{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5YFVPIPPKYIT5XWTGI2MJ35O5O","short_pith_number":"pith:5YFVPIPP","schema_version":"1.0","canonical_sha256":"ee0b57a1ef56113eded33234c4efaeeb949e29fed72cb33a547ca9285f527c07","source":{"kind":"arxiv","id":"2403.15941","version":3},"attestation_state":"computed","paper":{"title":"Explore until Confident: Efficient Exploration for Embodied Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Allen Z. Ren, Anirudha Majumdar, Anushri Dixit, Dorsa Sadigh, Jaden Clark, Masha Itkina","submitted_at":"2024-03-23T22:04:03Z","abstract_excerpt":"We consider the problem of Embodied Question Answering (EQA), which refers to settings where an embodied agent such as a robot needs to actively explore an environment to gather information until it is confident about the answer to a question. In this work, we leverage the strong semantic reasoning capabilities of large vision-language models (VLMs) to efficiently explore and answer such questions. However, there are two main challenges when using VLMs in EQA: they do not have an internal memory for mapping the scene to be able to plan how to explore over time, and their confidence can be misc"},"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":"2403.15941","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-23T22:04:03Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"a12fc797ca06bdd185d8bb2c4126329b58343eae0fe6bbcd93bca7d9820363d2","abstract_canon_sha256":"6b34ee1e4f3742a6dda9a0911daf0357d4a6823133955a44210e65769632c472"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:01.117784Z","signature_b64":"l9dy0xiVohYcHe0Awf0AaXEUACIS6QDds+4mTmFC/+omVLE3kmjKLSAoavpPPla24IRLGUoiCUmB6oboTH0pBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee0b57a1ef56113eded33234c4efaeeb949e29fed72cb33a547ca9285f527c07","last_reissued_at":"2026-07-05T08:41:01.117220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:01.117220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explore until Confident: Efficient Exploration for Embodied Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Allen Z. Ren, Anirudha Majumdar, Anushri Dixit, Dorsa Sadigh, Jaden Clark, Masha Itkina","submitted_at":"2024-03-23T22:04:03Z","abstract_excerpt":"We consider the problem of Embodied Question Answering (EQA), which refers to settings where an embodied agent such as a robot needs to actively explore an environment to gather information until it is confident about the answer to a question. In this work, we leverage the strong semantic reasoning capabilities of large vision-language models (VLMs) to efficiently explore and answer such questions. However, there are two main challenges when using VLMs in EQA: they do not have an internal memory for mapping the scene to be able to plan how to explore over time, and their confidence can be misc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15941","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/2403.15941/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":"2403.15941","created_at":"2026-07-05T08:41:01.117290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15941v3","created_at":"2026-07-05T08:41:01.117290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15941","created_at":"2026-07-05T08:41:01.117290+00:00"},{"alias_kind":"pith_short_12","alias_value":"5YFVPIPPKYIT","created_at":"2026-07-05T08:41:01.117290+00:00"},{"alias_kind":"pith_short_16","alias_value":"5YFVPIPPKYIT5XWT","created_at":"2026-07-05T08:41:01.117290+00:00"},{"alias_kind":"pith_short_8","alias_value":"5YFVPIPP","created_at":"2026-07-05T08:41:01.117290+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26046","citing_title":"RoboAtlas: Contextual Active SLAM","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24068","citing_title":"ObsGraph: Hierarchical Observation Representation for Embodied Reasoning and Exploration","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19383","citing_title":"3D Scene Graphs: Open Challenges and Future Directions","ref_index":122,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30111","citing_title":"Automating the Design of Embodied Agent Architectures","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29222","citing_title":"CORE Planner: Contextual-memory Oriented Reinforcement-learning in Unknown Environments for Robot Navigation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25813","citing_title":"Extending Embodied Question Answering from Perception to Decision","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23165","citing_title":"Autonomous Frontier-Based Exploration with VLM Guidance","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10118","citing_title":"Plan in Sandbox, Navigate in Open Worlds: Learning Physics-Grounded Abstracted Experience for Embodied Navigation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5YFVPIPPKYIT5XWTGI2MJ35O5O","json":"https://pith.science/pith/5YFVPIPPKYIT5XWTGI2MJ35O5O.json","graph_json":"https://pith.science/api/pith-number/5YFVPIPPKYIT5XWTGI2MJ35O5O/graph.json","events_json":"https://pith.science/api/pith-number/5YFVPIPPKYIT5XWTGI2MJ35O5O/events.json","paper":"https://pith.science/paper/5YFVPIPP"},"agent_actions":{"view_html":"https://pith.science/pith/5YFVPIPPKYIT5XWTGI2MJ35O5O","download_json":"https://pith.science/pith/5YFVPIPPKYIT5XWTGI2MJ35O5O.json","view_paper":"https://pith.science/paper/5YFVPIPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15941&json=true","fetch_graph":"https://pith.science/api/pith-number/5YFVPIPPKYIT5XWTGI2MJ35O5O/graph.json","fetch_events":"https://pith.science/api/pith-number/5YFVPIPPKYIT5XWTGI2MJ35O5O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5YFVPIPPKYIT5XWTGI2MJ35O5O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5YFVPIPPKYIT5XWTGI2MJ35O5O/action/storage_attestation","attest_author":"https://pith.science/pith/5YFVPIPPKYIT5XWTGI2MJ35O5O/action/author_attestation","sign_citation":"https://pith.science/pith/5YFVPIPPKYIT5XWTGI2MJ35O5O/action/citation_signature","submit_replication":"https://pith.science/pith/5YFVPIPPKYIT5XWTGI2MJ35O5O/action/replication_record"}},"created_at":"2026-07-05T08:41:01.117290+00:00","updated_at":"2026-07-05T08:41:01.117290+00:00"}