{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2OQDFCA7VBOZSLAUSSRRQQIKMY","short_pith_number":"pith:2OQDFCA7","schema_version":"1.0","canonical_sha256":"d3a032881fa85d992c1494a318410a663bee6a1c9125508682967c0138c075ea","source":{"kind":"arxiv","id":"2103.13413","version":1},"attestation_state":"computed","paper":{"title":"Vision Transformers for Dense Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexey Bochkovskiy, Ren\\'e Ranftl, Vladlen Koltun","submitted_at":"2021-03-24T18:01:17Z","abstract_excerpt":"We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. We assemble tokens from various stages of the vision transformer into image-like representations at various resolutions and progressively combine them into full-resolution predictions using a convolutional decoder. The transformer backbone processes representations at a constant and relatively high resolution and has a global receptive field at every stage. These properties allow the dense vision transformer to provide finer-gra"},"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":"2103.13413","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-24T18:01:17Z","cross_cats_sorted":[],"title_canon_sha256":"c0fd378cc0bb6bb23350591c9ff440d2b5bfade7aa1a54e107bdb6d0aab38fe8","abstract_canon_sha256":"9dad57c61584a1eb58cc4338774597c9d0b028f0aaa6b60f446e9239747d80dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:18.991129Z","signature_b64":"BTAWuGHtYxHL4FINXYC2euHl0YmnqshYuABqCSADYLRt2eNbozv0hNfPeS7xZ9wcuO/91XFkZXD3zx0SYK0nAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3a032881fa85d992c1494a318410a663bee6a1c9125508682967c0138c075ea","last_reissued_at":"2026-07-05T02:26:18.990787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:18.990787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision Transformers for Dense Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexey Bochkovskiy, Ren\\'e Ranftl, Vladlen Koltun","submitted_at":"2021-03-24T18:01:17Z","abstract_excerpt":"We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. We assemble tokens from various stages of the vision transformer into image-like representations at various resolutions and progressively combine them into full-resolution predictions using a convolutional decoder. The transformer backbone processes representations at a constant and relatively high resolution and has a global receptive field at every stage. These properties allow the dense vision transformer to provide finer-gra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13413","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/2103.13413/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":"2103.13413","created_at":"2026-07-05T02:26:18.990844+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.13413v1","created_at":"2026-07-05T02:26:18.990844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13413","created_at":"2026-07-05T02:26:18.990844+00:00"},{"alias_kind":"pith_short_12","alias_value":"2OQDFCA7VBOZ","created_at":"2026-07-05T02:26:18.990844+00:00"},{"alias_kind":"pith_short_16","alias_value":"2OQDFCA7VBOZSLAU","created_at":"2026-07-05T02:26:18.990844+00:00"},{"alias_kind":"pith_short_8","alias_value":"2OQDFCA7","created_at":"2026-07-05T02:26:18.990844+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27817","citing_title":"Turning Video Models into Generalist Robot Policies","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22190","citing_title":"No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2110.02178","citing_title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09862","citing_title":"FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2OQDFCA7VBOZSLAUSSRRQQIKMY","json":"https://pith.science/pith/2OQDFCA7VBOZSLAUSSRRQQIKMY.json","graph_json":"https://pith.science/api/pith-number/2OQDFCA7VBOZSLAUSSRRQQIKMY/graph.json","events_json":"https://pith.science/api/pith-number/2OQDFCA7VBOZSLAUSSRRQQIKMY/events.json","paper":"https://pith.science/paper/2OQDFCA7"},"agent_actions":{"view_html":"https://pith.science/pith/2OQDFCA7VBOZSLAUSSRRQQIKMY","download_json":"https://pith.science/pith/2OQDFCA7VBOZSLAUSSRRQQIKMY.json","view_paper":"https://pith.science/paper/2OQDFCA7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.13413&json=true","fetch_graph":"https://pith.science/api/pith-number/2OQDFCA7VBOZSLAUSSRRQQIKMY/graph.json","fetch_events":"https://pith.science/api/pith-number/2OQDFCA7VBOZSLAUSSRRQQIKMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2OQDFCA7VBOZSLAUSSRRQQIKMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2OQDFCA7VBOZSLAUSSRRQQIKMY/action/storage_attestation","attest_author":"https://pith.science/pith/2OQDFCA7VBOZSLAUSSRRQQIKMY/action/author_attestation","sign_citation":"https://pith.science/pith/2OQDFCA7VBOZSLAUSSRRQQIKMY/action/citation_signature","submit_replication":"https://pith.science/pith/2OQDFCA7VBOZSLAUSSRRQQIKMY/action/replication_record"}},"created_at":"2026-07-05T02:26:18.990844+00:00","updated_at":"2026-07-05T02:26:18.990844+00:00"}