{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:75KQI6PNN3YYIVP3VTDJFF63UE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2639de2d6fb832e897bc55e525a5b2602eae3c595c553e3c99b444cb4376e1e2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-09-10T15:27:17Z","title_canon_sha256":"ad68f954c03802baeb34d92646cb27b29c0b631c3f3ebaa8035db25f81cc0e95"},"schema_version":"1.0","source":{"id":"2509.08689","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.08689","created_at":"2026-07-05T12:08:34Z"},{"alias_kind":"arxiv_version","alias_value":"2509.08689v1","created_at":"2026-07-05T12:08:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08689","created_at":"2026-07-05T12:08:34Z"},{"alias_kind":"pith_short_12","alias_value":"75KQI6PNN3YY","created_at":"2026-07-05T12:08:34Z"},{"alias_kind":"pith_short_16","alias_value":"75KQI6PNN3YYIVP3","created_at":"2026-07-05T12:08:34Z"},{"alias_kind":"pith_short_8","alias_value":"75KQI6PN","created_at":"2026-07-05T12:08:34Z"}],"graph_snapshots":[{"event_id":"sha256:2fd9c3b2e4075bdf308cde1a536e642a8dbc7a36db40b1ce9b7a36b3961151f8","target":"graph","created_at":"2026-07-05T12:08:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.08689/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fraser Anderson, Frederik Brudy, George Fitzmaurice, Riccardo Bovo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-09-10T15:27:17Z","title":"Augmenting speech transcripts of VR recordings with gaze, pointing, and visual context for multimodal coreference resolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08689","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:be64854f1254b3db55c3d6ba282c732e5659f22bf83874724ee568a6876918c5","target":"record","created_at":"2026-07-05T12:08:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2639de2d6fb832e897bc55e525a5b2602eae3c595c553e3c99b444cb4376e1e2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-09-10T15:27:17Z","title_canon_sha256":"ad68f954c03802baeb34d92646cb27b29c0b631c3f3ebaa8035db25f81cc0e95"},"schema_version":"1.0","source":{"id":"2509.08689","kind":"arxiv","version":1}},"canonical_sha256":"ff550479ed6ef18455fbacc69297dba1257f4d56941e2079f5896a8890029d29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff550479ed6ef18455fbacc69297dba1257f4d56941e2079f5896a8890029d29","first_computed_at":"2026-07-05T12:08:34.237121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:08:34.237121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aZVkAm+gwouTq4rjkN5YyqKQC6A1Qe8nmy7pCrOSGJC9xq4ik5OeEJXLGpbjcKfXL8c8u8eQ10OwZC1J4NKcCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:08:34.237615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.08689","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be64854f1254b3db55c3d6ba282c732e5659f22bf83874724ee568a6876918c5","sha256:2fd9c3b2e4075bdf308cde1a536e642a8dbc7a36db40b1ce9b7a36b3961151f8"],"state_sha256":"7547565bcf1c05e0783b06c7a92a94789d3e399c64d456ae14de02a8cb25a030"}