{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YJXPG64OO4FWWAUIFO7WU7IBYK","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":"a5f5540d89a58fb45e006625990c3d82f2ca6bce57e0d390e757bae0b2f181a6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T07:32:02Z","title_canon_sha256":"9c796c10203d65aa3b9c56bb0b2200ef77093f039ab2f564c7e4c4078632c7d5"},"schema_version":"1.0","source":{"id":"2411.16156","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16156","created_at":"2026-07-05T10:33:40Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16156v2","created_at":"2026-07-05T10:33:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16156","created_at":"2026-07-05T10:33:40Z"},{"alias_kind":"pith_short_12","alias_value":"YJXPG64OO4FW","created_at":"2026-07-05T10:33:40Z"},{"alias_kind":"pith_short_16","alias_value":"YJXPG64OO4FWWAUI","created_at":"2026-07-05T10:33:40Z"},{"alias_kind":"pith_short_8","alias_value":"YJXPG64O","created_at":"2026-07-05T10:33:40Z"}],"graph_snapshots":[{"event_id":"sha256:de7772e457440558b381c0a94907468576327f52d14aa018848fc2cafafa0e6d","target":"graph","created_at":"2026-07-05T10:33:40Z","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/2411.16156/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present VideoOrion, a Video Large Language Model (Video-LLM) that explicitly captures the key semantic information in videos - the spatial-temporal dynamics of objects throughout the videos. VideoOrion employs expert vision models to extract object dynamics through a detect-segment-track pipeline, encoding them into a set of object tokens by aggregating spatial-temporal object features. Our method addresses the persistent challenge in Video-LLMs of efficiently compressing high-dimensional video data into semantic tokens that are comprehensible to LLMs. Compared to prior methods which resort","authors_text":"Hao Luo, Sipeng Zheng, Wanpeng Zhang, Yicheng Feng, Yijiang Li, Zihao Yue, Zongqing Lu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T07:32:02Z","title":"VideoOrion: Tokenizing Object Dynamics in Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16156","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:b25c3033d0e908312fdddaed06d5b776da3109bab4aa5f85efefa7f0acbecfcf","target":"record","created_at":"2026-07-05T10:33:40Z","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":"a5f5540d89a58fb45e006625990c3d82f2ca6bce57e0d390e757bae0b2f181a6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T07:32:02Z","title_canon_sha256":"9c796c10203d65aa3b9c56bb0b2200ef77093f039ab2f564c7e4c4078632c7d5"},"schema_version":"1.0","source":{"id":"2411.16156","kind":"arxiv","version":2}},"canonical_sha256":"c26ef37b8e770b6b02882bbf6a7d01c2a345a4b45314f9260f833a206ef445c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c26ef37b8e770b6b02882bbf6a7d01c2a345a4b45314f9260f833a206ef445c3","first_computed_at":"2026-07-05T10:33:40.057942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:40.057942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nbGezcGJYsZGSuGnNoIguUEtZQZQE/1xPksvJc3hwBdgHiIDMq3qhcWoN2+hSNFeO3gy+RLcWi+9n6rgV4xDCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:40.058450Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.16156","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b25c3033d0e908312fdddaed06d5b776da3109bab4aa5f85efefa7f0acbecfcf","sha256:de7772e457440558b381c0a94907468576327f52d14aa018848fc2cafafa0e6d"],"state_sha256":"c85eba360c04384bbc70204beb2ebe0c14fd663debfc33ce60c7f2fb00d29eae"}