{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U73BM72ZIBWZC2YQHBTDVO54KZ","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":"4c34e8c0eb212c7a064ad74201a8df673fbd1520a0c4d3602559233b8f4cde3e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T17:59:27Z","title_canon_sha256":"770949bd7137bb3fbba2b25ad901328a8086b5c4886d2cbad8a6130fa9d2661e"},"schema_version":"1.0","source":{"id":"2411.04923","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04923","created_at":"2026-07-05T10:38:37Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04923v3","created_at":"2026-07-05T10:38:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04923","created_at":"2026-07-05T10:38:37Z"},{"alias_kind":"pith_short_12","alias_value":"U73BM72ZIBWZ","created_at":"2026-07-05T10:38:37Z"},{"alias_kind":"pith_short_16","alias_value":"U73BM72ZIBWZC2YQ","created_at":"2026-07-05T10:38:37Z"},{"alias_kind":"pith_short_8","alias_value":"U73BM72Z","created_at":"2026-07-05T10:38:37Z"}],"graph_snapshots":[{"event_id":"sha256:09ce7632d54807f865b3a7b5d6ffe8415ed59aea5e2cde3e695d3b31f7429154","target":"graph","created_at":"2026-07-05T10:38:37Z","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/2411.04923/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-grained alignment between videos and text is challenging due to complex spatial and temporal dynamics in videos. Existing video-based Large Multimodal Models (LMMs) handle basic conversations but struggle with precise pixel-level grounding in videos. To address this, we introduce VideoGLaMM, a LMM designed for fine-grained pixel-level grounding in videos based on user-provided textual inputs. Our design seamlessly connects three key components: a Large Language Model, a dual vision encoder that emphasizes both spatial and temporal details, and a spatio-temporal decoder for accurate mask g","authors_text":"Eric Xing, Fahad Shahbaz Khan, Hanan Gani, Jiale Cao, Salman Khan, Shehan Munasinghe, Wenqi Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T17:59:27Z","title":"VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04923","kind":"arxiv","version":3},"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":"sha256:3e13fe91e8e1d1d5a03b060aae3091b6c056e2646390c8714f1f6f98042909d2","target":"record","created_at":"2026-07-05T10:38:37Z","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":"4c34e8c0eb212c7a064ad74201a8df673fbd1520a0c4d3602559233b8f4cde3e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T17:59:27Z","title_canon_sha256":"770949bd7137bb3fbba2b25ad901328a8086b5c4886d2cbad8a6130fa9d2661e"},"schema_version":"1.0","source":{"id":"2411.04923","kind":"arxiv","version":3}},"canonical_sha256":"a7f6167f59406d916b1038663abbbc566dab737790d72299bcad3138ba227d42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7f6167f59406d916b1038663abbbc566dab737790d72299bcad3138ba227d42","first_computed_at":"2026-07-05T10:38:37.748205Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:37.748205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cZ9DoNShjd1Ts6geICi2LaDteu8v08fX1ROrV6x2s6DTZ/hkVGpEfeAZNULNAULzaFUWmocTIOQOOZhRYKXZBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:37.748790Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.04923","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e13fe91e8e1d1d5a03b060aae3091b6c056e2646390c8714f1f6f98042909d2","sha256:09ce7632d54807f865b3a7b5d6ffe8415ed59aea5e2cde3e695d3b31f7429154"],"state_sha256":"588a610b05a9b78482f5ad00b5595217d42add6c99a51da3bb306fe78017a3e1"}