{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:F73VXBS5Q5LHK7SRPXJTS4IYTT","short_pith_number":"pith:F73VXBS5","schema_version":"1.0","canonical_sha256":"2ff75b865d8756757e517dd33971189ced229529cb0d674375bb0cbf59128eae","source":{"kind":"arxiv","id":"1604.01685","version":2},"attestation_state":"computed","paper":{"title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernt Schiele, Marius Cordts, Markus Enzweiler, Mohamed Omran, Rodrigo Benenson, Sebastian Ramos, Stefan Roth, Timo Rehfeld, Uwe Franke","submitted_at":"2016-04-06T16:34:33Z","abstract_excerpt":"Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban scene understanding, however, no current dataset adequately captures the complexity of real-world urban scenes.\n  To address this, we introduce Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling. Cityscapes is comprised of a large, diverse set of stereo video sequences recor"},"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":"1604.01685","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-06T16:34:33Z","cross_cats_sorted":[],"title_canon_sha256":"87424ca7e34431567bf84a27817c3b5589c97cdbdc19d0df3a602156fd77aeec","abstract_canon_sha256":"333edcee6a50130e2de284021fe08c4d98265dea6115faa1ccee3995a98546f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:32.202180Z","signature_b64":"/IJW704lQrU8yLpGHjHknYu/BF9/1WHF0Oh5dDAs4oJu3oaMrUCY00UL3OFgN6M5m0meSUt6XOCPVaHwZrLpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ff75b865d8756757e517dd33971189ced229529cb0d674375bb0cbf59128eae","last_reissued_at":"2026-05-18T01:17:32.201586Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:32.201586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernt Schiele, Marius Cordts, Markus Enzweiler, Mohamed Omran, Rodrigo Benenson, Sebastian Ramos, Stefan Roth, Timo Rehfeld, Uwe Franke","submitted_at":"2016-04-06T16:34:33Z","abstract_excerpt":"Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban scene understanding, however, no current dataset adequately captures the complexity of real-world urban scenes.\n  To address this, we introduce Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling. Cityscapes is comprised of a large, diverse set of stereo video sequences recor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.01685","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":""},"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":"1604.01685","created_at":"2026-05-18T01:17:32.201667+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.01685v2","created_at":"2026-05-18T01:17:32.201667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.01685","created_at":"2026-05-18T01:17:32.201667+00:00"},{"alias_kind":"pith_short_12","alias_value":"F73VXBS5Q5LH","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"F73VXBS5Q5LHK7SR","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"F73VXBS5","created_at":"2026-05-18T12:30:15.759754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.06876","citing_title":"Separable Convolutional LSTMs for Faster Video Segmentation","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06113","citing_title":"SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F73VXBS5Q5LHK7SRPXJTS4IYTT","json":"https://pith.science/pith/F73VXBS5Q5LHK7SRPXJTS4IYTT.json","graph_json":"https://pith.science/api/pith-number/F73VXBS5Q5LHK7SRPXJTS4IYTT/graph.json","events_json":"https://pith.science/api/pith-number/F73VXBS5Q5LHK7SRPXJTS4IYTT/events.json","paper":"https://pith.science/paper/F73VXBS5"},"agent_actions":{"view_html":"https://pith.science/pith/F73VXBS5Q5LHK7SRPXJTS4IYTT","download_json":"https://pith.science/pith/F73VXBS5Q5LHK7SRPXJTS4IYTT.json","view_paper":"https://pith.science/paper/F73VXBS5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.01685&json=true","fetch_graph":"https://pith.science/api/pith-number/F73VXBS5Q5LHK7SRPXJTS4IYTT/graph.json","fetch_events":"https://pith.science/api/pith-number/F73VXBS5Q5LHK7SRPXJTS4IYTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F73VXBS5Q5LHK7SRPXJTS4IYTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F73VXBS5Q5LHK7SRPXJTS4IYTT/action/storage_attestation","attest_author":"https://pith.science/pith/F73VXBS5Q5LHK7SRPXJTS4IYTT/action/author_attestation","sign_citation":"https://pith.science/pith/F73VXBS5Q5LHK7SRPXJTS4IYTT/action/citation_signature","submit_replication":"https://pith.science/pith/F73VXBS5Q5LHK7SRPXJTS4IYTT/action/replication_record"}},"created_at":"2026-05-18T01:17:32.201667+00:00","updated_at":"2026-05-18T01:17:32.201667+00:00"}