{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YJXPG64OO4FWWAUIFO7WU7IBYK","short_pith_number":"pith:YJXPG64O","schema_version":"1.0","canonical_sha256":"c26ef37b8e770b6b02882bbf6a7d01c2a345a4b45314f9260f833a206ef445c3","source":{"kind":"arxiv","id":"2411.16156","version":2},"attestation_state":"computed","paper":{"title":"VideoOrion: Tokenizing Object Dynamics in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Luo, Sipeng Zheng, Wanpeng Zhang, Yicheng Feng, Yijiang Li, Zihao Yue, Zongqing Lu","submitted_at":"2024-11-25T07:32:02Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.16156","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T07:32:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9c796c10203d65aa3b9c56bb0b2200ef77093f039ab2f564c7e4c4078632c7d5","abstract_canon_sha256":"a5f5540d89a58fb45e006625990c3d82f2ca6bce57e0d390e757bae0b2f181a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:40.058450Z","signature_b64":"nbGezcGJYsZGSuGnNoIguUEtZQZQE/1xPksvJc3hwBdgHiIDMq3qhcWoN2+hSNFeO3gy+RLcWi+9n6rgV4xDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c26ef37b8e770b6b02882bbf6a7d01c2a345a4b45314f9260f833a206ef445c3","last_reissued_at":"2026-07-05T10:33:40.057942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:40.057942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoOrion: Tokenizing Object Dynamics in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Luo, Sipeng Zheng, Wanpeng Zhang, Yicheng Feng, Yijiang Li, Zihao Yue, Zongqing Lu","submitted_at":"2024-11-25T07:32:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16156","kind":"arxiv","version":2},"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/2411.16156/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.16156","created_at":"2026-07-05T10:33:40.058006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16156v2","created_at":"2026-07-05T10:33:40.058006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16156","created_at":"2026-07-05T10:33:40.058006+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJXPG64OO4FW","created_at":"2026-07-05T10:33:40.058006+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJXPG64OO4FWWAUI","created_at":"2026-07-05T10:33:40.058006+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJXPG64O","created_at":"2026-07-05T10:33:40.058006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15597","citing_title":"Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJXPG64OO4FWWAUIFO7WU7IBYK","json":"https://pith.science/pith/YJXPG64OO4FWWAUIFO7WU7IBYK.json","graph_json":"https://pith.science/api/pith-number/YJXPG64OO4FWWAUIFO7WU7IBYK/graph.json","events_json":"https://pith.science/api/pith-number/YJXPG64OO4FWWAUIFO7WU7IBYK/events.json","paper":"https://pith.science/paper/YJXPG64O"},"agent_actions":{"view_html":"https://pith.science/pith/YJXPG64OO4FWWAUIFO7WU7IBYK","download_json":"https://pith.science/pith/YJXPG64OO4FWWAUIFO7WU7IBYK.json","view_paper":"https://pith.science/paper/YJXPG64O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16156&json=true","fetch_graph":"https://pith.science/api/pith-number/YJXPG64OO4FWWAUIFO7WU7IBYK/graph.json","fetch_events":"https://pith.science/api/pith-number/YJXPG64OO4FWWAUIFO7WU7IBYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJXPG64OO4FWWAUIFO7WU7IBYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJXPG64OO4FWWAUIFO7WU7IBYK/action/storage_attestation","attest_author":"https://pith.science/pith/YJXPG64OO4FWWAUIFO7WU7IBYK/action/author_attestation","sign_citation":"https://pith.science/pith/YJXPG64OO4FWWAUIFO7WU7IBYK/action/citation_signature","submit_replication":"https://pith.science/pith/YJXPG64OO4FWWAUIFO7WU7IBYK/action/replication_record"}},"created_at":"2026-07-05T10:33:40.058006+00:00","updated_at":"2026-07-05T10:33:40.058006+00:00"}