{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZLJSQ3WW43K3NHFJOGIK7VVFLZ","short_pith_number":"pith:ZLJSQ3WW","schema_version":"1.0","canonical_sha256":"cad3286ed6e6d5b69ca97190afd6a55e606e7070d5d9be39a509e02a029b0f17","source":{"kind":"arxiv","id":"2511.13207","version":2},"attestation_state":"computed","paper":{"title":"PIGEON: VLM-Driven Object Navigation via Points of Interest Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Cheng Chi, Cheng Peng, Heng Wang, Jing Liu, Pengwei Wang, Shanghang Zhang, Xiaobao Wei, Yanhao Zhang, Zhenzhe Zhang, Zhongyuan Wang","submitted_at":"2025-11-17T10:19:13Z","abstract_excerpt":"Object navigation in unseen indoor environments requires agents to perform semantic search under partial observability. Vision-language models (VLMs) provide strong semantic-spatial priors for this task, but how to interface them with robot navigation remains challenging: dense VLM inference is expensive, while abstracting environments into symbolic memories often separates high-level reasoning from the raw visual evidence that supports it. We propose we propose PIGEON (Point of Interest Guided Exploration for Object Navigation), a VLM-driven framework that formulates object navigation as raw-"},"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":"2511.13207","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-11-17T10:19:13Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f930bb6a526a7d112123b625f57a95fe59db56aba68bb5d8bbdf560f0ffb9c56","abstract_canon_sha256":"2531840cbd93f92cd4d1f8380ed90e842b71f2254606f06097aaa2580b0c3173"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:22.007676Z","signature_b64":"5c7wjK0wCKBSMHYy7/a9gspqHiGJIvOiiMdzv0pC21PK2S5ZD1MUNNyd2iyUdVaO+7Kp0ft7ew2YfYIQd2OKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cad3286ed6e6d5b69ca97190afd6a55e606e7070d5d9be39a509e02a029b0f17","last_reissued_at":"2026-06-11T01:09:22.006758Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:22.006758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PIGEON: VLM-Driven Object Navigation via Points of Interest Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Cheng Chi, Cheng Peng, Heng Wang, Jing Liu, Pengwei Wang, Shanghang Zhang, Xiaobao Wei, Yanhao Zhang, Zhenzhe Zhang, Zhongyuan Wang","submitted_at":"2025-11-17T10:19:13Z","abstract_excerpt":"Object navigation in unseen indoor environments requires agents to perform semantic search under partial observability. Vision-language models (VLMs) provide strong semantic-spatial priors for this task, but how to interface them with robot navigation remains challenging: dense VLM inference is expensive, while abstracting environments into symbolic memories often separates high-level reasoning from the raw visual evidence that supports it. We propose we propose PIGEON (Point of Interest Guided Exploration for Object Navigation), a VLM-driven framework that formulates object navigation as raw-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.13207","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/2511.13207/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":"2511.13207","created_at":"2026-06-11T01:09:22.006895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.13207v2","created_at":"2026-06-11T01:09:22.006895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.13207","created_at":"2026-06-11T01:09:22.006895+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZLJSQ3WW43K3","created_at":"2026-06-11T01:09:22.006895+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZLJSQ3WW43K3NHFJ","created_at":"2026-06-11T01:09:22.006895+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZLJSQ3WW","created_at":"2026-06-11T01:09:22.006895+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.21887","citing_title":"IGV-RRT: Prior-Real-Time Observation Fusion for Active Object Search in Changing Environments","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZLJSQ3WW43K3NHFJOGIK7VVFLZ","json":"https://pith.science/pith/ZLJSQ3WW43K3NHFJOGIK7VVFLZ.json","graph_json":"https://pith.science/api/pith-number/ZLJSQ3WW43K3NHFJOGIK7VVFLZ/graph.json","events_json":"https://pith.science/api/pith-number/ZLJSQ3WW43K3NHFJOGIK7VVFLZ/events.json","paper":"https://pith.science/paper/ZLJSQ3WW"},"agent_actions":{"view_html":"https://pith.science/pith/ZLJSQ3WW43K3NHFJOGIK7VVFLZ","download_json":"https://pith.science/pith/ZLJSQ3WW43K3NHFJOGIK7VVFLZ.json","view_paper":"https://pith.science/paper/ZLJSQ3WW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.13207&json=true","fetch_graph":"https://pith.science/api/pith-number/ZLJSQ3WW43K3NHFJOGIK7VVFLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZLJSQ3WW43K3NHFJOGIK7VVFLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZLJSQ3WW43K3NHFJOGIK7VVFLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZLJSQ3WW43K3NHFJOGIK7VVFLZ/action/storage_attestation","attest_author":"https://pith.science/pith/ZLJSQ3WW43K3NHFJOGIK7VVFLZ/action/author_attestation","sign_citation":"https://pith.science/pith/ZLJSQ3WW43K3NHFJOGIK7VVFLZ/action/citation_signature","submit_replication":"https://pith.science/pith/ZLJSQ3WW43K3NHFJOGIK7VVFLZ/action/replication_record"}},"created_at":"2026-06-11T01:09:22.006895+00:00","updated_at":"2026-06-11T01:09:22.006895+00:00"}