number/R5O3T43L32WZIBWEEB35TKHYBR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R5O3T43L32WZIBWEEB35TKHYBR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R5O3T43L32WZIBWEEB35TKHYBR/action/storage_attestation","attest_author":"https://pith.science/pith/R5O3T43L32WZIBWEEB35TKHYBR/action/author_attestation","sign_citation":"https://pith.science/pith/R5O3T43L32WZIBWEEB35TKHYBR/action/citation_signature","submit_replication":"https://pith.science/pith/R5O3T43L32WZIBWEEB35TKHYBR/action/replication_record"}},"created_at":"2026-07-05T11:23:16.265676+00:00","updated_at":"2026-07-05T11:23:16.265676+00:00"}