{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FQJ2THGLXUA6AVEU62RRY73OYM","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":"5b80f4584159e801a307386b52d221de0a574b84d20121f9d9e92a3578978a05","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T22:44:09Z","title_canon_sha256":"528f88999a8cc4173fd76c20a2c87c7304dcb828e666744228185a8a18df6ba0"},"schema_version":"1.0","source":{"id":"2605.21796","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21796","created_at":"2026-05-22T01:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21796v1","created_at":"2026-05-22T01:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21796","created_at":"2026-05-22T01:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"FQJ2THGLXUA6","created_at":"2026-05-22T01:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"FQJ2THGLXUA6AVEU","created_at":"2026-05-22T01:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"FQJ2THGL","created_at":"2026-05-22T01:03:32Z"}],"graph_snapshots":[{"event_id":"sha256:446bee2bb3a90ab2f4e4ccfc6ed7adb0e8fed2c05d11dd59579e168e340cb789","target":"graph","created_at":"2026-05-22T01:03:32Z","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/2605.21796/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grounding language in the physical world requires AI systems to interpret references that emerge dynamically during conversation. While current vision-language models (VLMs) excel at static image tasks, they struggle to resolve ambiguous expressions in spontaneous, multi-turn dialogue. We address this gap by introducing (1) a benchmark for referential communication in dynamic 3D environments, built from 6.7 hours of egocentric VR interaction with synchronized speech, motion, gaze, and 3D scene geometry, and (2) a two-stage grounding pipeline that explicitly resolves conversational ambiguity be","authors_text":"Anna Deichler, Anna Klezovich, Fethiye Irmak Dogan, Iolanda Leite, Jim O'Regan, Jonas Beskow, Lubos Marcinek","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T22:44:09Z","title":"MM-Conv: A Multimodal Dataset and Benchmark for Context-Aware Grounding in 3D Dialogue"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21796","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:b402290868477360f3a1a3fc6e5c24e2b1a83932c54555346a5528928ade8cde","target":"record","created_at":"2026-05-22T01:03:32Z","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":"5b80f4584159e801a307386b52d221de0a574b84d20121f9d9e92a3578978a05","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T22:44:09Z","title_canon_sha256":"528f88999a8cc4173fd76c20a2c87c7304dcb828e666744228185a8a18df6ba0"},"schema_version":"1.0","source":{"id":"2605.21796","kind":"arxiv","version":1}},"canonical_sha256":"2c13a99ccbbd01e05494f6a31c7f6ec33c84a295facb3e844017b648c6576f99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c13a99ccbbd01e05494f6a31c7f6ec33c84a295facb3e844017b648c6576f99","first_computed_at":"2026-05-22T01:03:32.820030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:32.820030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j0o+bJilWGrgjQmtylcymW+vtnwoVlvxUOXtyCEftsr1+zqPVtMlykbJUh8cE3dPHLWBHqeXrDiP6llx8dZTBQ==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:32.820657Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21796","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b402290868477360f3a1a3fc6e5c24e2b1a83932c54555346a5528928ade8cde","sha256:446bee2bb3a90ab2f4e4ccfc6ed7adb0e8fed2c05d11dd59579e168e340cb789"],"state_sha256":"086aa59d4245e9a2c1b4afb44dd6103c491d4eb37b43fe74375891f3e58bfc09"}