{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KIEK44BLUETJA3XXHLMNWYMIFN","short_pith_number":"pith:KIEK44BL","schema_version":"1.0","canonical_sha256":"5208ae702ba126906ef73ad8db61882b7517725224f63fe53b6601c0fadcfef0","source":{"kind":"arxiv","id":"2406.09833","version":3},"attestation_state":"computed","paper":{"title":"SHMamba: Structured Hyperbolic State Space Model for Audio-Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.AI","authors_text":"Guanghui Cheng, Wenrui Li, Zhe Yang","submitted_at":"2024-06-14T08:43:31Z","abstract_excerpt":"The Audio-Visual Question Answering (AVQA) task holds significant potential for applications. Compared to traditional unimodal approaches, the multi-modal input of AVQA makes feature extraction and fusion processes more challenging. Euclidean space is difficult to effectively represent multi-dimensional relationships of data. Especially when extracting and processing data with a tree structure or hierarchical structure, Euclidean space is not suitable as an embedding space. Additionally, the self-attention mechanism in Transformers is effective in capturing the dynamic relationships between el"},"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":"2406.09833","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-14T08:43:31Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"9a4cef43f82e6a27caed641b4ef3f6dce1d01d7598649c9bd5bf0901944fdf76","abstract_canon_sha256":"64c3a6f69e7ca9ffb72bf27700142cbd49a865c61bb7de3aff2c373739bf9cf5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:14.706050Z","signature_b64":"rb2xsZQ3m62dntXcI1GCRwTLzxkDPDILhtUEGE700YIJ8XxtdNZfE6AkMJJcLcU0Mz5AlUdbzNAxpDYlvCWABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5208ae702ba126906ef73ad8db61882b7517725224f63fe53b6601c0fadcfef0","last_reissued_at":"2026-07-05T08:44:14.705561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:14.705561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SHMamba: Structured Hyperbolic State Space Model for Audio-Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.AI","authors_text":"Guanghui Cheng, Wenrui Li, Zhe Yang","submitted_at":"2024-06-14T08:43:31Z","abstract_excerpt":"The Audio-Visual Question Answering (AVQA) task holds significant potential for applications. Compared to traditional unimodal approaches, the multi-modal input of AVQA makes feature extraction and fusion processes more challenging. Euclidean space is difficult to effectively represent multi-dimensional relationships of data. Especially when extracting and processing data with a tree structure or hierarchical structure, Euclidean space is not suitable as an embedding space. Additionally, the self-attention mechanism in Transformers is effective in capturing the dynamic relationships between el"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09833","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/2406.09833/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":"2406.09833","created_at":"2026-07-05T08:44:14.705618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09833v3","created_at":"2026-07-05T08:44:14.705618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09833","created_at":"2026-07-05T08:44:14.705618+00:00"},{"alias_kind":"pith_short_12","alias_value":"KIEK44BLUETJ","created_at":"2026-07-05T08:44:14.705618+00:00"},{"alias_kind":"pith_short_16","alias_value":"KIEK44BLUETJA3XX","created_at":"2026-07-05T08:44:14.705618+00:00"},{"alias_kind":"pith_short_8","alias_value":"KIEK44BL","created_at":"2026-07-05T08:44:14.705618+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.01129","citing_title":"A Survey of Mamba","ref_index":218,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KIEK44BLUETJA3XXHLMNWYMIFN","json":"https://pith.science/pith/KIEK44BLUETJA3XXHLMNWYMIFN.json","graph_json":"https://pith.science/api/pith-number/KIEK44BLUETJA3XXHLMNWYMIFN/graph.json","events_json":"https://pith.science/api/pith-number/KIEK44BLUETJA3XXHLMNWYMIFN/events.json","paper":"https://pith.science/paper/KIEK44BL"},"agent_actions":{"view_html":"https://pith.science/pith/KIEK44BLUETJA3XXHLMNWYMIFN","download_json":"https://pith.science/pith/KIEK44BLUETJA3XXHLMNWYMIFN.json","view_paper":"https://pith.science/paper/KIEK44BL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09833&json=true","fetch_graph":"https://pith.science/api/pith-number/KIEK44BLUETJA3XXHLMNWYMIFN/graph.json","fetch_events":"https://pith.science/api/pith-number/KIEK44BLUETJA3XXHLMNWYMIFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KIEK44BLUETJA3XXHLMNWYMIFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KIEK44BLUETJA3XXHLMNWYMIFN/action/storage_attestation","attest_author":"https://pith.science/pith/KIEK44BLUETJA3XXHLMNWYMIFN/action/author_attestation","sign_citation":"https://pith.science/pith/KIEK44BLUETJA3XXHLMNWYMIFN/action/citation_signature","submit_replication":"https://pith.science/pith/KIEK44BLUETJA3XXHLMNWYMIFN/action/replication_record"}},"created_at":"2026-07-05T08:44:14.705618+00:00","updated_at":"2026-07-05T08:44:14.705618+00:00"}