{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P7J2XQ2MPABXZ4VUTBWI3UKHJ5","short_pith_number":"pith:P7J2XQ2M","schema_version":"1.0","canonical_sha256":"7fd3abc34c78037cf2b4986c8dd1474f7e4abdd37a0b1e3a2a7d9e8ab842cae9","source":{"kind":"arxiv","id":"2608.10932","version":1},"attestation_state":"computed","paper":{"title":"Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bohai Gu, Dazhao Du, Eric Liu, Hualuo Liu, Jian Liu, Shiyan Du, Song Guo, Tao Han, Xi Chen, Yongjian Yu, Yujia Zhang","submitted_at":"2026-08-11T14:00:02Z","abstract_excerpt":"Understanding camera motion is fundamental to video perception, with applications in spatial intelligence and controllable video generation. Multimodal large language models (MLLMs) provide a natural interface for this task, but existing work typically assigns one or more labels to an entire clip. Such clip-level recognition overlooks two defining properties of real camera motion: it can change within a shot, and multiple movements can occur simultaneously. We therefore formulate camera-motion understanding as temporally grounded, compositional recognition, which requires a model to localize m"},"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":"2608.10932","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T14:00:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b19a8ec7e73a60d38a97ecbae5192f870def663e17d6be14aa8a985f632fd5d4","abstract_canon_sha256":"649be3b6681745db8ecfce477b3760837857b1a3d6a6c1dd3eb8ecbc7ab4c510"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:23:50.872424Z","signature_b64":"FCqIcWntUFswUlv9XuP5g/gAHt+Sf6jG/4nXuQUX4DpYj2sAiaT23rmq/hdSNSx0V05xGrpgHdrk1hm886vPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fd3abc34c78037cf2b4986c8dd1474f7e4abdd37a0b1e3a2a7d9e8ab842cae9","last_reissued_at":"2026-08-12T01:23:50.870776Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:23:50.870776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bohai Gu, Dazhao Du, Eric Liu, Hualuo Liu, Jian Liu, Shiyan Du, Song Guo, Tao Han, Xi Chen, Yongjian Yu, Yujia Zhang","submitted_at":"2026-08-11T14:00:02Z","abstract_excerpt":"Understanding camera motion is fundamental to video perception, with applications in spatial intelligence and controllable video generation. Multimodal large language models (MLLMs) provide a natural interface for this task, but existing work typically assigns one or more labels to an entire clip. Such clip-level recognition overlooks two defining properties of real camera motion: it can change within a shot, and multiple movements can occur simultaneously. We therefore formulate camera-motion understanding as temporally grounded, compositional recognition, which requires a model to localize m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10932","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/2608.10932/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":"2608.10932","created_at":"2026-08-12T01:23:50.874587+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.10932v1","created_at":"2026-08-12T01:23:50.874587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10932","created_at":"2026-08-12T01:23:50.874587+00:00"},{"alias_kind":"pith_short_12","alias_value":"P7J2XQ2MPABX","created_at":"2026-08-12T01:23:50.874587+00:00"},{"alias_kind":"pith_short_16","alias_value":"P7J2XQ2MPABXZ4VU","created_at":"2026-08-12T01:23:50.874587+00:00"},{"alias_kind":"pith_short_8","alias_value":"P7J2XQ2M","created_at":"2026-08-12T01:23:50.874587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P7J2XQ2MPABXZ4VUTBWI3UKHJ5","json":"https://pith.science/pith/P7J2XQ2MPABXZ4VUTBWI3UKHJ5.json","graph_json":"https://pith.science/api/pith-number/P7J2XQ2MPABXZ4VUTBWI3UKHJ5/graph.json","events_json":"https://pith.science/api/pith-number/P7J2XQ2MPABXZ4VUTBWI3UKHJ5/events.json","paper":"https://pith.science/paper/P7J2XQ2M"},"agent_actions":{"view_html":"https://pith.science/pith/P7J2XQ2MPABXZ4VUTBWI3UKHJ5","download_json":"https://pith.science/pith/P7J2XQ2MPABXZ4VUTBWI3UKHJ5.json","view_paper":"https://pith.science/paper/P7J2XQ2M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.10932&json=true","fetch_graph":"https://pith.science/api/pith-number/P7J2XQ2MPABXZ4VUTBWI3UKHJ5/graph.json","fetch_events":"https://pith.science/api/pith-number/P7J2XQ2MPABXZ4VUTBWI3UKHJ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P7J2XQ2MPABXZ4VUTBWI3UKHJ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P7J2XQ2MPABXZ4VUTBWI3UKHJ5/action/storage_attestation","attest_author":"https://pith.science/pith/P7J2XQ2MPABXZ4VUTBWI3UKHJ5/action/author_attestation","sign_citation":"https://pith.science/pith/P7J2XQ2MPABXZ4VUTBWI3UKHJ5/action/citation_signature","submit_replication":"https://pith.science/pith/P7J2XQ2MPABXZ4VUTBWI3UKHJ5/action/replication_record"}},"created_at":"2026-08-12T01:23:50.874587+00:00","updated_at":"2026-08-12T01:23:50.874587+00:00"}