{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KPVQ473KMUQ3SYQEYYX3DAQYG7","short_pith_number":"pith:KPVQ473K","canonical_record":{"source":{"id":"2406.19006","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-27T08:45:31Z","cross_cats_sorted":[],"title_canon_sha256":"6b8287f04b4ca4bdd245996ef32c9f421cf6963f73f39c98ef29b8288d900750","abstract_canon_sha256":"16a27bb3d33f2dd3870ae26ae3ef385e855f521d95d845430af1c28dbfc71b5f"},"schema_version":"1.0"},"canonical_sha256":"53eb0e7f6a6521b96204c62fb1821837cd21d2f04cb3c0d7d4f359af57e5b6a7","source":{"kind":"arxiv","id":"2406.19006","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19006","created_at":"2026-07-05T09:34:36Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19006v4","created_at":"2026-07-05T09:34:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19006","created_at":"2026-07-05T09:34:36Z"},{"alias_kind":"pith_short_12","alias_value":"KPVQ473KMUQ3","created_at":"2026-07-05T09:34:36Z"},{"alias_kind":"pith_short_16","alias_value":"KPVQ473KMUQ3SYQE","created_at":"2026-07-05T09:34:36Z"},{"alias_kind":"pith_short_8","alias_value":"KPVQ473K","created_at":"2026-07-05T09:34:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KPVQ473KMUQ3SYQEYYX3DAQYG7","target":"record","payload":{"canonical_record":{"source":{"id":"2406.19006","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-27T08:45:31Z","cross_cats_sorted":[],"title_canon_sha256":"6b8287f04b4ca4bdd245996ef32c9f421cf6963f73f39c98ef29b8288d900750","abstract_canon_sha256":"16a27bb3d33f2dd3870ae26ae3ef385e855f521d95d845430af1c28dbfc71b5f"},"schema_version":"1.0"},"canonical_sha256":"53eb0e7f6a6521b96204c62fb1821837cd21d2f04cb3c0d7d4f359af57e5b6a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:36.643918Z","signature_b64":"mAKkLo7EzzOj7jxddhqJn4A2Ipj7ZjdIDBio9A0eTJaTNSfqxTG0lXzCxJiRrjMRbtLSkiFEy/waplvLv67XAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53eb0e7f6a6521b96204c62fb1821837cd21d2f04cb3c0d7d4f359af57e5b6a7","last_reissued_at":"2026-07-05T09:34:36.643446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:36.643446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.19006","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:34:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mXv7kWqlTWlMQtm/r71tfC/BgldsPI/H/QBaToPjxduO0i8+/O6I+dTpv74+edwEtjqu2NEzttR+NwAi9sDLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T23:46:51.277913Z"},"content_sha256":"13ba418a4fbadfb7e221a1c760f4da1d01225574898054f36680c847a5c073c1","schema_version":"1.0","event_id":"sha256:13ba418a4fbadfb7e221a1c760f4da1d01225574898054f36680c847a5c073c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KPVQ473KMUQ3SYQEYYX3DAQYG7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Snakes and Ladders: Two Steps Up for VideoMamba","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albert Ali Salah, Hui Lu, Ronald Poppe","submitted_at":"2024-06-27T08:45:31Z","abstract_excerpt":"Video understanding requires the extraction of rich spatio-temporal representations, which transformer models achieve through self-attention. Unfortunately, self-attention poses a computational burden. In NLP, Mamba has surfaced as an efficient alternative for transformers. However, Mamba's successes do not trivially extend to vision tasks, including those in video analysis. In this paper, we theoretically analyze the differences between self-attention and Mamba. We identify two limitations in Mamba's token processing: historical decay and element contradiction. We propose VideoMambaPro (VMP) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19006","kind":"arxiv","version":4},"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/2406.19006/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":"2026-07-05T09:34:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5EoKxR2kBccnC4kmg86ADKWCnXatRGV2m4rAepEOGfyHjzVPu+R+FEdkdXp9lJk9sjlTB9DfaS3artjRtUj2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T23:46:51.278195Z"},"content_sha256":"d18cc41e0526255d6b2482da1a67241dc3ec5a4aa8efdcecdc64156d17f49a15","schema_version":"1.0","event_id":"sha256:d18cc41e0526255d6b2482da1a67241dc3ec5a4aa8efdcecdc64156d17f49a15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPVQ473KMUQ3SYQEYYX3DAQYG7/bundle.json","state_url":"https://pith.science/pith/KPVQ473KMUQ3SYQEYYX3DAQYG7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPVQ473KMUQ3SYQEYYX3DAQYG7/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":"2026-07-31T23:46:51Z","links":{"resolver":"https://pith.science/pith/KPVQ473KMUQ3SYQEYYX3DAQYG7","bundle":"https://pith.science/pith/KPVQ473KMUQ3SYQEYYX3DAQYG7/bundle.json","state":"https://pith.science/pith/KPVQ473KMUQ3SYQEYYX3DAQYG7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPVQ473KMUQ3SYQEYYX3DAQYG7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KPVQ473KMUQ3SYQEYYX3DAQYG7","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":"16a27bb3d33f2dd3870ae26ae3ef385e855f521d95d845430af1c28dbfc71b5f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-27T08:45:31Z","title_canon_sha256":"6b8287f04b4ca4bdd245996ef32c9f421cf6963f73f39c98ef29b8288d900750"},"schema_version":"1.0","source":{"id":"2406.19006","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19006","created_at":"2026-07-05T09:34:36Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19006v4","created_at":"2026-07-05T09:34:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19006","created_at":"2026-07-05T09:34:36Z"},{"alias_kind":"pith_short_12","alias_value":"KPVQ473KMUQ3","created_at":"2026-07-05T09:34:36Z"},{"alias_kind":"pith_short_16","alias_value":"KPVQ473KMUQ3SYQE","created_at":"2026-07-05T09:34:36Z"},{"alias_kind":"pith_short_8","alias_value":"KPVQ473K","created_at":"2026-07-05T09:34:36Z"}],"graph_snapshots":[{"event_id":"sha256:d18cc41e0526255d6b2482da1a67241dc3ec5a4aa8efdcecdc64156d17f49a15","target":"graph","created_at":"2026-07-05T09:34:36Z","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/2406.19006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video understanding requires the extraction of rich spatio-temporal representations, which transformer models achieve through self-attention. Unfortunately, self-attention poses a computational burden. In NLP, Mamba has surfaced as an efficient alternative for transformers. However, Mamba's successes do not trivially extend to vision tasks, including those in video analysis. In this paper, we theoretically analyze the differences between self-attention and Mamba. We identify two limitations in Mamba's token processing: historical decay and element contradiction. We propose VideoMambaPro (VMP) ","authors_text":"Albert Ali Salah, Hui Lu, Ronald Poppe","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-27T08:45:31Z","title":"Snakes and Ladders: Two Steps Up for VideoMamba"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19006","kind":"arxiv","version":4},"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":"sha256:13ba418a4fbadfb7e221a1c760f4da1d01225574898054f36680c847a5c073c1","target":"record","created_at":"2026-07-05T09:34:36Z","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":"16a27bb3d33f2dd3870ae26ae3ef385e855f521d95d845430af1c28dbfc71b5f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-27T08:45:31Z","title_canon_sha256":"6b8287f04b4ca4bdd245996ef32c9f421cf6963f73f39c98ef29b8288d900750"},"schema_version":"1.0","source":{"id":"2406.19006","kind":"arxiv","version":4}},"canonical_sha256":"53eb0e7f6a6521b96204c62fb1821837cd21d2f04cb3c0d7d4f359af57e5b6a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53eb0e7f6a6521b96204c62fb1821837cd21d2f04cb3c0d7d4f359af57e5b6a7","first_computed_at":"2026-07-05T09:34:36.643446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:36.643446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mAKkLo7EzzOj7jxddhqJn4A2Ipj7ZjdIDBio9A0eTJaTNSfqxTG0lXzCxJiRrjMRbtLSkiFEy/waplvLv67XAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:36.643918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.19006","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13ba418a4fbadfb7e221a1c760f4da1d01225574898054f36680c847a5c073c1","sha256:d18cc41e0526255d6b2482da1a67241dc3ec5a4aa8efdcecdc64156d17f49a15"],"state_sha256":"71f0b037b008f240ed4149436e1be851e18fcb59a01c6923a72dd1a55f290436"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YpygK+Kae8FimRviBKbgpTHJHVt25qSCktGArjO6ouo46H4BXyvlQzWs+3RxRWSKQhJQkCXblrwPpn9n0jC7BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T23:46:51.281336Z","bundle_sha256":"e90138ba7ea3b2005bc9d7ababc8ef09a34383e143aae0387bc797a040473640"}}