{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RID7QHKGNEAWAOWR2LAW4TXOMA","short_pith_number":"pith:RID7QHKG","schema_version":"1.0","canonical_sha256":"8a07f81d466901603ad1d2c16e4eee60263612a4eeaa60347257bc543e87c1bf","source":{"kind":"arxiv","id":"2405.05363","version":1},"attestation_state":"computed","paper":{"title":"LOC-ZSON: Language-driven Object-Centric Zero-Shot Object Retrieval and Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Arnie Sen, Dinesh Manocha, Harry Cheng, Muyuan Lin, Rajasimman Madhivanan, Richard Kim, Tianrui Guan, Yurou Yang","submitted_at":"2024-05-08T18:45:37Z","abstract_excerpt":"In this paper, we present LOC-ZSON, a novel Language-driven Object-Centric image representation for object navigation task within complex scenes. We propose an object-centric image representation and corresponding losses for visual-language model (VLM) fine-tuning, which can handle complex object-level queries. In addition, we design a novel LLM-based augmentation and prompt templates for stability during training and zero-shot inference. We implement our method on Astro robot and deploy it in both simulated and real-world environments for zero-shot object navigation. We show that our proposed"},"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":"2405.05363","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-08T18:45:37Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"58b99de7f3a16d9ac719e431c9bee88cf6961829d281fb9a4582f5418f853c1c","abstract_canon_sha256":"edcc352c233c6e55d4097872a830d80dd08aeefd1a7a6a4e12074277102c84b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:17.358673Z","signature_b64":"vaAXyEQ5HyH37jKBp4vu/QqFIYsU2+bWAtZdmg79LBogi0k4b0HyBLPbA5+Wq9jSLqcThzAnZwpGUekdpW9jBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a07f81d466901603ad1d2c16e4eee60263612a4eeaa60347257bc543e87c1bf","last_reissued_at":"2026-07-05T08:17:17.358178Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:17.358178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LOC-ZSON: Language-driven Object-Centric Zero-Shot Object Retrieval and Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Arnie Sen, Dinesh Manocha, Harry Cheng, Muyuan Lin, Rajasimman Madhivanan, Richard Kim, Tianrui Guan, Yurou Yang","submitted_at":"2024-05-08T18:45:37Z","abstract_excerpt":"In this paper, we present LOC-ZSON, a novel Language-driven Object-Centric image representation for object navigation task within complex scenes. We propose an object-centric image representation and corresponding losses for visual-language model (VLM) fine-tuning, which can handle complex object-level queries. In addition, we design a novel LLM-based augmentation and prompt templates for stability during training and zero-shot inference. We implement our method on Astro robot and deploy it in both simulated and real-world environments for zero-shot object navigation. We show that our proposed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05363","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/2405.05363/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":"2405.05363","created_at":"2026-07-05T08:17:17.358235+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.05363v1","created_at":"2026-07-05T08:17:17.358235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05363","created_at":"2026-07-05T08:17:17.358235+00:00"},{"alias_kind":"pith_short_12","alias_value":"RID7QHKGNEAW","created_at":"2026-07-05T08:17:17.358235+00:00"},{"alias_kind":"pith_short_16","alias_value":"RID7QHKGNEAWAOWR","created_at":"2026-07-05T08:17:17.358235+00:00"},{"alias_kind":"pith_short_8","alias_value":"RID7QHKG","created_at":"2026-07-05T08:17:17.358235+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07653","citing_title":"A Dataset for Dynamic Human Preferences for Vision Language Models","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RID7QHKGNEAWAOWR2LAW4TXOMA","json":"https://pith.science/pith/RID7QHKGNEAWAOWR2LAW4TXOMA.json","graph_json":"https://pith.science/api/pith-number/RID7QHKGNEAWAOWR2LAW4TXOMA/graph.json","events_json":"https://pith.science/api/pith-number/RID7QHKGNEAWAOWR2LAW4TXOMA/events.json","paper":"https://pith.science/paper/RID7QHKG"},"agent_actions":{"view_html":"https://pith.science/pith/RID7QHKGNEAWAOWR2LAW4TXOMA","download_json":"https://pith.science/pith/RID7QHKGNEAWAOWR2LAW4TXOMA.json","view_paper":"https://pith.science/paper/RID7QHKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.05363&json=true","fetch_graph":"https://pith.science/api/pith-number/RID7QHKGNEAWAOWR2LAW4TXOMA/graph.json","fetch_events":"https://pith.science/api/pith-number/RID7QHKGNEAWAOWR2LAW4TXOMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RID7QHKGNEAWAOWR2LAW4TXOMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RID7QHKGNEAWAOWR2LAW4TXOMA/action/storage_attestation","attest_author":"https://pith.science/pith/RID7QHKGNEAWAOWR2LAW4TXOMA/action/author_attestation","sign_citation":"https://pith.science/pith/RID7QHKGNEAWAOWR2LAW4TXOMA/action/citation_signature","submit_replication":"https://pith.science/pith/RID7QHKGNEAWAOWR2LAW4TXOMA/action/replication_record"}},"created_at":"2026-07-05T08:17:17.358235+00:00","updated_at":"2026-07-05T08:17:17.358235+00:00"}