{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:75KQI6PNN3YYIVP3VTDJFF63UE","short_pith_number":"pith:75KQI6PN","schema_version":"1.0","canonical_sha256":"ff550479ed6ef18455fbacc69297dba1257f4d56941e2079f5896a8890029d29","source":{"kind":"arxiv","id":"2509.08689","version":1},"attestation_state":"computed","paper":{"title":"Augmenting speech transcripts of VR recordings with gaze, pointing, and visual context for multimodal coreference resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Fraser Anderson, Frederik Brudy, George Fitzmaurice, Riccardo Bovo","submitted_at":"2025-09-10T15:27:17Z","abstract_excerpt":"Understanding transcripts of immersive multimodal conversations is challenging because speakers frequently rely on visual context and non-verbal cues, such as gestures and visual attention, which are not captured in speech alone. This lack of information makes coreferences resolution-the task of linking ambiguous expressions like ``it'' or ``there'' to their intended referents-particularly challenging. In this paper we present a system that augments VR speech transcript with eye-tracking laser pointing data, and scene metadata to generate textual descriptions of non-verbal communication and th"},"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":"2509.08689","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-09-10T15:27:17Z","cross_cats_sorted":[],"title_canon_sha256":"ad68f954c03802baeb34d92646cb27b29c0b631c3f3ebaa8035db25f81cc0e95","abstract_canon_sha256":"2639de2d6fb832e897bc55e525a5b2602eae3c595c553e3c99b444cb4376e1e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:34.237615Z","signature_b64":"aZVkAm+gwouTq4rjkN5YyqKQC6A1Qe8nmy7pCrOSGJC9xq4ik5OeEJXLGpbjcKfXL8c8u8eQ10OwZC1J4NKcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff550479ed6ef18455fbacc69297dba1257f4d56941e2079f5896a8890029d29","last_reissued_at":"2026-07-05T12:08:34.237121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:34.237121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Augmenting speech transcripts of VR recordings with gaze, pointing, and visual context for multimodal coreference resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Fraser Anderson, Frederik Brudy, George Fitzmaurice, Riccardo Bovo","submitted_at":"2025-09-10T15:27:17Z","abstract_excerpt":"Understanding transcripts of immersive multimodal conversations is challenging because speakers frequently rely on visual context and non-verbal cues, such as gestures and visual attention, which are not captured in speech alone. This lack of information makes coreferences resolution-the task of linking ambiguous expressions like ``it'' or ``there'' to their intended referents-particularly challenging. In this paper we present a system that augments VR speech transcript with eye-tracking laser pointing data, and scene metadata to generate textual descriptions of non-verbal communication and th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08689","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/2509.08689/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":"2509.08689","created_at":"2026-07-05T12:08:34.237182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08689v1","created_at":"2026-07-05T12:08:34.237182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08689","created_at":"2026-07-05T12:08:34.237182+00:00"},{"alias_kind":"pith_short_12","alias_value":"75KQI6PNN3YY","created_at":"2026-07-05T12:08:34.237182+00:00"},{"alias_kind":"pith_short_16","alias_value":"75KQI6PNN3YYIVP3","created_at":"2026-07-05T12:08:34.237182+00:00"},{"alias_kind":"pith_short_8","alias_value":"75KQI6PN","created_at":"2026-07-05T12:08:34.237182+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/75KQI6PNN3YYIVP3VTDJFF63UE","json":"https://pith.science/pith/75KQI6PNN3YYIVP3VTDJFF63UE.json","graph_json":"https://pith.science/api/pith-number/75KQI6PNN3YYIVP3VTDJFF63UE/graph.json","events_json":"https://pith.science/api/pith-number/75KQI6PNN3YYIVP3VTDJFF63UE/events.json","paper":"https://pith.science/paper/75KQI6PN"},"agent_actions":{"view_html":"https://pith.science/pith/75KQI6PNN3YYIVP3VTDJFF63UE","download_json":"https://pith.science/pith/75KQI6PNN3YYIVP3VTDJFF63UE.json","view_paper":"https://pith.science/paper/75KQI6PN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08689&json=true","fetch_graph":"https://pith.science/api/pith-number/75KQI6PNN3YYIVP3VTDJFF63UE/graph.json","fetch_events":"https://pith.science/api/pith-number/75KQI6PNN3YYIVP3VTDJFF63UE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75KQI6PNN3YYIVP3VTDJFF63UE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75KQI6PNN3YYIVP3VTDJFF63UE/action/storage_attestation","attest_author":"https://pith.science/pith/75KQI6PNN3YYIVP3VTDJFF63UE/action/author_attestation","sign_citation":"https://pith.science/pith/75KQI6PNN3YYIVP3VTDJFF63UE/action/citation_signature","submit_replication":"https://pith.science/pith/75KQI6PNN3YYIVP3VTDJFF63UE/action/replication_record"}},"created_at":"2026-07-05T12:08:34.237182+00:00","updated_at":"2026-07-05T12:08:34.237182+00:00"}