{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IBROWF3S4D3Y4DYIEFYEEFASJF","short_pith_number":"pith:IBROWF3S","schema_version":"1.0","canonical_sha256":"4062eb1772e0f78e0f08217042141249436dc01de5b8a38610e770f27848579f","source":{"kind":"arxiv","id":"2412.10726","version":1},"attestation_state":"computed","paper":{"title":"NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chuhao Zhou, Jianfei Yang, Lin Gu, Tao Wu, Yen Heng Wong","submitted_at":"2024-12-14T07:52:24Z","abstract_excerpt":"The rapid advancement of Vision-Language Models (VLMs) has significantly advanced the development of Embodied Question Answering (EQA), enhancing agents' abilities in language understanding and reasoning within complex and realistic scenarios. However, EQA in real-world scenarios remains challenging, as human-posed questions often contain noise that can interfere with an agent's exploration and response, bringing challenges especially for language beginners and non-expert users. To address this, we introduce a NoisyEQA benchmark designed to evaluate an agent's ability to recognize and correct "},"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":"2412.10726","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T07:52:24Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"1bd3726b9e575ec7d7774b736249cc6acacc03ab466a5f405c1ba7c0263918d8","abstract_canon_sha256":"5966f04673e0f1668ab9c2b2b50179fec798feea5489dfa5a92dbd192e9e452a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:20.512016Z","signature_b64":"RCUyU6nHyR419Ji5ntgdHRsTYB0xcBbg1S07kNjrDZBK/aUgg0cM6t+IXlQq4EnEpdEUdEii53pq+jtaqKoPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4062eb1772e0f78e0f08217042141249436dc01de5b8a38610e770f27848579f","last_reissued_at":"2026-07-05T09:49:20.511552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:20.511552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chuhao Zhou, Jianfei Yang, Lin Gu, Tao Wu, Yen Heng Wong","submitted_at":"2024-12-14T07:52:24Z","abstract_excerpt":"The rapid advancement of Vision-Language Models (VLMs) has significantly advanced the development of Embodied Question Answering (EQA), enhancing agents' abilities in language understanding and reasoning within complex and realistic scenarios. However, EQA in real-world scenarios remains challenging, as human-posed questions often contain noise that can interfere with an agent's exploration and response, bringing challenges especially for language beginners and non-expert users. To address this, we introduce a NoisyEQA benchmark designed to evaluate an agent's ability to recognize and correct "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10726","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/2412.10726/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":"2412.10726","created_at":"2026-07-05T09:49:20.511609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10726v1","created_at":"2026-07-05T09:49:20.511609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10726","created_at":"2026-07-05T09:49:20.511609+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBROWF3S4D3Y","created_at":"2026-07-05T09:49:20.511609+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBROWF3S4D3Y4DYI","created_at":"2026-07-05T09:49:20.511609+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBROWF3S","created_at":"2026-07-05T09:49:20.511609+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17639","citing_title":"ERQA-Plus: A Diagnostic Benchmark for Reasoning in Embodied AI","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25813","citing_title":"Extending Embodied Question Answering from Perception to Decision","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2512.24985","citing_title":"DarkQA: Benchmarking Vision-Language Models on Visual-Primitive Question Answering in Low-Light Indoor Scenes","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IBROWF3S4D3Y4DYIEFYEEFASJF","json":"https://pith.science/pith/IBROWF3S4D3Y4DYIEFYEEFASJF.json","graph_json":"https://pith.science/api/pith-number/IBROWF3S4D3Y4DYIEFYEEFASJF/graph.json","events_json":"https://pith.science/api/pith-number/IBROWF3S4D3Y4DYIEFYEEFASJF/events.json","paper":"https://pith.science/paper/IBROWF3S"},"agent_actions":{"view_html":"https://pith.science/pith/IBROWF3S4D3Y4DYIEFYEEFASJF","download_json":"https://pith.science/pith/IBROWF3S4D3Y4DYIEFYEEFASJF.json","view_paper":"https://pith.science/paper/IBROWF3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10726&json=true","fetch_graph":"https://pith.science/api/pith-number/IBROWF3S4D3Y4DYIEFYEEFASJF/graph.json","fetch_events":"https://pith.science/api/pith-number/IBROWF3S4D3Y4DYIEFYEEFASJF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBROWF3S4D3Y4DYIEFYEEFASJF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBROWF3S4D3Y4DYIEFYEEFASJF/action/storage_attestation","attest_author":"https://pith.science/pith/IBROWF3S4D3Y4DYIEFYEEFASJF/action/author_attestation","sign_citation":"https://pith.science/pith/IBROWF3S4D3Y4DYIEFYEEFASJF/action/citation_signature","submit_replication":"https://pith.science/pith/IBROWF3S4D3Y4DYIEFYEEFASJF/action/replication_record"}},"created_at":"2026-07-05T09:49:20.511609+00:00","updated_at":"2026-07-05T09:49:20.511609+00:00"}