{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GKTF6JWBE53GMAFKCEYGZI3GYC","short_pith_number":"pith:GKTF6JWB","schema_version":"1.0","canonical_sha256":"32a65f26c127766600aa11306ca366c0badd05900daf1c8cd92c10b9f55f8355","source":{"kind":"arxiv","id":"2312.12433","version":3},"attestation_state":"computed","paper":{"title":"TAO-Amodal: A Benchmark for Tracking Any Object Amodally","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Achal Dave, Cheng-Yen Hsieh, Deva Ramanan, Kaihua Chen, Tarasha Khurana","submitted_at":"2023-12-19T18:58:40Z","abstract_excerpt":"Amodal perception, the ability to comprehend complete object structures from partial visibility, is a fundamental skill, even for infants. Its significance extends to applications like autonomous driving, where a clear understanding of heavily occluded objects is essential. However, modern detection and tracking algorithms often overlook this critical capability, perhaps due to the prevalence of \\textit{modal} annotations in most benchmarks. To address the scarcity of amodal benchmarks, we introduce TAO-Amodal, featuring 833 diverse categories in thousands of video sequences. Our dataset inclu"},"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":"2312.12433","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T18:58:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2b7c63cc797bec4d0abf5ca25c08b019a478b3cbc3e134d29c7e18e46f87e30a","abstract_canon_sha256":"3d5c7405c7981303ded24c784d85092aa4723acd477c99add744dbb85f8963dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:46.986583Z","signature_b64":"ONmJcXcyQ6Kz6WzSY31aeg5X+e3zGI1EHYHnm9zGithobpURXX7xCGy06HVmRVk95nTOmd0Bqjg1nRWo3J3IAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32a65f26c127766600aa11306ca366c0badd05900daf1c8cd92c10b9f55f8355","last_reissued_at":"2026-07-05T08:03:46.986109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:46.986109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TAO-Amodal: A Benchmark for Tracking Any Object Amodally","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Achal Dave, Cheng-Yen Hsieh, Deva Ramanan, Kaihua Chen, Tarasha Khurana","submitted_at":"2023-12-19T18:58:40Z","abstract_excerpt":"Amodal perception, the ability to comprehend complete object structures from partial visibility, is a fundamental skill, even for infants. Its significance extends to applications like autonomous driving, where a clear understanding of heavily occluded objects is essential. However, modern detection and tracking algorithms often overlook this critical capability, perhaps due to the prevalence of \\textit{modal} annotations in most benchmarks. To address the scarcity of amodal benchmarks, we introduce TAO-Amodal, featuring 833 diverse categories in thousands of video sequences. Our dataset inclu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12433","kind":"arxiv","version":3},"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/2312.12433/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":"2312.12433","created_at":"2026-07-05T08:03:46.986167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.12433v3","created_at":"2026-07-05T08:03:46.986167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12433","created_at":"2026-07-05T08:03:46.986167+00:00"},{"alias_kind":"pith_short_12","alias_value":"GKTF6JWBE53G","created_at":"2026-07-05T08:03:46.986167+00:00"},{"alias_kind":"pith_short_16","alias_value":"GKTF6JWBE53GMAFK","created_at":"2026-07-05T08:03:46.986167+00:00"},{"alias_kind":"pith_short_8","alias_value":"GKTF6JWB","created_at":"2026-07-05T08:03:46.986167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.13633","citing_title":"EGM: Efficient Visual Grounding Language Models","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GKTF6JWBE53GMAFKCEYGZI3GYC","json":"https://pith.science/pith/GKTF6JWBE53GMAFKCEYGZI3GYC.json","graph_json":"https://pith.science/api/pith-number/GKTF6JWBE53GMAFKCEYGZI3GYC/graph.json","events_json":"https://pith.science/api/pith-number/GKTF6JWBE53GMAFKCEYGZI3GYC/events.json","paper":"https://pith.science/paper/GKTF6JWB"},"agent_actions":{"view_html":"https://pith.science/pith/GKTF6JWBE53GMAFKCEYGZI3GYC","download_json":"https://pith.science/pith/GKTF6JWBE53GMAFKCEYGZI3GYC.json","view_paper":"https://pith.science/paper/GKTF6JWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.12433&json=true","fetch_graph":"https://pith.science/api/pith-number/GKTF6JWBE53GMAFKCEYGZI3GYC/graph.json","fetch_events":"https://pith.science/api/pith-number/GKTF6JWBE53GMAFKCEYGZI3GYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GKTF6JWBE53GMAFKCEYGZI3GYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GKTF6JWBE53GMAFKCEYGZI3GYC/action/storage_attestation","attest_author":"https://pith.science/pith/GKTF6JWBE53GMAFKCEYGZI3GYC/action/author_attestation","sign_citation":"https://pith.science/pith/GKTF6JWBE53GMAFKCEYGZI3GYC/action/citation_signature","submit_replication":"https://pith.science/pith/GKTF6JWBE53GMAFKCEYGZI3GYC/action/replication_record"}},"created_at":"2026-07-05T08:03:46.986167+00:00","updated_at":"2026-07-05T08:03:46.986167+00:00"}