{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DQJJE5D32DDGDVRY43G35WGSKI","short_pith_number":"pith:DQJJE5D3","schema_version":"1.0","canonical_sha256":"1c1292747bd0c661d638e6cdbed8d252300e6c23b8c7899458335c9aa8f64c83","source":{"kind":"arxiv","id":"1912.11121","version":1},"attestation_state":"computed","paper":{"title":"Learning to Navigate Using Mid-Level Visual Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexander Sax, Amir Zamir, Bradley Emi, Jeffrey O. Zhang, Jitendra Malik, Leonidas Guibas, Silvio Savarese","submitted_at":"2019-12-23T21:45:50Z","abstract_excerpt":"How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform downstream motor tasks (e.g. navigating a complex environment)? What are the consequences of not utilizing such visual priors in learning? We study these questions by integrating a generic perceptual skill set (a distance estimator, an edge detector, etc.) within a reinforcement learning framework (see Fig. 1). This skill set (\"mid-level vision\") provides the policy with a more processed state of the world compared to raw images.\n  Our large-scale study demonstrates that using "},"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":"1912.11121","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-23T21:45:50Z","cross_cats_sorted":["cs.LG","cs.NE","cs.RO"],"title_canon_sha256":"3a78fee19c5d262f945a939f4b15a1312f009690db1ffd713bb0f41ada83ce4f","abstract_canon_sha256":"b2ee78291733d26443c7abf29748ccc4ab10bb2ccc36aab559b28e390c10cff3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:17.233396Z","signature_b64":"2hkEQXVUJwrdxi3drWPImUv/qeHRGvECt1IDgynb/+2s74uZd91kyUfJyMvbxkpeXkGkpff91t4SFjicM7SCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c1292747bd0c661d638e6cdbed8d252300e6c23b8c7899458335c9aa8f64c83","last_reissued_at":"2026-07-05T00:28:17.232982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:17.232982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Navigate Using Mid-Level Visual Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexander Sax, Amir Zamir, Bradley Emi, Jeffrey O. Zhang, Jitendra Malik, Leonidas Guibas, Silvio Savarese","submitted_at":"2019-12-23T21:45:50Z","abstract_excerpt":"How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform downstream motor tasks (e.g. navigating a complex environment)? What are the consequences of not utilizing such visual priors in learning? We study these questions by integrating a generic perceptual skill set (a distance estimator, an edge detector, etc.) within a reinforcement learning framework (see Fig. 1). This skill set (\"mid-level vision\") provides the policy with a more processed state of the world compared to raw images.\n  Our large-scale study demonstrates that using "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.11121","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/1912.11121/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":"1912.11121","created_at":"2026-07-05T00:28:17.233045+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.11121v1","created_at":"2026-07-05T00:28:17.233045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.11121","created_at":"2026-07-05T00:28:17.233045+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQJJE5D32DDG","created_at":"2026-07-05T00:28:17.233045+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQJJE5D32DDGDVRY","created_at":"2026-07-05T00:28:17.233045+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQJJE5D3","created_at":"2026-07-05T00:28:17.233045+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16899","citing_title":"LASAR: Towards Spatio-temporal Reasoning with Latent Cognitive Map","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQJJE5D32DDGDVRY43G35WGSKI","json":"https://pith.science/pith/DQJJE5D32DDGDVRY43G35WGSKI.json","graph_json":"https://pith.science/api/pith-number/DQJJE5D32DDGDVRY43G35WGSKI/graph.json","events_json":"https://pith.science/api/pith-number/DQJJE5D32DDGDVRY43G35WGSKI/events.json","paper":"https://pith.science/paper/DQJJE5D3"},"agent_actions":{"view_html":"https://pith.science/pith/DQJJE5D32DDGDVRY43G35WGSKI","download_json":"https://pith.science/pith/DQJJE5D32DDGDVRY43G35WGSKI.json","view_paper":"https://pith.science/paper/DQJJE5D3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.11121&json=true","fetch_graph":"https://pith.science/api/pith-number/DQJJE5D32DDGDVRY43G35WGSKI/graph.json","fetch_events":"https://pith.science/api/pith-number/DQJJE5D32DDGDVRY43G35WGSKI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQJJE5D32DDGDVRY43G35WGSKI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQJJE5D32DDGDVRY43G35WGSKI/action/storage_attestation","attest_author":"https://pith.science/pith/DQJJE5D32DDGDVRY43G35WGSKI/action/author_attestation","sign_citation":"https://pith.science/pith/DQJJE5D32DDGDVRY43G35WGSKI/action/citation_signature","submit_replication":"https://pith.science/pith/DQJJE5D32DDGDVRY43G35WGSKI/action/replication_record"}},"created_at":"2026-07-05T00:28:17.233045+00:00","updated_at":"2026-07-05T00:28:17.233045+00:00"}