{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CNQLMV4Y5CSAIHUKCO2K5P5STP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0139cf9e62c2d5ec2712e9075b6d4c31b4682b5221f5cb832c0e80cf3d509ea9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-17T19:36:37Z","title_canon_sha256":"2628fbc26a40fa68cfc739c90e928c3568f1a7ac42e231863b1106f4cf6ef298"},"schema_version":"1.0","source":{"id":"2409.11513","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11513","created_at":"2026-07-05T10:07:44Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11513v2","created_at":"2026-07-05T10:07:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11513","created_at":"2026-07-05T10:07:44Z"},{"alias_kind":"pith_short_12","alias_value":"CNQLMV4Y5CSA","created_at":"2026-07-05T10:07:44Z"},{"alias_kind":"pith_short_16","alias_value":"CNQLMV4Y5CSAIHUK","created_at":"2026-07-05T10:07:44Z"},{"alias_kind":"pith_short_8","alias_value":"CNQLMV4Y","created_at":"2026-07-05T10:07:44Z"}],"graph_snapshots":[{"event_id":"sha256:3bd11a3f878df0e7339ea87f43a697a8f4dfa5dd5c0e13f9ecb3b07ac2720a64","target":"graph","created_at":"2026-07-05T10:07:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.11513/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Apoorva Beedu, Irfan Essa, Jason Sheinkopf, Zhikang Dong","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-17T19:36:37Z","title":"Mamba Fusion: Learning Actions Through Questioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11513","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:573e0193003d29d27b6bf3ec728f5a7f003d558a4f2be3fc23eb108fdd798b84","target":"record","created_at":"2026-07-05T10:07:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0139cf9e62c2d5ec2712e9075b6d4c31b4682b5221f5cb832c0e80cf3d509ea9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-17T19:36:37Z","title_canon_sha256":"2628fbc26a40fa68cfc739c90e928c3568f1a7ac42e231863b1106f4cf6ef298"},"schema_version":"1.0","source":{"id":"2409.11513","kind":"arxiv","version":2}},"canonical_sha256":"1360b65798e8a4041e8a13b4aebfb29bcc52dce16b5b5500bec820db342bc241","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1360b65798e8a4041e8a13b4aebfb29bcc52dce16b5b5500bec820db342bc241","first_computed_at":"2026-07-05T10:07:44.288582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:44.288582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WYPlZxCnCMlSmy/Bm43gB3gniPtrQPbKJnX9GW+Qr+rUlsNDNI31P+tA0DeK9YP1AxGK0/g55anM8T6qCEOgBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:44.289064Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11513","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:573e0193003d29d27b6bf3ec728f5a7f003d558a4f2be3fc23eb108fdd798b84","sha256:3bd11a3f878df0e7339ea87f43a697a8f4dfa5dd5c0e13f9ecb3b07ac2720a64"],"state_sha256":"0c9ea4073b7768e9416b96a07936189bee56c6b37c56855e541c47630577f992"}