{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GXGQEREABZLHQ2OKRN3EQCZIXV","short_pith_number":"pith:GXGQEREA","schema_version":"1.0","canonical_sha256":"35cd0244800e567869ca8b76480b28bd401f90991a2c5c672c44f58b1418caab","source":{"kind":"arxiv","id":"2407.17085","version":1},"attestation_state":"computed","paper":{"title":"OVR: A Dataset for Open Vocabulary Temporal Repetition Counting in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Debidatta Dwibedi, Jonathan Tompson, Yusuf Aytar","submitted_at":"2024-07-24T08:22:49Z","abstract_excerpt":"We introduce a dataset of annotations of temporal repetitions in videos. The dataset, OVR (pronounced as over), contains annotations for over 72K videos, with each annotation specifying the number of repetitions, the start and end time of the repetitions, and also a free-form description of what is repeating. The annotations are provided for videos sourced from Kinetics and Ego4D, and consequently cover both Exo and Ego viewing conditions, with a huge variety of actions and activities. Moreover, OVR is almost an order of magnitude larger than previous datasets for video repetition. We also pro"},"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":"2407.17085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-24T08:22:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"745f274740663a1bbd78ad0694d195eb8853d22262699433e92fe718180a8d71","abstract_canon_sha256":"a60b5818faf358cee4086d8bf351e24cff8303d7a4b6f92f89405bbe3c19179a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:01.936783Z","signature_b64":"+10S2jHtU780+WN58+KEBOR15Y75J0/I1JCK1tTyvk8YCmJfMnrbJwBPjdwdk3QkEXt/q2RROerpyMa4hp1HAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35cd0244800e567869ca8b76480b28bd401f90991a2c5c672c44f58b1418caab","last_reissued_at":"2026-07-05T08:48:01.936360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:01.936360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OVR: A Dataset for Open Vocabulary Temporal Repetition Counting in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Debidatta Dwibedi, Jonathan Tompson, Yusuf Aytar","submitted_at":"2024-07-24T08:22:49Z","abstract_excerpt":"We introduce a dataset of annotations of temporal repetitions in videos. The dataset, OVR (pronounced as over), contains annotations for over 72K videos, with each annotation specifying the number of repetitions, the start and end time of the repetitions, and also a free-form description of what is repeating. The annotations are provided for videos sourced from Kinetics and Ego4D, and consequently cover both Exo and Ego viewing conditions, with a huge variety of actions and activities. Moreover, OVR is almost an order of magnitude larger than previous datasets for video repetition. We also pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17085","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/2407.17085/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":"2407.17085","created_at":"2026-07-05T08:48:01.936424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.17085v1","created_at":"2026-07-05T08:48:01.936424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17085","created_at":"2026-07-05T08:48:01.936424+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXGQEREABZLH","created_at":"2026-07-05T08:48:01.936424+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXGQEREABZLHQ2OK","created_at":"2026-07-05T08:48:01.936424+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXGQEREA","created_at":"2026-07-05T08:48:01.936424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23045","citing_title":"The TIME Machine: On The Power of Motion for Efficient Perception","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23407","citing_title":"PushupBench: Your VLM is not good at counting pushups","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GXGQEREABZLHQ2OKRN3EQCZIXV","json":"https://pith.science/pith/GXGQEREABZLHQ2OKRN3EQCZIXV.json","graph_json":"https://pith.science/api/pith-number/GXGQEREABZLHQ2OKRN3EQCZIXV/graph.json","events_json":"https://pith.science/api/pith-number/GXGQEREABZLHQ2OKRN3EQCZIXV/events.json","paper":"https://pith.science/paper/GXGQEREA"},"agent_actions":{"view_html":"https://pith.science/pith/GXGQEREABZLHQ2OKRN3EQCZIXV","download_json":"https://pith.science/pith/GXGQEREABZLHQ2OKRN3EQCZIXV.json","view_paper":"https://pith.science/paper/GXGQEREA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.17085&json=true","fetch_graph":"https://pith.science/api/pith-number/GXGQEREABZLHQ2OKRN3EQCZIXV/graph.json","fetch_events":"https://pith.science/api/pith-number/GXGQEREABZLHQ2OKRN3EQCZIXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXGQEREABZLHQ2OKRN3EQCZIXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXGQEREABZLHQ2OKRN3EQCZIXV/action/storage_attestation","attest_author":"https://pith.science/pith/GXGQEREABZLHQ2OKRN3EQCZIXV/action/author_attestation","sign_citation":"https://pith.science/pith/GXGQEREABZLHQ2OKRN3EQCZIXV/action/citation_signature","submit_replication":"https://pith.science/pith/GXGQEREABZLHQ2OKRN3EQCZIXV/action/replication_record"}},"created_at":"2026-07-05T08:48:01.936424+00:00","updated_at":"2026-07-05T08:48:01.936424+00:00"}