{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5CR5H6LACONSDDCOHMMELGPM32","short_pith_number":"pith:5CR5H6LA","schema_version":"1.0","canonical_sha256":"e8a3d3f960139b218c4e3b184599ecdeb5d3a3eacaef8ea15db8d6bc0413ddf8","source":{"kind":"arxiv","id":"2207.00052","version":3},"attestation_state":"computed","paper":{"title":"Visual Pre-training for Navigation: What Can We Learn from Noise?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ching-Yun Ko, Pulkit Agrawal, Yanwei Wang","submitted_at":"2022-06-30T18:35:00Z","abstract_excerpt":"One powerful paradigm in visual navigation is to predict actions from observations directly. Training such an end-to-end system allows representations useful for downstream tasks to emerge automatically. However, the lack of inductive bias makes this system data inefficient. We hypothesize a sufficient representation of the current view and the goal view for a navigation policy can be learned by predicting the location and size of a crop of the current view that corresponds to the goal. We further show that training such random crop prediction in a self-supervised fashion purely on synthetic n"},"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":"2207.00052","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-30T18:35:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9e34550762a5cceb3c5d26689a7e95e31a8e4806ac2e6adf430218b47b6190c9","abstract_canon_sha256":"00c569fe8a27e028018864f58d75d9cc02df27af52903d236f1c2d53d77e68d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:04.364909Z","signature_b64":"U6UC+e0pfAk3zEWr9PZo8FZUcnWVPALRgTPaeCSDNk3/SnYJrTorLp8pxIfSb6TyXD3AP0FUUYF8yk8H+KWADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8a3d3f960139b218c4e3b184599ecdeb5d3a3eacaef8ea15db8d6bc0413ddf8","last_reissued_at":"2026-07-05T06:35:04.364445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:04.364445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Pre-training for Navigation: What Can We Learn from Noise?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ching-Yun Ko, Pulkit Agrawal, Yanwei Wang","submitted_at":"2022-06-30T18:35:00Z","abstract_excerpt":"One powerful paradigm in visual navigation is to predict actions from observations directly. Training such an end-to-end system allows representations useful for downstream tasks to emerge automatically. However, the lack of inductive bias makes this system data inefficient. We hypothesize a sufficient representation of the current view and the goal view for a navigation policy can be learned by predicting the location and size of a crop of the current view that corresponds to the goal. We further show that training such random crop prediction in a self-supervised fashion purely on synthetic n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00052","kind":"arxiv","version":3},"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/2207.00052/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":"2207.00052","created_at":"2026-07-05T06:35:04.364497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.00052v3","created_at":"2026-07-05T06:35:04.364497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00052","created_at":"2026-07-05T06:35:04.364497+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CR5H6LACONS","created_at":"2026-07-05T06:35:04.364497+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CR5H6LACONSDDCO","created_at":"2026-07-05T06:35:04.364497+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CR5H6LA","created_at":"2026-07-05T06:35:04.364497+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14287","citing_title":"Steering Robots with Inference-Time Interactions","ref_index":153,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5CR5H6LACONSDDCOHMMELGPM32","json":"https://pith.science/pith/5CR5H6LACONSDDCOHMMELGPM32.json","graph_json":"https://pith.science/api/pith-number/5CR5H6LACONSDDCOHMMELGPM32/graph.json","events_json":"https://pith.science/api/pith-number/5CR5H6LACONSDDCOHMMELGPM32/events.json","paper":"https://pith.science/paper/5CR5H6LA"},"agent_actions":{"view_html":"https://pith.science/pith/5CR5H6LACONSDDCOHMMELGPM32","download_json":"https://pith.science/pith/5CR5H6LACONSDDCOHMMELGPM32.json","view_paper":"https://pith.science/paper/5CR5H6LA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.00052&json=true","fetch_graph":"https://pith.science/api/pith-number/5CR5H6LACONSDDCOHMMELGPM32/graph.json","fetch_events":"https://pith.science/api/pith-number/5CR5H6LACONSDDCOHMMELGPM32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CR5H6LACONSDDCOHMMELGPM32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CR5H6LACONSDDCOHMMELGPM32/action/storage_attestation","attest_author":"https://pith.science/pith/5CR5H6LACONSDDCOHMMELGPM32/action/author_attestation","sign_citation":"https://pith.science/pith/5CR5H6LACONSDDCOHMMELGPM32/action/citation_signature","submit_replication":"https://pith.science/pith/5CR5H6LACONSDDCOHMMELGPM32/action/replication_record"}},"created_at":"2026-07-05T06:35:04.364497+00:00","updated_at":"2026-07-05T06:35:04.364497+00:00"}