{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LXCNSUADVJAJRLXK5J6S62ZMUJ","short_pith_number":"pith:LXCNSUAD","canonical_record":{"source":{"id":"2409.19603","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-29T07:47:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e48db4c40573044ef94fa984fad27475bff5997c3aea8078f3df409cecc35b03","abstract_canon_sha256":"6e4a42b077075b6a8980821237dfdde3b46618e1f1c08e44156511fd73635d25"},"schema_version":"1.0"},"canonical_sha256":"5dc4d95003aa4098aeeaea7d2f6b2ca26da2544bba9d430674b0e51436b9b535","source":{"kind":"arxiv","id":"2409.19603","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19603","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19603v1","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19603","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"LXCNSUADVJAJ","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"LXCNSUADVJAJRLXK","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"LXCNSUAD","created_at":"2026-07-05T09:13:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LXCNSUADVJAJRLXK5J6S62ZMUJ","target":"record","payload":{"canonical_record":{"source":{"id":"2409.19603","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-29T07:47:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e48db4c40573044ef94fa984fad27475bff5997c3aea8078f3df409cecc35b03","abstract_canon_sha256":"6e4a42b077075b6a8980821237dfdde3b46618e1f1c08e44156511fd73635d25"},"schema_version":"1.0"},"canonical_sha256":"5dc4d95003aa4098aeeaea7d2f6b2ca26da2544bba9d430674b0e51436b9b535","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:18.162998Z","signature_b64":"zTUIP1Y720n4aPIanoFccMgwLBFQr9tS40KLUjNBNDqa0iYWjVb0HClbm4r4udawKpe5scM+hSQzsGUhGCefCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dc4d95003aa4098aeeaea7d2f6b2ca26da2544bba9d430674b0e51436b9b535","last_reissued_at":"2026-07-05T09:13:18.162625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:18.162625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.19603","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:13:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R5Lc+qU/6sImIiQ+sfXIFkYXZU32dwd0i59RJyiPnMjBqid7gcaC7Wi6NHx6SQO10tGthmwh70YF27Yl/AOWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:43:43.282526Z"},"content_sha256":"d032f8f87e0e3cbe6fa057c8e295e62aa34f2fc021489d620c458c85d55bfc0c","schema_version":"1.0","event_id":"sha256:d032f8f87e0e3cbe6fa057c8e295e62aa34f2fc021489d620c458c85d55bfc0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LXCNSUADVJAJRLXK5J6S62ZMUJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haiyang Mei, Joya Chen, Lei Liu, Mike Zheng Shou, Pichao Wang, Tong He, Zechen Bai, Zheng Zhang, Ziteng Gao","submitted_at":"2024-09-29T07:47:15Z","abstract_excerpt":"We introduce VideoLISA, a video-based multimodal large language model designed to tackle the problem of language-instructed reasoning segmentation in videos. Leveraging the reasoning capabilities and world knowledge of large language models, and augmented by the Segment Anything Model, VideoLISA generates temporally consistent segmentation masks in videos based on language instructions. Existing image-based methods, such as LISA, struggle with video tasks due to the additional temporal dimension, which requires temporal dynamic understanding and consistent segmentation across frames. VideoLISA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19603","kind":"arxiv","version":1},"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/2409.19603/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":"2026-07-05T09:13:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XSq8AMVAiH7MrdwBNwvAq/9Q8BmeSJAxCEW28EaPOL+shQ3hnwMvxE9V9wWIFWboBKufkI3rBB/qkJXD+F0pDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:43:43.283038Z"},"content_sha256":"24d9071e19e8b97dd6bf87f6da6d693a3f88e46766bfe54102f83403da47c7af","schema_version":"1.0","event_id":"sha256:24d9071e19e8b97dd6bf87f6da6d693a3f88e46766bfe54102f83403da47c7af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LXCNSUADVJAJRLXK5J6S62ZMUJ/bundle.json","state_url":"https://pith.science/pith/LXCNSUADVJAJRLXK5J6S62ZMUJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LXCNSUADVJAJRLXK5J6S62ZMUJ/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":"2026-08-10T12:43:43Z","links":{"resolver":"https://pith.science/pith/LXCNSUADVJAJRLXK5J6S62ZMUJ","bundle":"https://pith.science/pith/LXCNSUADVJAJRLXK5J6S62ZMUJ/bundle.json","state":"https://pith.science/pith/LXCNSUADVJAJRLXK5J6S62ZMUJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LXCNSUADVJAJRLXK5J6S62ZMUJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LXCNSUADVJAJRLXK5J6S62ZMUJ","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":"6e4a42b077075b6a8980821237dfdde3b46618e1f1c08e44156511fd73635d25","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-29T07:47:15Z","title_canon_sha256":"e48db4c40573044ef94fa984fad27475bff5997c3aea8078f3df409cecc35b03"},"schema_version":"1.0","source":{"id":"2409.19603","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19603","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19603v1","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19603","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"LXCNSUADVJAJ","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"LXCNSUADVJAJRLXK","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"LXCNSUAD","created_at":"2026-07-05T09:13:18Z"}],"graph_snapshots":[{"event_id":"sha256:24d9071e19e8b97dd6bf87f6da6d693a3f88e46766bfe54102f83403da47c7af","target":"graph","created_at":"2026-07-05T09:13:18Z","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/2409.19603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce VideoLISA, a video-based multimodal large language model designed to tackle the problem of language-instructed reasoning segmentation in videos. Leveraging the reasoning capabilities and world knowledge of large language models, and augmented by the Segment Anything Model, VideoLISA generates temporally consistent segmentation masks in videos based on language instructions. Existing image-based methods, such as LISA, struggle with video tasks due to the additional temporal dimension, which requires temporal dynamic understanding and consistent segmentation across frames. VideoLISA","authors_text":"Haiyang Mei, Joya Chen, Lei Liu, Mike Zheng Shou, Pichao Wang, Tong He, Zechen Bai, Zheng Zhang, Ziteng Gao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-29T07:47:15Z","title":"One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19603","kind":"arxiv","version":1},"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:d032f8f87e0e3cbe6fa057c8e295e62aa34f2fc021489d620c458c85d55bfc0c","target":"record","created_at":"2026-07-05T09:13:18Z","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":"6e4a42b077075b6a8980821237dfdde3b46618e1f1c08e44156511fd73635d25","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-29T07:47:15Z","title_canon_sha256":"e48db4c40573044ef94fa984fad27475bff5997c3aea8078f3df409cecc35b03"},"schema_version":"1.0","source":{"id":"2409.19603","kind":"arxiv","version":1}},"canonical_sha256":"5dc4d95003aa4098aeeaea7d2f6b2ca26da2544bba9d430674b0e51436b9b535","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5dc4d95003aa4098aeeaea7d2f6b2ca26da2544bba9d430674b0e51436b9b535","first_computed_at":"2026-07-05T09:13:18.162625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:18.162625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zTUIP1Y720n4aPIanoFccMgwLBFQr9tS40KLUjNBNDqa0iYWjVb0HClbm4r4udawKpe5scM+hSQzsGUhGCefCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:18.162998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.19603","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d032f8f87e0e3cbe6fa057c8e295e62aa34f2fc021489d620c458c85d55bfc0c","sha256:24d9071e19e8b97dd6bf87f6da6d693a3f88e46766bfe54102f83403da47c7af"],"state_sha256":"90738b40ae7f3d97962a592f4e39d9eed9374bb8204b0dc38b5725e95b66ba37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RuSedFLmsnGZLCatyIX8/3gZkTX+fJXQqwOGUEU5Zu0bvJleFETPMfAM2LqZ57VAwyXpeVsw7KhoZ7wwqAVjCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:43:43.286246Z","bundle_sha256":"f3f87a16ecad479e9df79eb2a8ea20d9015434bc02a738eb4e11b832996e8ac8"}}