{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6NM4TN6Q7G2DLGPR2L4IU77CF7","short_pith_number":"pith:6NM4TN6Q","schema_version":"1.0","canonical_sha256":"f359c9b7d0f9b43599f1d2f88a7fe22fdd78a91588b394659c39ed4d55f2045e","source":{"kind":"arxiv","id":"2102.11859","version":2},"attestation_state":"computed","paper":{"title":"STEP: Segmenting and Tracking Every Pixel","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aljo\\v{s}a O\\v{s}ep, Andreas Geiger, Bastian Leibe, Bradley Green, Daniel Cremers, Hartwig Adam, Jun Xie, Laura Leal-Taix\\'e, Liang-Chieh Chen, Mark Weber, Maxwell Collins, Paul Voigtlaender, Yukun Zhu","submitted_at":"2021-02-23T18:43:02Z","abstract_excerpt":"The task of assigning semantic classes and track identities to every pixel in a video is called video panoptic segmentation. Our work is the first that targets this task in a real-world setting requiring dense interpretation in both spatial and temporal domains. As the ground-truth for this task is difficult and expensive to obtain, existing datasets are either constructed synthetically or only sparsely annotated within short video clips. To overcome this, we introduce a new benchmark encompassing two datasets, KITTI-STEP, and MOTChallenge-STEP. The datasets contain long video sequences, provi"},"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":"2102.11859","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-23T18:43:02Z","cross_cats_sorted":[],"title_canon_sha256":"27e4a29cacc6eb53849c1802fbbeed1806bc1868b543d1f85725abba08664565","abstract_canon_sha256":"65c676caaa70b945af4f61c1c35c34b627a12c7fefcaef58251c59f2727e93d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:15.948883Z","signature_b64":"15P0LGcnU1YtmTFlQcuXnK2dTRrKO6l8udyh4ml9i7oKv+BJ0VLDcXshHrHHfimwZmpJfSTh92ASJpXf2v79Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f359c9b7d0f9b43599f1d2f88a7fe22fdd78a91588b394659c39ed4d55f2045e","last_reissued_at":"2026-07-05T03:38:15.948371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:15.948371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STEP: Segmenting and Tracking Every Pixel","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aljo\\v{s}a O\\v{s}ep, Andreas Geiger, Bastian Leibe, Bradley Green, Daniel Cremers, Hartwig Adam, Jun Xie, Laura Leal-Taix\\'e, Liang-Chieh Chen, Mark Weber, Maxwell Collins, Paul Voigtlaender, Yukun Zhu","submitted_at":"2021-02-23T18:43:02Z","abstract_excerpt":"The task of assigning semantic classes and track identities to every pixel in a video is called video panoptic segmentation. Our work is the first that targets this task in a real-world setting requiring dense interpretation in both spatial and temporal domains. As the ground-truth for this task is difficult and expensive to obtain, existing datasets are either constructed synthetically or only sparsely annotated within short video clips. To overcome this, we introduce a new benchmark encompassing two datasets, KITTI-STEP, and MOTChallenge-STEP. The datasets contain long video sequences, provi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.11859","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/2102.11859/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":"2102.11859","created_at":"2026-07-05T03:38:15.948442+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.11859v2","created_at":"2026-07-05T03:38:15.948442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.11859","created_at":"2026-07-05T03:38:15.948442+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NM4TN6Q7G2D","created_at":"2026-07-05T03:38:15.948442+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NM4TN6Q7G2DLGPR","created_at":"2026-07-05T03:38:15.948442+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NM4TN6Q","created_at":"2026-07-05T03:38:15.948442+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26515","citing_title":"Forget, Anticipate and Adapt: Test Time Training for Long Videos","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26515","citing_title":"Forget, Anticipate and Adapt: Test Time Training for Long Videos","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2602.05414","citing_title":"TSBOW -- Traffic Surveillance Benchmark for Occluded Vehicles Under Various Weather Conditions","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2602.05414","citing_title":"TSBOW -- Traffic Surveillance Benchmark for Occluded Vehicles Under Various Weather Conditions","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NM4TN6Q7G2DLGPR2L4IU77CF7","json":"https://pith.science/pith/6NM4TN6Q7G2DLGPR2L4IU77CF7.json","graph_json":"https://pith.science/api/pith-number/6NM4TN6Q7G2DLGPR2L4IU77CF7/graph.json","events_json":"https://pith.science/api/pith-number/6NM4TN6Q7G2DLGPR2L4IU77CF7/events.json","paper":"https://pith.science/paper/6NM4TN6Q"},"agent_actions":{"view_html":"https://pith.science/pith/6NM4TN6Q7G2DLGPR2L4IU77CF7","download_json":"https://pith.science/pith/6NM4TN6Q7G2DLGPR2L4IU77CF7.json","view_paper":"https://pith.science/paper/6NM4TN6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.11859&json=true","fetch_graph":"https://pith.science/api/pith-number/6NM4TN6Q7G2DLGPR2L4IU77CF7/graph.json","fetch_events":"https://pith.science/api/pith-number/6NM4TN6Q7G2DLGPR2L4IU77CF7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NM4TN6Q7G2DLGPR2L4IU77CF7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NM4TN6Q7G2DLGPR2L4IU77CF7/action/storage_attestation","attest_author":"https://pith.science/pith/6NM4TN6Q7G2DLGPR2L4IU77CF7/action/author_attestation","sign_citation":"https://pith.science/pith/6NM4TN6Q7G2DLGPR2L4IU77CF7/action/citation_signature","submit_replication":"https://pith.science/pith/6NM4TN6Q7G2DLGPR2L4IU77CF7/action/replication_record"}},"created_at":"2026-07-05T03:38:15.948442+00:00","updated_at":"2026-07-05T03:38:15.948442+00:00"}