{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CNQLMV4Y5CSAIHUKCO2K5P5STP","short_pith_number":"pith:CNQLMV4Y","schema_version":"1.0","canonical_sha256":"1360b65798e8a4041e8a13b4aebfb29bcc52dce16b5b5500bec820db342bc241","source":{"kind":"arxiv","id":"2409.11513","version":2},"attestation_state":"computed","paper":{"title":"Mamba Fusion: Learning Actions Through Questioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Apoorva Beedu, Irfan Essa, Jason Sheinkopf, Zhikang Dong","submitted_at":"2024-09-17T19:36:37Z","abstract_excerpt":"Video Language Models (VLMs) are crucial for generalizing across diverse tasks and using language cues to enhance learning. While transformer-based architectures have been the de facto in vision-language training, they face challenges like quadratic computational complexity, high GPU memory usage, and difficulty with long-term dependencies. To address these limitations, we introduce MambaVL, a novel model that leverages recent advancements in selective state space modality fusion to efficiently capture long-range dependencies and learn joint representations for vision and language data. MambaV"},"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":"2409.11513","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-17T19:36:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2628fbc26a40fa68cfc739c90e928c3568f1a7ac42e231863b1106f4cf6ef298","abstract_canon_sha256":"0139cf9e62c2d5ec2712e9075b6d4c31b4682b5221f5cb832c0e80cf3d509ea9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:44.289064Z","signature_b64":"WYPlZxCnCMlSmy/Bm43gB3gniPtrQPbKJnX9GW+Qr+rUlsNDNI31P+tA0DeK9YP1AxGK0/g55anM8T6qCEOgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1360b65798e8a4041e8a13b4aebfb29bcc52dce16b5b5500bec820db342bc241","last_reissued_at":"2026-07-05T10:07:44.288582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:44.288582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mamba Fusion: Learning Actions Through Questioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Apoorva Beedu, Irfan Essa, Jason Sheinkopf, Zhikang Dong","submitted_at":"2024-09-17T19:36:37Z","abstract_excerpt":"Video Language Models (VLMs) are crucial for generalizing across diverse tasks and using language cues to enhance learning. While transformer-based architectures have been the de facto in vision-language training, they face challenges like quadratic computational complexity, high GPU memory usage, and difficulty with long-term dependencies. To address these limitations, we introduce MambaVL, a novel model that leverages recent advancements in selective state space modality fusion to efficiently capture long-range dependencies and learn joint representations for vision and language data. MambaV"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11513","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/2409.11513/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":"2409.11513","created_at":"2026-07-05T10:07:44.288638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11513v2","created_at":"2026-07-05T10:07:44.288638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11513","created_at":"2026-07-05T10:07:44.288638+00:00"},{"alias_kind":"pith_short_12","alias_value":"CNQLMV4Y5CSA","created_at":"2026-07-05T10:07:44.288638+00:00"},{"alias_kind":"pith_short_16","alias_value":"CNQLMV4Y5CSAIHUK","created_at":"2026-07-05T10:07:44.288638+00:00"},{"alias_kind":"pith_short_8","alias_value":"CNQLMV4Y","created_at":"2026-07-05T10:07:44.288638+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.18801","citing_title":"Every Image Listens, Every Image Dances: Music-Driven Image Animation","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CNQLMV4Y5CSAIHUKCO2K5P5STP","json":"https://pith.science/pith/CNQLMV4Y5CSAIHUKCO2K5P5STP.json","graph_json":"https://pith.science/api/pith-number/CNQLMV4Y5CSAIHUKCO2K5P5STP/graph.json","events_json":"https://pith.science/api/pith-number/CNQLMV4Y5CSAIHUKCO2K5P5STP/events.json","paper":"https://pith.science/paper/CNQLMV4Y"},"agent_actions":{"view_html":"https://pith.science/pith/CNQLMV4Y5CSAIHUKCO2K5P5STP","download_json":"https://pith.science/pith/CNQLMV4Y5CSAIHUKCO2K5P5STP.json","view_paper":"https://pith.science/paper/CNQLMV4Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11513&json=true","fetch_graph":"https://pith.science/api/pith-number/CNQLMV4Y5CSAIHUKCO2K5P5STP/graph.json","fetch_events":"https://pith.science/api/pith-number/CNQLMV4Y5CSAIHUKCO2K5P5STP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CNQLMV4Y5CSAIHUKCO2K5P5STP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CNQLMV4Y5CSAIHUKCO2K5P5STP/action/storage_attestation","attest_author":"https://pith.science/pith/CNQLMV4Y5CSAIHUKCO2K5P5STP/action/author_attestation","sign_citation":"https://pith.science/pith/CNQLMV4Y5CSAIHUKCO2K5P5STP/action/citation_signature","submit_replication":"https://pith.science/pith/CNQLMV4Y5CSAIHUKCO2K5P5STP/action/replication_record"}},"created_at":"2026-07-05T10:07:44.288638+00:00","updated_at":"2026-07-05T10:07:44.288638+00:00"}