{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SDH75FCACGA2WTEBZWZOFSLZ67","short_pith_number":"pith:SDH75FCA","schema_version":"1.0","canonical_sha256":"90cffe94401181ab4c81cdb2e2c979f7c96de6476d064b236275c00c4113c156","source":{"kind":"arxiv","id":"2303.07798","version":1},"attestation_state":"computed","paper":{"title":"OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNav","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alexei Baevski, Arjun Majumdar, Dhruv Batra, Karmesh Yadav, Naoki Yokoyama, Oleksandr Maksymets, Ram Ramrakhya, Zsolt Kira","submitted_at":"2023-03-14T11:15:37Z","abstract_excerpt":"We present a single neural network architecture composed of task-agnostic components (ViTs, convolutions, and LSTMs) that achieves state-of-art results on both the ImageNav (\"go to location in <this picture>\") and ObjectNav (\"find a chair\") tasks without any task-specific modules like object detection, segmentation, mapping, or planning modules. Such general-purpose methods offer advantages of simplicity in design, positive scaling with available compute, and versatile applicability to multiple tasks. Our work builds upon the recent success of self-supervised learning (SSL) for pre-training vi"},"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":"2303.07798","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-14T11:15:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a35e84ce965f2e9b4d3afa3ab7c49b0f03385a6528d8b3b91a28f404a12b6305","abstract_canon_sha256":"826eb2ac186e0592c2aa914505f3ce55f177fdbd4d556a00f8d68c259eb50333"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:11.631292Z","signature_b64":"jVadBTGeq1PejB+1+Ee29a/3ocFpFX4MMAnNakLfvp6mkdz1R11weK2bCH6KZYDEERSzWbTVYUCQH7DOkiOVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90cffe94401181ab4c81cdb2e2c979f7c96de6476d064b236275c00c4113c156","last_reissued_at":"2026-07-05T05:51:11.630773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:11.630773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNav","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alexei Baevski, Arjun Majumdar, Dhruv Batra, Karmesh Yadav, Naoki Yokoyama, Oleksandr Maksymets, Ram Ramrakhya, Zsolt Kira","submitted_at":"2023-03-14T11:15:37Z","abstract_excerpt":"We present a single neural network architecture composed of task-agnostic components (ViTs, convolutions, and LSTMs) that achieves state-of-art results on both the ImageNav (\"go to location in <this picture>\") and ObjectNav (\"find a chair\") tasks without any task-specific modules like object detection, segmentation, mapping, or planning modules. Such general-purpose methods offer advantages of simplicity in design, positive scaling with available compute, and versatile applicability to multiple tasks. Our work builds upon the recent success of self-supervised learning (SSL) for pre-training vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07798","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/2303.07798/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":"2303.07798","created_at":"2026-07-05T05:51:11.630837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.07798v1","created_at":"2026-07-05T05:51:11.630837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07798","created_at":"2026-07-05T05:51:11.630837+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDH75FCACGA2","created_at":"2026-07-05T05:51:11.630837+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDH75FCACGA2WTEB","created_at":"2026-07-05T05:51:11.630837+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDH75FCA","created_at":"2026-07-05T05:51:11.630837+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29917","citing_title":"Flying to Image-Specified Objects: 3D Quadrotor Navigation via Cross-Graph Memory and Viewpoint Planning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27582","citing_title":"Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigation","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2403.09905","citing_title":"Personalized Embodied Navigation for Portable Object Finding","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2506.01418","citing_title":"SEMNAV: Enhancing Visual Semantic Navigation in Robotics through Semantic Segmentation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19594","citing_title":"MCNav: Memory-Aware Dynamic Cognitive Map for Zero-shot Goal-oriented Navigation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2509.16445","citing_title":"FiLM-Nav: Efficient and Generalizable Navigation via VLM Fine-tuning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20685","citing_title":"C-NAV: Towards Self-Evolving Continual Object Navigation in Open World","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2512.17435","citing_title":"ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06224","citing_title":"Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2603.20530","citing_title":"Memory Over Maps: 3D Object Localization Without Reconstruction","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26788","citing_title":"ReMemNav: A Rethinking and Memory-Augmented Framework for Zero-Shot Object Navigation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14803","citing_title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05960","citing_title":"Plug-and-Play Label Map Diffusion for Universal Goal-Oriented Navigation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05351","citing_title":"AnyImageNav: Any-View Geometry for Precise Last-Meter Image-Goal Navigation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12872","citing_title":"OVAL: Open-Vocabulary Augmented Memory Model for Lifelong Object Goal Navigation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17473","citing_title":"Dual-Anchoring: Addressing State Drift in Vision-Language Navigation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17407","citing_title":"Think before Go: Hierarchical Reasoning for Image-goal Navigation","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SDH75FCACGA2WTEBZWZOFSLZ67","json":"https://pith.science/pith/SDH75FCACGA2WTEBZWZOFSLZ67.json","graph_json":"https://pith.science/api/pith-number/SDH75FCACGA2WTEBZWZOFSLZ67/graph.json","events_json":"https://pith.science/api/pith-number/SDH75FCACGA2WTEBZWZOFSLZ67/events.json","paper":"https://pith.science/paper/SDH75FCA"},"agent_actions":{"view_html":"https://pith.science/pith/SDH75FCACGA2WTEBZWZOFSLZ67","download_json":"https://pith.science/pith/SDH75FCACGA2WTEBZWZOFSLZ67.json","view_paper":"https://pith.science/paper/SDH75FCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.07798&json=true","fetch_graph":"https://pith.science/api/pith-number/SDH75FCACGA2WTEBZWZOFSLZ67/graph.json","fetch_events":"https://pith.science/api/pith-number/SDH75FCACGA2WTEBZWZOFSLZ67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDH75FCACGA2WTEBZWZOFSLZ67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDH75FCACGA2WTEBZWZOFSLZ67/action/storage_attestation","attest_author":"https://pith.science/pith/SDH75FCACGA2WTEBZWZOFSLZ67/action/author_attestation","sign_citation":"https://pith.science/pith/SDH75FCACGA2WTEBZWZOFSLZ67/action/citation_signature","submit_replication":"https://pith.science/pith/SDH75FCACGA2WTEBZWZOFSLZ67/action/replication_record"}},"created_at":"2026-07-05T05:51:11.630837+00:00","updated_at":"2026-07-05T05:51:11.630837+00:00"}