{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "gordon-kembhavi-et-al-iqa-himn-spatial-memory-2017", "title": "IQA: asking questions that require an agent to look and act", "summary": "“Is there an apple in the refrigerator?” cannot always be answered from the first camera image. The agent may need to move, open the door and remember what it saw. Gordon and colleagues introduce an interactive question-answering task and a hierarchical system that divides planning, navigation, detection, manipulation and answering. A spatial memory stores observations at locations rather than forcing a single recurrent state to remember everything. Their IQADATA resource supplies automatically generated existence, counting and spatial-relation questions in simulated kitchens. The contribution combines this task design with the specific memory and controller architecture, without separately counting the underlying AI2-THOR engine.", "boundary": "The original split uses 25 training kitchens and five test kitchens; questions follow templates rather than unrestricted human conversation. Training uses simulator-provided supervision, and some reported results additionally use ideal detections or navigation. Those results must be distinguished from learned-perception results. The learned system does not outperform simple answer-frequency guessing on every question type. No real-house robot experiment or general language-understanding guarantee is established.", "area": "Embodied question answering and hierarchical agents", "topic": "Artificial intelligence", "year": 2017, "lane": "HUMAN", "result": "ALGORITHM", "package_id": "gordon-kembhavi-et-al-iqa-himn-spatial-memory-2017", "target": { "record_id": "urn:uuid:54b8ec63-83ba-44d0-a802-6bdf5f636ae6", "version": 1, "content_hash": "sha256:9d2150282c8ee5cfa7c83c081101c494082a4b3ffeb4f620ce81946eebe1ec43" }, "humans": [ "Daniel Gordon", "Aniruddha Kembhavi", "Mohammad Rastegari", "Joseph Redmon", "Dieter Fox", "Ali Farhadi" ], "authors_complete": true, "human_role_note": "Source-listed human researchers and engineers for the exact method or resource. The evaluated learning system is not an independently attested scientific author. Earlier methods, funding and data-collection roles remain separate. Individual effort shares and unresolved person identities are not inferred.", "agents": [], "related": [], "subresults": [], "scientific_assessment": { "source_review": "SOURCE_CURATED", "scientific_review": "NOT_REVIEWED_BY_WRS", "formal_replay": "NOT_RUN", "provider_attestation": "NONE" }, "sources": [ { "id": "cur20261017-arxiv-1712-03316v1", "title": "IQA: Visual Question Answering in Interactive Environments", "url": "https://arxiv.org/abs/1712.03316v1", "date": "2017-12-09" } ], "points": "75000", "published_grade": { "id": "gordon-kembhavi-et-al-iqa-himn-spatial-memory-2017", "entry_id": "gordon-kembhavi-et-al-iqa-himn-spatial-memory-2017", "band": "A", "modifier": null, "target": { "record_id": "urn:uuid:54b8ec63-83ba-44d0-a802-6bdf5f636ae6", "version": 1, "content_hash": "sha256:9d2150282c8ee5cfa7c83c081101c494082a4b3ffeb4f620ce81946eebe1ec43" }, "what_changed": "“Is there an apple in the refrigerator?” cannot always be answered from the first camera image. The agent may need to move, open the door and remember what it saw. Gordon and colleagues introduce an interactive question-answering task and a hierarchical system that divides planning, navigation, detection, manipulation and answering. A spatial memory stores observations at locations rather than forcing a single recurrent state to remember everything. Their IQADATA resource supplies automatically generated existence, counting and spatial-relation questions in simulated kitchens. The contribution combines this task design with the specific memory and controller architecture, without separately counting the underlying AI2-THOR engine.", "scope": "“Is there an apple in the refrigerator?” cannot always be answered from the first camera image. The agent may need to move, open the door and remember what it saw. Gordon and colleagues introduce an interactive question-answering task and a hierarchical system that divides planning, navigation, detection, manipulation and answering. A spatial memory stores observations at locations rather than forcing a single recurrent state to remember everything. Their IQADATA resource supplies automatically generated existence, counting and spatial-relation questions in simulated kitchens. The contribution combines this task design with the specific memory and controller architecture, without separately counting the underlying AI2-THOR engine. The original split uses 25 training kitchens and five test kitchens; questions follow templates rather than unrestricted human conversation. Training uses simulator-provided supervision, and some reported results additionally use ideal detections or navigation. Those results must be distinguished from learned-perception results. The learned system does not outperform simple answer-frequency guessing on every question type. No real-house robot experiment or general language-understanding guarantee is established.", "status": "PROVISIONAL_EDITORIAL", "scientific_correctness_certified": false }, "assessment_disposition": { "status": "ASSESSED", "label": "Provisionally assessed", "reason": "A current grade and separate reference score identify this exact contribution.", "target": { "record_id": "urn:uuid:54b8ec63-83ba-44d0-a802-6bdf5f636ae6", "version": 1, "content_hash": "sha256:9d2150282c8ee5cfa7c83c081101c494082a4b3ffeb4f620ce81946eebe1ec43" }, "edition": "ratings-e039106f30dec177" } }, "version": { "kind": "PUBLIC_RECORD_VIEW", "previous": null, "published_at": "2026-10-23T00:00:00Z", "publisher": { "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33", "role": "WRS_EDITORIAL_PUBLICATION" }, "record": { "contributors": [ { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Daniel Gordon", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "IQA: Visual Question Answering in Interactive Environments", "url": "https://arxiv.org/abs/1712.03316v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Aniruddha Kembhavi", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "IQA: Visual Question Answering in Interactive Environments", "url": "https://arxiv.org/abs/1712.03316v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Mohammad Rastegari", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "IQA: Visual Question Answering in Interactive Environments", "url": "https://arxiv.org/abs/1712.03316v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Joseph Redmon", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "IQA: Visual Question Answering in Interactive Environments", "url": "https://arxiv.org/abs/1712.03316v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Dieter Fox", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "IQA: Visual Question Answering in Interactive Environments", "url": "https://arxiv.org/abs/1712.03316v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ali Farhadi", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "IQA: Visual Question Answering in Interactive Environments", "url": "https://arxiv.org/abs/1712.03316v1" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "IQA: Visual Question Answering in Interactive Environments", "url": "https://arxiv.org/abs/1712.03316v1" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "The original split uses 25 training kitchens and five test kitchens; questions follow templates rather than unrestricted human conversation. Training uses simulator-provided supervision, and some reported results additionally use ideal detections or navigation. Those results must be distinguished from learned-perception results. The learned system does not outperform simple answer-frequency guessing on every question type. No real-house robot experiment or general language-understanding guarantee is established.", "domain": "Embodied question answering and hierarchical agents" }, "sources": [ { "citation": "IQA: Visual Question Answering in Interactive Environments", "url": "https://arxiv.org/abs/1712.03316v1" } ], "statement": "# IQA: asking questions that require an agent to look and act\n\n“Is there an apple in the refrigerator?” cannot always be answered from the first camera image. The agent may need to move, open the door and remember what it saw. Gordon and colleagues introduce an interactive question-answering task and a hierarchical system that divides planning, navigation, detection, manipulation and answering. A spatial memory stores observations at locations rather than forcing a single recurrent state to remember everything. Their IQADATA resource supplies automatically generated existence, counting and spatial-relation questions in simulated kitchens. The contribution combines this task design with the specific memory and controller architecture, without separately counting the underlying AI2-THOR engine.\n\n## Scientific scope\n\nThe original split uses 25 training kitchens and five test kitchens; questions follow templates rather than unrestricted human conversation. Training uses simulator-provided supervision, and some reported results additionally use ideal detections or navigation. Those results must be distinguished from learned-perception results. The learned system does not outperform simple answer-frequency guessing on every question type. No real-house robot experiment or general language-understanding guarantee is established.\n\n## Reading status\n\nThis is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.\n\n## People and systems\n\nDaniel Gordon; Aniruddha Kembhavi; Mohammad Rastegari; Joseph Redmon; Dieter Fox; Ali Farhadi\n\nSource-listed human researchers and engineers for the exact method or resource. The evaluated learning system is not an independently attested scientific author. Earlier methods, funding and data-collection roles remain separate. Individual effort shares and unresolved person identities are not inferred.\n\n\n\n## Original sources\n\n- [IQA: Visual Question Answering in Interactive Environments](https://arxiv.org/abs/1712.03316v1)\n", "summary": "“Is there an apple in the refrigerator?” cannot always be answered from the first camera image. The agent may need to move, open the door and remember what it saw. Gordon and colleagues introduce an interactive question-answering task and a hierarchical system that divides planning, navigation, detection, manipulation and answering. A spatial memory stores observations at locations rather than forcing a single recurrent state to remember everything. Their IQADATA resource supplies automatically generated existence, counting and spatial-relation questions in simulated kitchens. The contribution combines this task design with the specific memory and controller architecture, without separately counting the underlying AI2-THOR engine.", "title": "IQA: asking questions that require an agent to look and act" }, "record_id": "urn:uuid:54b8ec63-83ba-44d0-a802-6bdf5f636ae6", "version": 1, "source_ref": { "record_id": "urn:uuid:54b8ec63-83ba-44d0-a802-6bdf5f636ae6", "version": 1, "content_hash": "sha256:9d2150282c8ee5cfa7c83c081101c494082a4b3ffeb4f620ce81946eebe1ec43" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:d27673b8f752587e057287f38dbade54be43d368daac3e149e6ad2c733e28017" }, "target": { "record_id": "urn:uuid:54b8ec63-83ba-44d0-a802-6bdf5f636ae6", "version": 1, "content_hash": "sha256:9d2150282c8ee5cfa7c83c081101c494082a4b3ffeb4f620ce81946eebe1ec43" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "gordon-kembhavi-et-al-iqa-himn-spatial-memory-2017", "entry_id": "gordon-kembhavi-et-al-iqa-himn-spatial-memory-2017", "revision": 1, "title": "IQA: asking questions that require an agent to look and act", "context": "Embodied question answering and hierarchical agents", "track": "Reusable scientific method, experimental result or historical framework", "band": "A", "modifier": null, "status": "PROVISIONAL_EDITORIAL", "assessed_on": "2026-10-23", "evidence_cutoff": "2026-10-23", "achievement_state": "SUPPORTED_SCOPED_RESULT", "what_changed": "“Is there an apple in the refrigerator?” cannot always be answered from the first camera image. The agent may need to move, open the door and remember what it saw. Gordon and colleagues introduce an interactive question-answering task and a hierarchical system that divides planning, navigation, detection, manipulation and answering. A spatial memory stores observations at locations rather than forcing a single recurrent state to remember everything. Their IQADATA resource supplies automatically generated existence, counting and spatial-relation questions in simulated kitchens. The contribution combines this task design with the specific memory and controller architecture, without separately counting the underlying AI2-THOR engine.", "scope": "“Is there an apple in the refrigerator?” cannot always be answered from the first camera image. The agent may need to move, open the door and remember what it saw. Gordon and colleagues introduce an interactive question-answering task and a hierarchical system that divides planning, navigation, detection, manipulation and answering. A spatial memory stores observations at locations rather than forcing a single recurrent state to remember everything. Their IQADATA resource supplies automatically generated existence, counting and spatial-relation questions in simulated kitchens. The contribution combines this task design with the specific memory and controller architecture, without separately counting the underlying AI2-THOR engine. The original split uses 25 training kitchens and five test kitchens; questions follow templates rather than unrestricted human conversation. Training uses simulator-provided supervision, and some reported results additionally use ideal detections or navigation. Those results must be distinguished from learned-perception results. The learned system does not outperform simple answer-frequency guessing on every question type. No real-house robot experiment or general language-understanding guarantee is established.", "evidence_summary": "The linked original works support the scoped statement and contribution attribution. WRS has not independently replayed experiments or reconstructed a full mathematical proof. The original split uses 25 training kitchens and five test kitchens; questions follow templates rather than unrestricted human conversation. Training uses simulator-provided supervision, and some reported results additionally use ideal detections or navigation. Those results must be distinguished from learned-perception results. The learned system does not outperform simple answer-frequency guessing on every question type. No real-house robot experiment or general language-understanding guarantee is established.", "references": [ { "title": "IQA: Visual Question Answering in Interactive Environments", "url": "https://arxiv.org/abs/1712.03316v1", "locator": "Original scoped contribution, statement/method and evidence limits; source-specific attribution retained." } ], "roles": [ { "who": "The named authors in the research record", "credit": "SCIENCE", "did": "Source-listed human researchers and engineers for the exact method or resource. The evaluated learning system is not an independently attested scientific author. Earlier methods, funding and data-collection roles remain separate. Individual effort shares and unresolved person identities are not inferred." } ], "target": { "record_id": "urn:uuid:54b8ec63-83ba-44d0-a802-6bdf5f636ae6", "version": 1, "content_hash": "sha256:9d2150282c8ee5cfa7c83c081101c494082a4b3ffeb4f620ce81946eebe1ec43" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "75000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }