{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RID7QHKGNEAWAOWR2LAW4TXOMA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"edcc352c233c6e55d4097872a830d80dd08aeefd1a7a6a4e12074277102c84b8","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-08T18:45:37Z","title_canon_sha256":"58b99de7f3a16d9ac719e431c9bee88cf6961829d281fb9a4582f5418f853c1c"},"schema_version":"1.0","source":{"id":"2405.05363","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.05363","created_at":"2026-07-05T08:17:17Z"},{"alias_kind":"arxiv_version","alias_value":"2405.05363v1","created_at":"2026-07-05T08:17:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05363","created_at":"2026-07-05T08:17:17Z"},{"alias_kind":"pith_short_12","alias_value":"RID7QHKGNEAW","created_at":"2026-07-05T08:17:17Z"},{"alias_kind":"pith_short_16","alias_value":"RID7QHKGNEAWAOWR","created_at":"2026-07-05T08:17:17Z"},{"alias_kind":"pith_short_8","alias_value":"RID7QHKG","created_at":"2026-07-05T08:17:17Z"}],"graph_snapshots":[{"event_id":"sha256:92a77cf901fb1787c6134a5b3ad62e20c4ade4f90c0827b01350f895fdb605aa","target":"graph","created_at":"2026-07-05T08:17:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.05363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arnie Sen, Dinesh Manocha, Harry Cheng, Muyuan Lin, Rajasimman Madhivanan, Richard Kim, Tianrui Guan, Yurou Yang","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-08T18:45:37Z","title":"LOC-ZSON: Language-driven Object-Centric Zero-Shot Object Retrieval and Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05363","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:aaaf94464a5b83804462f6749dea24700de23869d42a01b726d5e747b0de0cd4","target":"record","created_at":"2026-07-05T08:17:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"edcc352c233c6e55d4097872a830d80dd08aeefd1a7a6a4e12074277102c84b8","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-08T18:45:37Z","title_canon_sha256":"58b99de7f3a16d9ac719e431c9bee88cf6961829d281fb9a4582f5418f853c1c"},"schema_version":"1.0","source":{"id":"2405.05363","kind":"arxiv","version":1}},"canonical_sha256":"8a07f81d466901603ad1d2c16e4eee60263612a4eeaa60347257bc543e87c1bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a07f81d466901603ad1d2c16e4eee60263612a4eeaa60347257bc543e87c1bf","first_computed_at":"2026-07-05T08:17:17.358178Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:17:17.358178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vaAXyEQ5HyH37jKBp4vu/QqFIYsU2+bWAtZdmg79LBogi0k4b0HyBLPbA5+Wq9jSLqcThzAnZwpGUekdpW9jBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:17:17.358673Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.05363","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aaaf94464a5b83804462f6749dea24700de23869d42a01b726d5e747b0de0cd4","sha256:92a77cf901fb1787c6134a5b3ad62e20c4ade4f90c0827b01350f895fdb605aa"],"state_sha256":"9ca0113e943ddecf2bd7c63a7875d31ffb058ba72c0787e9d57c507028b536e2"}