{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HWJOO3UCZIPGSXZKB7PIQ7Z4J2","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":"0813a117de0b6a8686b03d2914c86ce3860a80832d190f48ea9c8f6f2f349f52","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-23T13:23:22Z","title_canon_sha256":"93519cb250d66b69c3d0886e0673b862d770787b08056ffdb6092e2cf4339da3"},"schema_version":"1.0","source":{"id":"2411.15556","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15556","created_at":"2026-07-05T10:40:36Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15556v2","created_at":"2026-07-05T10:40:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15556","created_at":"2026-07-05T10:40:36Z"},{"alias_kind":"pith_short_12","alias_value":"HWJOO3UCZIPG","created_at":"2026-07-05T10:40:36Z"},{"alias_kind":"pith_short_16","alias_value":"HWJOO3UCZIPGSXZK","created_at":"2026-07-05T10:40:36Z"},{"alias_kind":"pith_short_8","alias_value":"HWJOO3UC","created_at":"2026-07-05T10:40:36Z"}],"graph_snapshots":[{"event_id":"sha256:248482ee8f7fbbe92a0b11c6784deb145951ea1e29c9075bd2dd04e555d38ddd","target":"graph","created_at":"2026-07-05T10:40:36Z","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/2411.15556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) are crucial for applications requiring integrated understanding textual and visual information. However, existing VLMs struggle with long videos due to computational inefficiency, memory limitations, and difficulties in maintaining coherent understanding across extended sequences. To address these challenges, we introduce ReWind, a novel memory-based VLM designed for efficient long video understanding while preserving temporal fidelity. ReWind operates in a two-stage framework. In the first stage, ReWind maintains a dynamic learnable memory module with a novel \\te","authors_text":"Anxhelo Diko, Ioannis Patras, Shiyan Sun, Tinghuai Wang, Wassim Swaileh","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-23T13:23:22Z","title":"ReWind: Understanding Long Videos with Instructed Learnable Memory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15556","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:a98a0fc371e9bea5554f3fad3d1f062bb9dee0f67bee00c71a0654dd62703dd1","target":"record","created_at":"2026-07-05T10:40:36Z","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":"0813a117de0b6a8686b03d2914c86ce3860a80832d190f48ea9c8f6f2f349f52","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-23T13:23:22Z","title_canon_sha256":"93519cb250d66b69c3d0886e0673b862d770787b08056ffdb6092e2cf4339da3"},"schema_version":"1.0","source":{"id":"2411.15556","kind":"arxiv","version":2}},"canonical_sha256":"3d92e76e82ca1e695f2a0fde887f3c4e8e9e136cd180ca75f4dbd2330df4d71d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d92e76e82ca1e695f2a0fde887f3c4e8e9e136cd180ca75f4dbd2330df4d71d","first_computed_at":"2026-07-05T10:40:36.983384Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:36.983384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nX6xH7W4L0J1fdzsc0S9jMYuRwS+C19c2o2Ro1BVMTDzUlI7zFi62e+NvpE4zR9vCdPXmS81B1uZZgmhSrkKBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:36.983879Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15556","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a98a0fc371e9bea5554f3fad3d1f062bb9dee0f67bee00c71a0654dd62703dd1","sha256:248482ee8f7fbbe92a0b11c6784deb145951ea1e29c9075bd2dd04e555d38ddd"],"state_sha256":"2a37771203f21e904d0e1a77f2db0b8e5349f2c92e47326a5a3a0b062ac4f0c4"}