{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VVDAJS2QTRGF3UYVKISKQFXAYN","short_pith_number":"pith:VVDAJS2Q","schema_version":"1.0","canonical_sha256":"ad4604cb509c4c5dd3155224a816e0c3692df556a1155afac08c53b5c9a251ca","source":{"kind":"arxiv","id":"2607.19743","version":1},"attestation_state":"computed","paper":{"title":"Efficient Tracking and Understanding Object Transformations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Yihong Sun","submitted_at":"2026-07-22T04:28:38Z","abstract_excerpt":"Tracking objects through state transformations is essential for understanding real-world dynamics. However, existing methods are computationally expensive. TubeletGraph recently showed impressive capabilities, but its inference cost (~$4.4$ seconds per object-frame on VOST) precludes any real-time deployment possibilities. We observe that TubeletGraph's overhead arises from building a spatiotemporal partition of the input video: (1) entity segmentation is computed densely for every frame regardless of whether a transformation occurs, and (2) every entity in the scene is tracked, scaling cost w"},"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":"2607.19743","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-22T04:28:38Z","cross_cats_sorted":[],"title_canon_sha256":"e4953de3096dddc124a61a79a60b270fe4e19a338993e026ff5e0c6fa61fde59","abstract_canon_sha256":"3097537a38627a089ba9fbc6ad0929ce05bbc1f1d5d1476a9d48bcf1fec98a2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T00:24:06.822570Z","signature_b64":"b/0v43c2UnE5JRnK/ldoJi8BfdqKOApY2/mT41+YkDq/JuKBFViWZeMIpK13PhZYkcPcd5zBQpEoEQWaP9nUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad4604cb509c4c5dd3155224a816e0c3692df556a1155afac08c53b5c9a251ca","last_reissued_at":"2026-07-23T00:24:06.821740Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T00:24:06.821740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Tracking and Understanding Object Transformations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Yihong Sun","submitted_at":"2026-07-22T04:28:38Z","abstract_excerpt":"Tracking objects through state transformations is essential for understanding real-world dynamics. However, existing methods are computationally expensive. TubeletGraph recently showed impressive capabilities, but its inference cost (~$4.4$ seconds per object-frame on VOST) precludes any real-time deployment possibilities. We observe that TubeletGraph's overhead arises from building a spatiotemporal partition of the input video: (1) entity segmentation is computed densely for every frame regardless of whether a transformation occurs, and (2) every entity in the scene is tracked, scaling cost w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19743","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/2607.19743/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":"2607.19743","created_at":"2026-07-23T00:24:06.822167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.19743v1","created_at":"2026-07-23T00:24:06.822167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19743","created_at":"2026-07-23T00:24:06.822167+00:00"},{"alias_kind":"pith_short_12","alias_value":"VVDAJS2QTRGF","created_at":"2026-07-23T00:24:06.822167+00:00"},{"alias_kind":"pith_short_16","alias_value":"VVDAJS2QTRGF3UYV","created_at":"2026-07-23T00:24:06.822167+00:00"},{"alias_kind":"pith_short_8","alias_value":"VVDAJS2Q","created_at":"2026-07-23T00:24:06.822167+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/VVDAJS2QTRGF3UYVKISKQFXAYN","json":"https://pith.science/pith/VVDAJS2QTRGF3UYVKISKQFXAYN.json","graph_json":"https://pith.science/api/pith-number/VVDAJS2QTRGF3UYVKISKQFXAYN/graph.json","events_json":"https://pith.science/api/pith-number/VVDAJS2QTRGF3UYVKISKQFXAYN/events.json","paper":"https://pith.science/paper/VVDAJS2Q"},"agent_actions":{"view_html":"https://pith.science/pith/VVDAJS2QTRGF3UYVKISKQFXAYN","download_json":"https://pith.science/pith/VVDAJS2QTRGF3UYVKISKQFXAYN.json","view_paper":"https://pith.science/paper/VVDAJS2Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.19743&json=true","fetch_graph":"https://pith.science/api/pith-number/VVDAJS2QTRGF3UYVKISKQFXAYN/graph.json","fetch_events":"https://pith.science/api/pith-number/VVDAJS2QTRGF3UYVKISKQFXAYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VVDAJS2QTRGF3UYVKISKQFXAYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VVDAJS2QTRGF3UYVKISKQFXAYN/action/storage_attestation","attest_author":"https://pith.science/pith/VVDAJS2QTRGF3UYVKISKQFXAYN/action/author_attestation","sign_citation":"https://pith.science/pith/VVDAJS2QTRGF3UYVKISKQFXAYN/action/citation_signature","submit_replication":"https://pith.science/pith/VVDAJS2QTRGF3UYVKISKQFXAYN/action/replication_record"}},"created_at":"2026-07-23T00:24:06.822167+00:00","updated_at":"2026-07-23T00:24:06.822167+00:00"}