{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:U73BM72ZIBWZC2YQHBTDVO54KZ","short_pith_number":"pith:U73BM72Z","canonical_record":{"source":{"id":"2411.04923","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T17:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"770949bd7137bb3fbba2b25ad901328a8086b5c4886d2cbad8a6130fa9d2661e","abstract_canon_sha256":"4c34e8c0eb212c7a064ad74201a8df673fbd1520a0c4d3602559233b8f4cde3e"},"schema_version":"1.0"},"canonical_sha256":"a7f6167f59406d916b1038663abbbc566dab737790d72299bcad3138ba227d42","source":{"kind":"arxiv","id":"2411.04923","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:U73BM72ZIBWZC2YQHBTDVO54KZ","target":"record","payload":{"canonical_record":{"source":{"id":"2411.04923","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T17:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"770949bd7137bb3fbba2b25ad901328a8086b5c4886d2cbad8a6130fa9d2661e","abstract_canon_sha256":"4c34e8c0eb212c7a064ad74201a8df673fbd1520a0c4d3602559233b8f4cde3e"},"schema_version":"1.0"},"canonical_sha256":"a7f6167f59406d916b1038663abbbc566dab737790d72299bcad3138ba227d42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:37.748790Z","signature_b64":"cZ9DoNShjd1Ts6geICi2LaDteu8v08fX1ROrV6x2s6DTZ/hkVGpEfeAZNULNAULzaFUWmocTIOQOOZhRYKXZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7f6167f59406d916b1038663abbbc566dab737790d72299bcad3138ba227d42","last_reissued_at":"2026-07-05T10:38:37.748205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:37.748205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.04923","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:38:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NulTx0CwFGelUzxj2kwS5EL0iZRJWRHQ4lCKgTsTi5dUgHUFv7TDKrXkA52burqSeH7QnePMCnmQMQ2dv3u6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:19:46.116398Z"},"content_sha256":"3e13fe91e8e1d1d5a03b060aae3091b6c056e2646390c8714f1f6f98042909d2","schema_version":"1.0","event_id":"sha256:3e13fe91e8e1d1d5a03b060aae3091b6c056e2646390c8714f1f6f98042909d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:U73BM72ZIBWZC2YQHBTDVO54KZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Xing, Fahad Shahbaz Khan, Hanan Gani, Jiale Cao, Salman Khan, Shehan Munasinghe, Wenqi Zhu","submitted_at":"2024-11-07T17:59:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04923","kind":"arxiv","version":3},"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/2411.04923/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":"2026-07-05T10:38:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P/UnEAOIgrFHqhdoaXw0CG686bEaHkikq/Sip0QVWOCEaApyo2OKAJOk/3gUT5VOzrUdHu0NKwRK/FH9YHdhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:19:46.116775Z"},"content_sha256":"09ce7632d54807f865b3a7b5d6ffe8415ed59aea5e2cde3e695d3b31f7429154","schema_version":"1.0","event_id":"sha256:09ce7632d54807f865b3a7b5d6ffe8415ed59aea5e2cde3e695d3b31f7429154"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U73BM72ZIBWZC2YQHBTDVO54KZ/bundle.json","state_url":"https://pith.science/pith/U73BM72ZIBWZC2YQHBTDVO54KZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U73BM72ZIBWZC2YQHBTDVO54KZ/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":"2026-07-07T12:19:46Z","links":{"resolver":"https://pith.science/pith/U73BM72ZIBWZC2YQHBTDVO54KZ","bundle":"https://pith.science/pith/U73BM72ZIBWZC2YQHBTDVO54KZ/bundle.json","state":"https://pith.science/pith/U73BM72ZIBWZC2YQHBTDVO54KZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U73BM72ZIBWZC2YQHBTDVO54KZ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qlxi2nZ9ZnkoC1CCJkvlmweYZbaZn9NlWGh9N1HpBuZdfp+weMC+iaPt5O8mZByJYuaG3HhvOhQKnvcW/rbdDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:19:46.118745Z","bundle_sha256":"0e81e0824b49d58c0e2baf8c905f1f489838ac2875e23c3ed13a378f4f471476"}}