{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BXZBWNLXUJRIIH3U7HE23R6BEK","short_pith_number":"pith:BXZBWNLX","schema_version":"1.0","canonical_sha256":"0df21b3577a262841f74f9c9adc7c122b529179fb3b3b1239b4be220b16c83b6","source":{"kind":"arxiv","id":"2203.10421","version":2},"attestation_state":"computed","paper":{"title":"CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Gabriel Ilharco, Ludwig Schmidt, Mitchell Wortsman, Samir Yitzhak Gadre, Shuran Song","submitted_at":"2022-03-20T00:52:45Z","abstract_excerpt":"For robots to be generally useful, they must be able to find arbitrary objects described by people (i.e., be language-driven) even without expensive navigation training on in-domain data (i.e., perform zero-shot inference). We explore these capabilities in a unified setting: language-driven zero-shot object navigation (L-ZSON). Inspired by the recent success of open-vocabulary models for image classification, we investigate a straightforward framework, CLIP on Wheels (CoW), to adapt open-vocabulary models to this task without fine-tuning. To better evaluate L-ZSON, we introduce the Pasture ben"},"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":"2203.10421","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-20T00:52:45Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"e6c013eeb9e80375b0ed4dd66d52d037debc213ee9cef763b751b2727a397214","abstract_canon_sha256":"e150a80272c95ed08c62c6dafd881fef85b5079c9d916bd3ac691ebec4ada2e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:14.449610Z","signature_b64":"dvfYAgUq5Oss745zGxjEb9FWZMjM4UtnV6VlHf9UjcW/jEgeisA+JmZHTV0vrePx/0U74UbDIckZGViRpSAnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0df21b3577a262841f74f9c9adc7c122b529179fb3b3b1239b4be220b16c83b6","last_reissued_at":"2026-07-05T05:25:14.449013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:14.449013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Gabriel Ilharco, Ludwig Schmidt, Mitchell Wortsman, Samir Yitzhak Gadre, Shuran Song","submitted_at":"2022-03-20T00:52:45Z","abstract_excerpt":"For robots to be generally useful, they must be able to find arbitrary objects described by people (i.e., be language-driven) even without expensive navigation training on in-domain data (i.e., perform zero-shot inference). We explore these capabilities in a unified setting: language-driven zero-shot object navigation (L-ZSON). Inspired by the recent success of open-vocabulary models for image classification, we investigate a straightforward framework, CLIP on Wheels (CoW), to adapt open-vocabulary models to this task without fine-tuning. To better evaluate L-ZSON, we introduce the Pasture ben"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10421","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.10421/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":"2203.10421","created_at":"2026-07-05T05:25:14.449103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.10421v2","created_at":"2026-07-05T05:25:14.449103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10421","created_at":"2026-07-05T05:25:14.449103+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXZBWNLXUJRI","created_at":"2026-07-05T05:25:14.449103+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXZBWNLXUJRIIH3U","created_at":"2026-07-05T05:25:14.449103+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXZBWNLX","created_at":"2026-07-05T05:25:14.449103+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30696","citing_title":"ViTL: Temporal Logic-Guided Zero-Shot Natural Language Navigation via Vision-Language Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26239","citing_title":"Sentinel: Embodied Cooperative Spatial Reasoning and Planning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10345","citing_title":"TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17800","citing_title":"ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BXZBWNLXUJRIIH3U7HE23R6BEK","json":"https://pith.science/pith/BXZBWNLXUJRIIH3U7HE23R6BEK.json","graph_json":"https://pith.science/api/pith-number/BXZBWNLXUJRIIH3U7HE23R6BEK/graph.json","events_json":"https://pith.science/api/pith-number/BXZBWNLXUJRIIH3U7HE23R6BEK/events.json","paper":"https://pith.science/paper/BXZBWNLX"},"agent_actions":{"view_html":"https://pith.science/pith/BXZBWNLXUJRIIH3U7HE23R6BEK","download_json":"https://pith.science/pith/BXZBWNLXUJRIIH3U7HE23R6BEK.json","view_paper":"https://pith.science/paper/BXZBWNLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.10421&json=true","fetch_graph":"https://pith.science/api/pith-number/BXZBWNLXUJRIIH3U7HE23R6BEK/graph.json","fetch_events":"https://pith.science/api/pith-number/BXZBWNLXUJRIIH3U7HE23R6BEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXZBWNLXUJRIIH3U7HE23R6BEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXZBWNLXUJRIIH3U7HE23R6BEK/action/storage_attestation","attest_author":"https://pith.science/pith/BXZBWNLXUJRIIH3U7HE23R6BEK/action/author_attestation","sign_citation":"https://pith.science/pith/BXZBWNLXUJRIIH3U7HE23R6BEK/action/citation_signature","submit_replication":"https://pith.science/pith/BXZBWNLXUJRIIH3U7HE23R6BEK/action/replication_record"}},"created_at":"2026-07-05T05:25:14.449103+00:00","updated_at":"2026-07-05T05:25:14.449103+00:00"}