{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GIGCX5QNRPMLWF6JOHQFM2OJFC","short_pith_number":"pith:GIGCX5QN","schema_version":"1.0","canonical_sha256":"320c2bf60d8bd8bb17c971e05669c928802007559903bb338dcc860eee8c890a","source":{"kind":"arxiv","id":"1712.04850","version":2},"attestation_state":"computed","paper":{"title":"Self-Supervised Relative Depth Learning for Urban Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Erik Learned-Miller, Greg Shakhnarovich, Gustav Larsson, Huaizu Jiang, Michael Maire","submitted_at":"2017-12-13T16:39:14Z","abstract_excerpt":"As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth. It is natural for a learning agent to associate image patterns with the magnitude of their displacement over time: as the agent moves, faraway mountains don't move much; nearby trees move a lot. This natural relationship between the appearance of objects and their motion is a rich source of information about the world. In this work, we start by training a deep network, using fully automatic supervision, to predict relative scene depth from single images. The relative d"},"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":"1712.04850","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-13T16:39:14Z","cross_cats_sorted":[],"title_canon_sha256":"4dbfef26368df09629b2211b7979a3ddd58be8712dc86d537950ada904d32b3f","abstract_canon_sha256":"e24fe1a2ae9e30c84fe6ebae9df9c560b223788e543a7ce04e52c7da22a69212"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:41.324686Z","signature_b64":"Azcwxaus7Pjqu/6PPgs+wq8nmmGkD6t1ML8bzLLlQlcSv8NSseFc952HABC6W6CkgDQHjll6Zyx5DEbig9xOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"320c2bf60d8bd8bb17c971e05669c928802007559903bb338dcc860eee8c890a","last_reissued_at":"2026-05-18T00:19:41.324043Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:41.324043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Relative Depth Learning for Urban Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Erik Learned-Miller, Greg Shakhnarovich, Gustav Larsson, Huaizu Jiang, Michael Maire","submitted_at":"2017-12-13T16:39:14Z","abstract_excerpt":"As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth. It is natural for a learning agent to associate image patterns with the magnitude of their displacement over time: as the agent moves, faraway mountains don't move much; nearby trees move a lot. This natural relationship between the appearance of objects and their motion is a rich source of information about the world. In this work, we start by training a deep network, using fully automatic supervision, to predict relative scene depth from single images. The relative d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.04850","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":"1712.04850","created_at":"2026-05-18T00:19:41.324129+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.04850v2","created_at":"2026-05-18T00:19:41.324129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.04850","created_at":"2026-05-18T00:19:41.324129+00:00"},{"alias_kind":"pith_short_12","alias_value":"GIGCX5QNRPML","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GIGCX5QNRPMLWF6J","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GIGCX5QN","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GIGCX5QNRPMLWF6JOHQFM2OJFC","json":"https://pith.science/pith/GIGCX5QNRPMLWF6JOHQFM2OJFC.json","graph_json":"https://pith.science/api/pith-number/GIGCX5QNRPMLWF6JOHQFM2OJFC/graph.json","events_json":"https://pith.science/api/pith-number/GIGCX5QNRPMLWF6JOHQFM2OJFC/events.json","paper":"https://pith.science/paper/GIGCX5QN"},"agent_actions":{"view_html":"https://pith.science/pith/GIGCX5QNRPMLWF6JOHQFM2OJFC","download_json":"https://pith.science/pith/GIGCX5QNRPMLWF6JOHQFM2OJFC.json","view_paper":"https://pith.science/paper/GIGCX5QN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.04850&json=true","fetch_graph":"https://pith.science/api/pith-number/GIGCX5QNRPMLWF6JOHQFM2OJFC/graph.json","fetch_events":"https://pith.science/api/pith-number/GIGCX5QNRPMLWF6JOHQFM2OJFC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GIGCX5QNRPMLWF6JOHQFM2OJFC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GIGCX5QNRPMLWF6JOHQFM2OJFC/action/storage_attestation","attest_author":"https://pith.science/pith/GIGCX5QNRPMLWF6JOHQFM2OJFC/action/author_attestation","sign_citation":"https://pith.science/pith/GIGCX5QNRPMLWF6JOHQFM2OJFC/action/citation_signature","submit_replication":"https://pith.science/pith/GIGCX5QNRPMLWF6JOHQFM2OJFC/action/replication_record"}},"created_at":"2026-05-18T00:19:41.324129+00:00","updated_at":"2026-05-18T00:19:41.324129+00:00"}