{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:O6CMLCE4JDELEVTJI6NIRIX4NK","short_pith_number":"pith:O6CMLCE4","schema_version":"1.0","canonical_sha256":"7784c5889c48c8b25669479a88a2fc6a8c59a00e62bd015e2dd2a4f2d230954c","source":{"kind":"arxiv","id":"2310.16405","version":1},"attestation_state":"computed","paper":{"title":"Binary State Recognition by Robots using Visual Question Answering of Pre-Trained Vision-Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Kei Okada, Kento Kawaharazuka, Masayuki Inaba, Naoaki Kanazawa, Yoshiki Obinata","submitted_at":"2023-10-25T06:44:22Z","abstract_excerpt":"Recognition of the current state is indispensable for the operation of a robot. There are various states to be recognized, such as whether an elevator door is open or closed, whether an object has been grasped correctly, and whether the TV is turned on or off. Until now, these states have been recognized by programmatically describing the state of a point cloud or raw image, by annotating and learning images, by using special sensors, etc. In contrast to these methods, we apply Visual Question Answering (VQA) from a Pre-Trained Vision-Language Model (PTVLM) trained on a large-scale dataset, to"},"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":"2310.16405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-25T06:44:22Z","cross_cats_sorted":[],"title_canon_sha256":"9695d9241abe7f2460c7ef66beb49c3e6c62c45217103334b6ff97bb047803ec","abstract_canon_sha256":"dd9f608494cd8a706e70859067c5afcbfb7577ac19910d74f6e4eebad9a09c09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:57.008378Z","signature_b64":"FmEMU3/q/XMOGLERYT++f6owcUuk74oVqC96gme8+CtTaoVpi7komuRQfs1p+vWvToF9/SU41TS4RNFkSAsyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7784c5889c48c8b25669479a88a2fc6a8c59a00e62bd015e2dd2a4f2d230954c","last_reissued_at":"2026-07-05T07:04:57.007973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:57.007973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Binary State Recognition by Robots using Visual Question Answering of Pre-Trained Vision-Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Kei Okada, Kento Kawaharazuka, Masayuki Inaba, Naoaki Kanazawa, Yoshiki Obinata","submitted_at":"2023-10-25T06:44:22Z","abstract_excerpt":"Recognition of the current state is indispensable for the operation of a robot. There are various states to be recognized, such as whether an elevator door is open or closed, whether an object has been grasped correctly, and whether the TV is turned on or off. Until now, these states have been recognized by programmatically describing the state of a point cloud or raw image, by annotating and learning images, by using special sensors, etc. In contrast to these methods, we apply Visual Question Answering (VQA) from a Pre-Trained Vision-Language Model (PTVLM) trained on a large-scale dataset, to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16405","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/2310.16405/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":"2310.16405","created_at":"2026-07-05T07:04:57.008027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.16405v1","created_at":"2026-07-05T07:04:57.008027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16405","created_at":"2026-07-05T07:04:57.008027+00:00"},{"alias_kind":"pith_short_12","alias_value":"O6CMLCE4JDEL","created_at":"2026-07-05T07:04:57.008027+00:00"},{"alias_kind":"pith_short_16","alias_value":"O6CMLCE4JDELEVTJ","created_at":"2026-07-05T07:04:57.008027+00:00"},{"alias_kind":"pith_short_8","alias_value":"O6CMLCE4","created_at":"2026-07-05T07:04:57.008027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O6CMLCE4JDELEVTJI6NIRIX4NK","json":"https://pith.science/pith/O6CMLCE4JDELEVTJI6NIRIX4NK.json","graph_json":"https://pith.science/api/pith-number/O6CMLCE4JDELEVTJI6NIRIX4NK/graph.json","events_json":"https://pith.science/api/pith-number/O6CMLCE4JDELEVTJI6NIRIX4NK/events.json","paper":"https://pith.science/paper/O6CMLCE4"},"agent_actions":{"view_html":"https://pith.science/pith/O6CMLCE4JDELEVTJI6NIRIX4NK","download_json":"https://pith.science/pith/O6CMLCE4JDELEVTJI6NIRIX4NK.json","view_paper":"https://pith.science/paper/O6CMLCE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.16405&json=true","fetch_graph":"https://pith.science/api/pith-number/O6CMLCE4JDELEVTJI6NIRIX4NK/graph.json","fetch_events":"https://pith.science/api/pith-number/O6CMLCE4JDELEVTJI6NIRIX4NK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O6CMLCE4JDELEVTJI6NIRIX4NK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O6CMLCE4JDELEVTJI6NIRIX4NK/action/storage_attestation","attest_author":"https://pith.science/pith/O6CMLCE4JDELEVTJI6NIRIX4NK/action/author_attestation","sign_citation":"https://pith.science/pith/O6CMLCE4JDELEVTJI6NIRIX4NK/action/citation_signature","submit_replication":"https://pith.science/pith/O6CMLCE4JDELEVTJI6NIRIX4NK/action/replication_record"}},"created_at":"2026-07-05T07:04:57.008027+00:00","updated_at":"2026-07-05T07:04:57.008027+00:00"}