{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N2SLL5C3SDN3KUMFIXUPVUDYRJ","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":"ea6374a6f2b77f348c6d4a5499f78d7d21e1b56b9be2f92e72f07a769285b48c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T18:58:04Z","title_canon_sha256":"259ffc2f8ecea1e9820c5d413daefe580b7ba7860de4208420e49a9b10266414"},"schema_version":"1.0","source":{"id":"2501.08326","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08326","created_at":"2026-07-05T10:37:42Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08326v2","created_at":"2026-07-05T10:37:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08326","created_at":"2026-07-05T10:37:42Z"},{"alias_kind":"pith_short_12","alias_value":"N2SLL5C3SDN3","created_at":"2026-07-05T10:37:42Z"},{"alias_kind":"pith_short_16","alias_value":"N2SLL5C3SDN3KUMF","created_at":"2026-07-05T10:37:42Z"},{"alias_kind":"pith_short_8","alias_value":"N2SLL5C3","created_at":"2026-07-05T10:37:42Z"}],"graph_snapshots":[{"event_id":"sha256:f5bb6b7111350daac3cfa6b4beb8c9980df1a7bea742da6c4b7b584c9ca01020","target":"graph","created_at":"2026-07-05T10:37:42Z","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/2501.08326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Omni-RGPT, a multimodal large language model designed to facilitate region-level comprehension for both images and videos. To achieve consistent region representation across spatio-temporal dimensions, we introduce Token Mark, a set of tokens highlighting the target regions within the visual feature space. These tokens are directly embedded into spatial regions using region prompts (e.g., boxes or masks) and simultaneously incorporated into the text prompt to specify the target, establishing a direct connection between visual and text tokens. To further support robust video understa","authors_text":"De-An Huang, Min-Hung Chen, Miran Heo, Ryo Hachiuma, Seon Joo Kim, Sifei Liu, Subhashree Radhakrishnan, Yu-Chiang Frank Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T18:58:04Z","title":"Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08326","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:a8b21f0d9901a53b4f24f62e18e695367373a6dcad5c9ca12cfd05f062ee7ea6","target":"record","created_at":"2026-07-05T10:37:42Z","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":"ea6374a6f2b77f348c6d4a5499f78d7d21e1b56b9be2f92e72f07a769285b48c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T18:58:04Z","title_canon_sha256":"259ffc2f8ecea1e9820c5d413daefe580b7ba7860de4208420e49a9b10266414"},"schema_version":"1.0","source":{"id":"2501.08326","kind":"arxiv","version":2}},"canonical_sha256":"6ea4b5f45b90dbb5518545e8fad0788a4c23ff54d1c30a7276c988eda8160c09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ea4b5f45b90dbb5518545e8fad0788a4c23ff54d1c30a7276c988eda8160c09","first_computed_at":"2026-07-05T10:37:42.686512Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:42.686512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OAfFPsvqAo0yyA+s2zjyD37YCotLBK1FTHuQsnDFBKp5PTr9OcIkAFiRwF8056xIR7N+bgVx1cj2C6JJYdOLCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:42.687097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.08326","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8b21f0d9901a53b4f24f62e18e695367373a6dcad5c9ca12cfd05f062ee7ea6","sha256:f5bb6b7111350daac3cfa6b4beb8c9980df1a7bea742da6c4b7b584c9ca01020"],"state_sha256":"7a8af0af45099124c47d5896c66738286c130a2d1c6f59fb5597ffd615c742fa"}