{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZQTQUOH7772OCLKJD4KHGOKOT7","short_pith_number":"pith:ZQTQUOH7","schema_version":"1.0","canonical_sha256":"cc270a38fffff4e12d491f1473394e9fe1e120e932d5cbd2a6bd273a1faa3bde","source":{"kind":"arxiv","id":"2605.24622","version":1},"attestation_state":"computed","paper":{"title":"PoseRefer: Pathway-Local Parameters for Semantically Grounded Reference Resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Anna Deichler","submitted_at":"2026-05-23T15:20:04Z","abstract_excerpt":"A robot resolving ``put the cup on that one'' must fuse gesture, language, and scene geometry, yet 3D grounding benchmarks only partially capture this regime: descriptions are written post-hoc, gestures are templated, or pointing is staged for the camera. MM-Conv captures natural co-speech gesture from dyadic VR interaction alongside full-body motion capture and 3D scene graphs. We use it to evaluate pose-language fusion with a decoupled late-fusion architecture in which pose and text pathways share no learned parameters. The two choices together make category, pose, and text contributions eas"},"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":"2605.24622","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-23T15:20:04Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0b6152d1c9798e3795ed5e35daf46a9fc0c9b79061323608ea0f16e99df6e67c","abstract_canon_sha256":"790687c03b1d0d87fed814dcfe78e5edc64c6cbe3b077b2beb4fdc4ca2f5e8fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:49.447398Z","signature_b64":"AIcBkWsZBc9Vhltm2Oh2AN3Hkkp8Gu01wbiKCS7Ifozxdc1VMNjtdWoEE6FZhV8lsEkDfoGE115vF314xNd3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc270a38fffff4e12d491f1473394e9fe1e120e932d5cbd2a6bd273a1faa3bde","last_reissued_at":"2026-05-26T01:03:49.446523Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:49.446523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PoseRefer: Pathway-Local Parameters for Semantically Grounded Reference Resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Anna Deichler","submitted_at":"2026-05-23T15:20:04Z","abstract_excerpt":"A robot resolving ``put the cup on that one'' must fuse gesture, language, and scene geometry, yet 3D grounding benchmarks only partially capture this regime: descriptions are written post-hoc, gestures are templated, or pointing is staged for the camera. MM-Conv captures natural co-speech gesture from dyadic VR interaction alongside full-body motion capture and 3D scene graphs. We use it to evaluate pose-language fusion with a decoupled late-fusion architecture in which pose and text pathways share no learned parameters. The two choices together make category, pose, and text contributions eas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24622","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/2605.24622/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":"2605.24622","created_at":"2026-05-26T01:03:49.446670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24622v1","created_at":"2026-05-26T01:03:49.446670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24622","created_at":"2026-05-26T01:03:49.446670+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQTQUOH7772O","created_at":"2026-05-26T01:03:49.446670+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQTQUOH7772OCLKJ","created_at":"2026-05-26T01:03:49.446670+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQTQUOH7","created_at":"2026-05-26T01:03:49.446670+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/ZQTQUOH7772OCLKJD4KHGOKOT7","json":"https://pith.science/pith/ZQTQUOH7772OCLKJD4KHGOKOT7.json","graph_json":"https://pith.science/api/pith-number/ZQTQUOH7772OCLKJD4KHGOKOT7/graph.json","events_json":"https://pith.science/api/pith-number/ZQTQUOH7772OCLKJD4KHGOKOT7/events.json","paper":"https://pith.science/paper/ZQTQUOH7"},"agent_actions":{"view_html":"https://pith.science/pith/ZQTQUOH7772OCLKJD4KHGOKOT7","download_json":"https://pith.science/pith/ZQTQUOH7772OCLKJD4KHGOKOT7.json","view_paper":"https://pith.science/paper/ZQTQUOH7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24622&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQTQUOH7772OCLKJD4KHGOKOT7/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQTQUOH7772OCLKJD4KHGOKOT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQTQUOH7772OCLKJD4KHGOKOT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQTQUOH7772OCLKJD4KHGOKOT7/action/storage_attestation","attest_author":"https://pith.science/pith/ZQTQUOH7772OCLKJD4KHGOKOT7/action/author_attestation","sign_citation":"https://pith.science/pith/ZQTQUOH7772OCLKJD4KHGOKOT7/action/citation_signature","submit_replication":"https://pith.science/pith/ZQTQUOH7772OCLKJD4KHGOKOT7/action/replication_record"}},"created_at":"2026-05-26T01:03:49.446670+00:00","updated_at":"2026-05-26T01:03:49.446670+00:00"}