{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5ZDBLAGZFIE5HGGSXECHX55WRA","short_pith_number":"pith:5ZDBLAGZ","schema_version":"1.0","canonical_sha256":"ee461580d92a09d398d2b9047bf7b688154c7de7df045a80be58686e319c9a5b","source":{"kind":"arxiv","id":"2410.00253","version":1},"attestation_state":"computed","paper":{"title":"MM-Conv: A Multi-modal Conversational Dataset for Virtual Humans","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.GR","cs.HC"],"primary_cat":"cs.CV","authors_text":"Anna Deichler, Jim O'Regan, Jonas Beskow","submitted_at":"2024-09-30T21:51:30Z","abstract_excerpt":"In this paper, we present a novel dataset captured using a VR headset to record conversations between participants within a physics simulator (AI2-THOR). Our primary objective is to extend the field of co-speech gesture generation by incorporating rich contextual information within referential settings. Participants engaged in various conversational scenarios, all based on referential communication tasks. The dataset provides a rich set of multimodal recordings such as motion capture, speech, gaze, and scene graphs. This comprehensive dataset aims to enhance the understanding and development o"},"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":"2410.00253","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-30T21:51:30Z","cross_cats_sorted":["cs.CL","cs.GR","cs.HC"],"title_canon_sha256":"fd24147ff2c0c2a0154abf3b47e4080ef9b4c0a4ed859743527f809722858b97","abstract_canon_sha256":"f64358849b3077766a96faabd2417ff893deb1e66132fd1d7a49c070621cf9bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:01.778270Z","signature_b64":"C8ou07fiaaBALxMXdIWT6Q1Gqg9IwxDOq7SaT6ddqeg6HkgtkdcPiLIq2IPKstCCadIesFyuAM3MAnzEmvvFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee461580d92a09d398d2b9047bf7b688154c7de7df045a80be58686e319c9a5b","last_reissued_at":"2026-07-05T09:14:01.777768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:01.777768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-Conv: A Multi-modal Conversational Dataset for Virtual Humans","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.GR","cs.HC"],"primary_cat":"cs.CV","authors_text":"Anna Deichler, Jim O'Regan, Jonas Beskow","submitted_at":"2024-09-30T21:51:30Z","abstract_excerpt":"In this paper, we present a novel dataset captured using a VR headset to record conversations between participants within a physics simulator (AI2-THOR). Our primary objective is to extend the field of co-speech gesture generation by incorporating rich contextual information within referential settings. Participants engaged in various conversational scenarios, all based on referential communication tasks. The dataset provides a rich set of multimodal recordings such as motion capture, speech, gaze, and scene graphs. This comprehensive dataset aims to enhance the understanding and development o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00253","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/2410.00253/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":"2410.00253","created_at":"2026-07-05T09:14:01.777832+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.00253v1","created_at":"2026-07-05T09:14:01.777832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00253","created_at":"2026-07-05T09:14:01.777832+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZDBLAGZFIE5","created_at":"2026-07-05T09:14:01.777832+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZDBLAGZFIE5HGGS","created_at":"2026-07-05T09:14:01.777832+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZDBLAGZ","created_at":"2026-07-05T09:14:01.777832+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02908","citing_title":"SentiAvatar: Towards Expressive and Interactive Digital Humans","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ZDBLAGZFIE5HGGSXECHX55WRA","json":"https://pith.science/pith/5ZDBLAGZFIE5HGGSXECHX55WRA.json","graph_json":"https://pith.science/api/pith-number/5ZDBLAGZFIE5HGGSXECHX55WRA/graph.json","events_json":"https://pith.science/api/pith-number/5ZDBLAGZFIE5HGGSXECHX55WRA/events.json","paper":"https://pith.science/paper/5ZDBLAGZ"},"agent_actions":{"view_html":"https://pith.science/pith/5ZDBLAGZFIE5HGGSXECHX55WRA","download_json":"https://pith.science/pith/5ZDBLAGZFIE5HGGSXECHX55WRA.json","view_paper":"https://pith.science/paper/5ZDBLAGZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.00253&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZDBLAGZFIE5HGGSXECHX55WRA/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZDBLAGZFIE5HGGSXECHX55WRA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZDBLAGZFIE5HGGSXECHX55WRA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZDBLAGZFIE5HGGSXECHX55WRA/action/storage_attestation","attest_author":"https://pith.science/pith/5ZDBLAGZFIE5HGGSXECHX55WRA/action/author_attestation","sign_citation":"https://pith.science/pith/5ZDBLAGZFIE5HGGSXECHX55WRA/action/citation_signature","submit_replication":"https://pith.science/pith/5ZDBLAGZFIE5HGGSXECHX55WRA/action/replication_record"}},"created_at":"2026-07-05T09:14:01.777832+00:00","updated_at":"2026-07-05T09:14:01.777832+00:00"}