{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6LJHGCHNNH6D4YUWNSKCRSHJUE","short_pith_number":"pith:6LJHGCHN","canonical_record":{"source":{"id":"2503.11579","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T16:45:23Z","cross_cats_sorted":[],"title_canon_sha256":"43d84025d0d850b36ff49aca4e87656fb5606b55699307ad2857b5ad93f5111c","abstract_canon_sha256":"4d2ef441767cde42ccc885ca45084f553092c71f45678de86687240503af5c7f"},"schema_version":"1.0"},"canonical_sha256":"f2d27308ed69fc3e62966c9428c8e9a1045c3370ae80f8a2c680bc4eebffce45","source":{"kind":"arxiv","id":"2503.11579","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.11579","created_at":"2026-07-05T11:38:05Z"},{"alias_kind":"arxiv_version","alias_value":"2503.11579v2","created_at":"2026-07-05T11:38:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11579","created_at":"2026-07-05T11:38:05Z"},{"alias_kind":"pith_short_12","alias_value":"6LJHGCHNNH6D","created_at":"2026-07-05T11:38:05Z"},{"alias_kind":"pith_short_16","alias_value":"6LJHGCHNNH6D4YUW","created_at":"2026-07-05T11:38:05Z"},{"alias_kind":"pith_short_8","alias_value":"6LJHGCHN","created_at":"2026-07-05T11:38:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6LJHGCHNNH6D4YUWNSKCRSHJUE","target":"record","payload":{"canonical_record":{"source":{"id":"2503.11579","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T16:45:23Z","cross_cats_sorted":[],"title_canon_sha256":"43d84025d0d850b36ff49aca4e87656fb5606b55699307ad2857b5ad93f5111c","abstract_canon_sha256":"4d2ef441767cde42ccc885ca45084f553092c71f45678de86687240503af5c7f"},"schema_version":"1.0"},"canonical_sha256":"f2d27308ed69fc3e62966c9428c8e9a1045c3370ae80f8a2c680bc4eebffce45","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:05.486601Z","signature_b64":"N08w1PBqyEGlSPs4c5aKbeq+r9h0B2PEsVPxti0R1gf0EEgG/I5v+CKKZ7+j5TI07FEvSkMyPJOSLqnS+37DBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2d27308ed69fc3e62966c9428c8e9a1045c3370ae80f8a2c680bc4eebffce45","last_reissued_at":"2026-07-05T11:38:05.486088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:05.486088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.11579","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:38:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qLOQslej8IF6Q3E1GedqNJcmDnDUQvXjOOJUf6hQFLWw+nOY0q8d/QPeQtxhHKZevLPZM92nCJiXK5eAUyetAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T00:33:44.888666Z"},"content_sha256":"b594c6a60d676989aef375fe100f8546cc265ba470dcb5cc686aa4d10705afb6","schema_version":"1.0","event_id":"sha256:b594c6a60d676989aef375fe100f8546cc265ba470dcb5cc686aa4d10705afb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6LJHGCHNNH6D4YUWNSKCRSHJUE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Wei, Ge Zhang, Huan Yang, Weiming Ren, Wenhu Chen, Wentao Ma","submitted_at":"2025-03-14T16:45:23Z","abstract_excerpt":"State-of-the-art transformer-based large multimodal models (LMMs) struggle to handle hour-long video inputs due to the quadratic complexity of the causal self-attention operations, leading to high computational costs during training and inference. Existing token compression-based methods reduce the number of video tokens but often incur information loss and remain inefficient for extremely long sequences. In this paper, we explore an orthogonal direction to build a hybrid Mamba-Transformer model (VAMBA) that employs Mamba-2 blocks to encode video tokens with linear complexity. Without any toke"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11579","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/2503.11579/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:38:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QdpoOwQ4ypH/TL/HckktwNlYm/8XmuO1uiFtU+KQBkiFyV630AqPxPcm7wb/ja3S5F8YIgY6dM35++gdRdGvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T00:33:44.889213Z"},"content_sha256":"f9e918c5cf5a509723b8728e1f8f600a16472fac269b5223c574bb9e8b02652e","schema_version":"1.0","event_id":"sha256:f9e918c5cf5a509723b8728e1f8f600a16472fac269b5223c574bb9e8b02652e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6LJHGCHNNH6D4YUWNSKCRSHJUE/bundle.json","state_url":"https://pith.science/pith/6LJHGCHNNH6D4YUWNSKCRSHJUE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6LJHGCHNNH6D4YUWNSKCRSHJUE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T00:33:44Z","links":{"resolver":"https://pith.science/pith/6LJHGCHNNH6D4YUWNSKCRSHJUE","bundle":"https://pith.science/pith/6LJHGCHNNH6D4YUWNSKCRSHJUE/bundle.json","state":"https://pith.science/pith/6LJHGCHNNH6D4YUWNSKCRSHJUE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6LJHGCHNNH6D4YUWNSKCRSHJUE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6LJHGCHNNH6D4YUWNSKCRSHJUE","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":"4d2ef441767cde42ccc885ca45084f553092c71f45678de86687240503af5c7f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T16:45:23Z","title_canon_sha256":"43d84025d0d850b36ff49aca4e87656fb5606b55699307ad2857b5ad93f5111c"},"schema_version":"1.0","source":{"id":"2503.11579","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.11579","created_at":"2026-07-05T11:38:05Z"},{"alias_kind":"arxiv_version","alias_value":"2503.11579v2","created_at":"2026-07-05T11:38:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11579","created_at":"2026-07-05T11:38:05Z"},{"alias_kind":"pith_short_12","alias_value":"6LJHGCHNNH6D","created_at":"2026-07-05T11:38:05Z"},{"alias_kind":"pith_short_16","alias_value":"6LJHGCHNNH6D4YUW","created_at":"2026-07-05T11:38:05Z"},{"alias_kind":"pith_short_8","alias_value":"6LJHGCHN","created_at":"2026-07-05T11:38:05Z"}],"graph_snapshots":[{"event_id":"sha256:f9e918c5cf5a509723b8728e1f8f600a16472fac269b5223c574bb9e8b02652e","target":"graph","created_at":"2026-07-05T11:38:05Z","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/2503.11579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art transformer-based large multimodal models (LMMs) struggle to handle hour-long video inputs due to the quadratic complexity of the causal self-attention operations, leading to high computational costs during training and inference. Existing token compression-based methods reduce the number of video tokens but often incur information loss and remain inefficient for extremely long sequences. In this paper, we explore an orthogonal direction to build a hybrid Mamba-Transformer model (VAMBA) that employs Mamba-2 blocks to encode video tokens with linear complexity. Without any toke","authors_text":"Cong Wei, Ge Zhang, Huan Yang, Weiming Ren, Wenhu Chen, Wentao Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T16:45:23Z","title":"Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11579","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:b594c6a60d676989aef375fe100f8546cc265ba470dcb5cc686aa4d10705afb6","target":"record","created_at":"2026-07-05T11:38:05Z","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":"4d2ef441767cde42ccc885ca45084f553092c71f45678de86687240503af5c7f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T16:45:23Z","title_canon_sha256":"43d84025d0d850b36ff49aca4e87656fb5606b55699307ad2857b5ad93f5111c"},"schema_version":"1.0","source":{"id":"2503.11579","kind":"arxiv","version":2}},"canonical_sha256":"f2d27308ed69fc3e62966c9428c8e9a1045c3370ae80f8a2c680bc4eebffce45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2d27308ed69fc3e62966c9428c8e9a1045c3370ae80f8a2c680bc4eebffce45","first_computed_at":"2026-07-05T11:38:05.486088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:05.486088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N08w1PBqyEGlSPs4c5aKbeq+r9h0B2PEsVPxti0R1gf0EEgG/I5v+CKKZ7+j5TI07FEvSkMyPJOSLqnS+37DBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:05.486601Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.11579","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b594c6a60d676989aef375fe100f8546cc265ba470dcb5cc686aa4d10705afb6","sha256:f9e918c5cf5a509723b8728e1f8f600a16472fac269b5223c574bb9e8b02652e"],"state_sha256":"e04013b8641ef6225a2b1805b24a4f24127cc26c007fb76daa92367770bb31a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KBwzpOgqe4xW3GYqKAmJL9JEqeZCw8PryjU7D92eROnRLYuJUlfF9Uak5FD9YlA57vqjVjOd5Xxw7TU4ilKvCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T00:33:44.895126Z","bundle_sha256":"1f233615640a5371b4e90133bd86b5a5de35997aebc6232c52ea5a6879a842c2"}}