{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KPZBK4NJKHYAM72DBOYC6623TE","short_pith_number":"pith:KPZBK4NJ","schema_version":"1.0","canonical_sha256":"53f21571a951f0067f430bb02f7b5b991126150d01867eee66c70b33324b52d2","source":{"kind":"arxiv","id":"2303.05052","version":1},"attestation_state":"computed","paper":{"title":"VQA-based Robotic State Recognition Optimized with Genetic Algorithm","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":"2023-03-09T05:55:50Z","abstract_excerpt":"State recognition of objects and environment in robots has been conducted in various ways. In most cases, this is executed by processing point clouds, learning images with annotations, and using specialized sensors. In contrast, in this study, we propose a state recognition method that applies Visual Question Answering (VQA) in a Pre-Trained Vision-Language Model (PTVLM) trained from a large-scale dataset. By using VQA, it is possible to intuitively describe robotic state recognition in the spoken language. On the other hand, there are various possible ways to ask about the same event, and the"},"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":"2303.05052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-03-09T05:55:50Z","cross_cats_sorted":[],"title_canon_sha256":"4487616e1d2ed62ddbaee23a04999a9018ebe54c673776a35925e3ef99b96a90","abstract_canon_sha256":"b652ff74512accdc69980b2668845b35d73da7b506cf00b2b24ff31b19f91f4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:22.511041Z","signature_b64":"RchfuCS3B7UaWd41CX7wMnHq5heCNslaxqbdVRxISiwOxM7e0xi28OslRf2kxpNSOgfqRbY2QAlDkARuPJpoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53f21571a951f0067f430bb02f7b5b991126150d01867eee66c70b33324b52d2","last_reissued_at":"2026-07-05T07:25:22.510453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:22.510453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VQA-based Robotic State Recognition Optimized with Genetic Algorithm","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":"2023-03-09T05:55:50Z","abstract_excerpt":"State recognition of objects and environment in robots has been conducted in various ways. In most cases, this is executed by processing point clouds, learning images with annotations, and using specialized sensors. In contrast, in this study, we propose a state recognition method that applies Visual Question Answering (VQA) in a Pre-Trained Vision-Language Model (PTVLM) trained from a large-scale dataset. By using VQA, it is possible to intuitively describe robotic state recognition in the spoken language. On the other hand, there are various possible ways to ask about the same event, and the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05052","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/2303.05052/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":"2303.05052","created_at":"2026-07-05T07:25:22.510510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.05052v1","created_at":"2026-07-05T07:25:22.510510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05052","created_at":"2026-07-05T07:25:22.510510+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPZBK4NJKHYA","created_at":"2026-07-05T07:25:22.510510+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPZBK4NJKHYAM72D","created_at":"2026-07-05T07:25:22.510510+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPZBK4NJ","created_at":"2026-07-05T07:25:22.510510+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/KPZBK4NJKHYAM72DBOYC6623TE","json":"https://pith.science/pith/KPZBK4NJKHYAM72DBOYC6623TE.json","graph_json":"https://pith.science/api/pith-number/KPZBK4NJKHYAM72DBOYC6623TE/graph.json","events_json":"https://pith.science/api/pith-number/KPZBK4NJKHYAM72DBOYC6623TE/events.json","paper":"https://pith.science/paper/KPZBK4NJ"},"agent_actions":{"view_html":"https://pith.science/pith/KPZBK4NJKHYAM72DBOYC6623TE","download_json":"https://pith.science/pith/KPZBK4NJKHYAM72DBOYC6623TE.json","view_paper":"https://pith.science/paper/KPZBK4NJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.05052&json=true","fetch_graph":"https://pith.science/api/pith-number/KPZBK4NJKHYAM72DBOYC6623TE/graph.json","fetch_events":"https://pith.science/api/pith-number/KPZBK4NJKHYAM72DBOYC6623TE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPZBK4NJKHYAM72DBOYC6623TE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPZBK4NJKHYAM72DBOYC6623TE/action/storage_attestation","attest_author":"https://pith.science/pith/KPZBK4NJKHYAM72DBOYC6623TE/action/author_attestation","sign_citation":"https://pith.science/pith/KPZBK4NJKHYAM72DBOYC6623TE/action/citation_signature","submit_replication":"https://pith.science/pith/KPZBK4NJKHYAM72DBOYC6623TE/action/replication_record"}},"created_at":"2026-07-05T07:25:22.510510+00:00","updated_at":"2026-07-05T07:25:22.510510+00:00"}