{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2OOILN45XXRMS5UTQQG2VCJRHC","short_pith_number":"pith:2OOILN45","schema_version":"1.0","canonical_sha256":"d39c85b79dbde2c97693840daa893138982c6a45fe900b2ff67a6cd97cf41c71","source":{"kind":"arxiv","id":"2508.16143","version":1},"attestation_state":"computed","paper":{"title":"Take That for Me: Multimodal Exophora Resolution with Interactive Questioning for Ambiguous Out-of-View Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Akira Oyama, Akira Taniguchi, Shoichi Hasegawa, Tadahiro Taniguchi, Yoshinobu Hagiwara","submitted_at":"2025-08-22T07:09:06Z","abstract_excerpt":"Daily life support robots must interpret ambiguous verbal instructions involving demonstratives such as ``Bring me that cup,'' even when objects or users are out of the robot's view. Existing approaches to exophora resolution primarily rely on visual data and thus fail in real-world scenarios where the object or user is not visible. We propose Multimodal Interactive Exophora resolution with user Localization (MIEL), which is a multimodal exophora resolution framework leveraging sound source localization (SSL), semantic mapping, visual-language models (VLMs), and interactive questioning with GP"},"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":"2508.16143","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-22T07:09:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"96739fe9ea4332fd34db99b281553effd94fc909c25ed0935543aa763ef9176b","abstract_canon_sha256":"be001605dd3d7ee034344993f11ad833c50ef0cd3745dc471c4c8d7754c9bfb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:42.762225Z","signature_b64":"JfmigbmouHCq6uccAFeZEXopHSaW3hJ/UJ3AO+olYGixt6mRwIshOFMkqIFpMN6Ol7vckXHw+WG+gLDTqkdLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d39c85b79dbde2c97693840daa893138982c6a45fe900b2ff67a6cd97cf41c71","last_reissued_at":"2026-07-05T11:57:42.761755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:42.761755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Take That for Me: Multimodal Exophora Resolution with Interactive Questioning for Ambiguous Out-of-View Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Akira Oyama, Akira Taniguchi, Shoichi Hasegawa, Tadahiro Taniguchi, Yoshinobu Hagiwara","submitted_at":"2025-08-22T07:09:06Z","abstract_excerpt":"Daily life support robots must interpret ambiguous verbal instructions involving demonstratives such as ``Bring me that cup,'' even when objects or users are out of the robot's view. Existing approaches to exophora resolution primarily rely on visual data and thus fail in real-world scenarios where the object or user is not visible. We propose Multimodal Interactive Exophora resolution with user Localization (MIEL), which is a multimodal exophora resolution framework leveraging sound source localization (SSL), semantic mapping, visual-language models (VLMs), and interactive questioning with GP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16143","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/2508.16143/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":"2508.16143","created_at":"2026-07-05T11:57:42.761812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16143v1","created_at":"2026-07-05T11:57:42.761812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16143","created_at":"2026-07-05T11:57:42.761812+00:00"},{"alias_kind":"pith_short_12","alias_value":"2OOILN45XXRM","created_at":"2026-07-05T11:57:42.761812+00:00"},{"alias_kind":"pith_short_16","alias_value":"2OOILN45XXRMS5UT","created_at":"2026-07-05T11:57:42.761812+00:00"},{"alias_kind":"pith_short_8","alias_value":"2OOILN45","created_at":"2026-07-05T11:57:42.761812+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/2OOILN45XXRMS5UTQQG2VCJRHC","json":"https://pith.science/pith/2OOILN45XXRMS5UTQQG2VCJRHC.json","graph_json":"https://pith.science/api/pith-number/2OOILN45XXRMS5UTQQG2VCJRHC/graph.json","events_json":"https://pith.science/api/pith-number/2OOILN45XXRMS5UTQQG2VCJRHC/events.json","paper":"https://pith.science/paper/2OOILN45"},"agent_actions":{"view_html":"https://pith.science/pith/2OOILN45XXRMS5UTQQG2VCJRHC","download_json":"https://pith.science/pith/2OOILN45XXRMS5UTQQG2VCJRHC.json","view_paper":"https://pith.science/paper/2OOILN45","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16143&json=true","fetch_graph":"https://pith.science/api/pith-number/2OOILN45XXRMS5UTQQG2VCJRHC/graph.json","fetch_events":"https://pith.science/api/pith-number/2OOILN45XXRMS5UTQQG2VCJRHC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2OOILN45XXRMS5UTQQG2VCJRHC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2OOILN45XXRMS5UTQQG2VCJRHC/action/storage_attestation","attest_author":"https://pith.science/pith/2OOILN45XXRMS5UTQQG2VCJRHC/action/author_attestation","sign_citation":"https://pith.science/pith/2OOILN45XXRMS5UTQQG2VCJRHC/action/citation_signature","submit_replication":"https://pith.science/pith/2OOILN45XXRMS5UTQQG2VCJRHC/action/replication_record"}},"created_at":"2026-07-05T11:57:42.761812+00:00","updated_at":"2026-07-05T11:57:42.761812+00:00"}