{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MX37Q5O7CPWGKY3PQBH4IG45KH","short_pith_number":"pith:MX37Q5O7","schema_version":"1.0","canonical_sha256":"65f7f875df13ec65636f804fc41b9d51de805dfd7ab03e98426a78f3ee23b73f","source":{"kind":"arxiv","id":"2410.00388","version":3},"attestation_state":"computed","paper":{"title":"Find Everything: A General Vision Language Model Approach to Multi-Object Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aaron Hao Tan, Angus Fung, Daniel Choi, Haitong Wang","submitted_at":"2024-10-01T04:20:54Z","abstract_excerpt":"The Multi-Object Search (MOS) problem involves navigating to a sequence of locations to maximize the likelihood of finding target objects while minimizing travel costs. In this paper, we introduce a novel approach to the MOS problem, called Finder, which leverages vision language models (VLMs) to locate multiple objects across diverse environments. Specifically, our approach introduces multi-channel score maps to track and reason about multiple objects simultaneously during navigation, along with a score map technique that combines scene-level and object-level semantic correlations. Experiment"},"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":"2410.00388","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-01T04:20:54Z","cross_cats_sorted":[],"title_canon_sha256":"cc5dd2ba7f5f304daef0dcae65cff8daee14ecada9ee1653c297425088be1b3d","abstract_canon_sha256":"6fc1fd90cb2744376046f13440c487ebd25cb6d7ebd9e9e0b276e534c7d14b83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:10.387668Z","signature_b64":"C0QxeUuGjmXbVPhm2XrPGeHVvBx50IgsCeMZaXmNtYrK8ejSQOf2jy0IAj/2Z8EflxkM2ap8cLbSq2ANVH0xBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65f7f875df13ec65636f804fc41b9d51de805dfd7ab03e98426a78f3ee23b73f","last_reissued_at":"2026-07-05T12:05:10.387127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:10.387127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Find Everything: A General Vision Language Model Approach to Multi-Object Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aaron Hao Tan, Angus Fung, Daniel Choi, Haitong Wang","submitted_at":"2024-10-01T04:20:54Z","abstract_excerpt":"The Multi-Object Search (MOS) problem involves navigating to a sequence of locations to maximize the likelihood of finding target objects while minimizing travel costs. In this paper, we introduce a novel approach to the MOS problem, called Finder, which leverages vision language models (VLMs) to locate multiple objects across diverse environments. Specifically, our approach introduces multi-channel score maps to track and reason about multiple objects simultaneously during navigation, along with a score map technique that combines scene-level and object-level semantic correlations. Experiment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00388","kind":"arxiv","version":3},"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/2410.00388/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":"2410.00388","created_at":"2026-07-05T12:05:10.387183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.00388v3","created_at":"2026-07-05T12:05:10.387183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00388","created_at":"2026-07-05T12:05:10.387183+00:00"},{"alias_kind":"pith_short_12","alias_value":"MX37Q5O7CPWG","created_at":"2026-07-05T12:05:10.387183+00:00"},{"alias_kind":"pith_short_16","alias_value":"MX37Q5O7CPWGKY3P","created_at":"2026-07-05T12:05:10.387183+00:00"},{"alias_kind":"pith_short_8","alias_value":"MX37Q5O7","created_at":"2026-07-05T12:05:10.387183+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12872","citing_title":"OVAL: Open-Vocabulary Augmented Memory Model for Lifelong Object Goal Navigation","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MX37Q5O7CPWGKY3PQBH4IG45KH","json":"https://pith.science/pith/MX37Q5O7CPWGKY3PQBH4IG45KH.json","graph_json":"https://pith.science/api/pith-number/MX37Q5O7CPWGKY3PQBH4IG45KH/graph.json","events_json":"https://pith.science/api/pith-number/MX37Q5O7CPWGKY3PQBH4IG45KH/events.json","paper":"https://pith.science/paper/MX37Q5O7"},"agent_actions":{"view_html":"https://pith.science/pith/MX37Q5O7CPWGKY3PQBH4IG45KH","download_json":"https://pith.science/pith/MX37Q5O7CPWGKY3PQBH4IG45KH.json","view_paper":"https://pith.science/paper/MX37Q5O7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.00388&json=true","fetch_graph":"https://pith.science/api/pith-number/MX37Q5O7CPWGKY3PQBH4IG45KH/graph.json","fetch_events":"https://pith.science/api/pith-number/MX37Q5O7CPWGKY3PQBH4IG45KH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MX37Q5O7CPWGKY3PQBH4IG45KH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MX37Q5O7CPWGKY3PQBH4IG45KH/action/storage_attestation","attest_author":"https://pith.science/pith/MX37Q5O7CPWGKY3PQBH4IG45KH/action/author_attestation","sign_citation":"https://pith.science/pith/MX37Q5O7CPWGKY3PQBH4IG45KH/action/citation_signature","submit_replication":"https://pith.science/pith/MX37Q5O7CPWGKY3PQBH4IG45KH/action/replication_record"}},"created_at":"2026-07-05T12:05:10.387183+00:00","updated_at":"2026-07-05T12:05:10.387183+00:00"}