{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OQQ2Q7VFRFTW5R4U6COD6R4V4A","short_pith_number":"pith:OQQ2Q7VF","schema_version":"1.0","canonical_sha256":"7421a87ea589676ec794f09c3f4795e02aaf8a5bccf424ed313fbb3073b879c4","source":{"kind":"arxiv","id":"2506.13971","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Fusion with Semi-Supervised Learning Minimizes Annotation Quantity for Modeling Videoconference Conversation Experience","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.HC","cs.LG","cs.MM"],"primary_cat":"eess.AS","authors_text":"Andrew Chang, Chenkai Hu, David Poeppel, Dustin Freeman, Ji Qi, Kexin Zhang, Viswadruth Akkaraju, Zhuojian Wei","submitted_at":"2025-06-01T01:09:08Z","abstract_excerpt":"Group conversations over videoconferencing are a complex social behavior. However, the subjective moments of negative experience, where the conversation loses fluidity or enjoyment remain understudied. These moments are infrequent in naturalistic data, and thus training a supervised learning (SL) model requires costly manual data annotation. We applied semi-supervised learning (SSL) to leverage targeted labeled and unlabeled clips for training multimodal (audio, facial, text) deep features to predict non-fluid or unenjoyable moments in holdout videoconference sessions. The modality-fused co-tr"},"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":"2506.13971","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-01T01:09:08Z","cross_cats_sorted":["cs.CL","cs.HC","cs.LG","cs.MM"],"title_canon_sha256":"348cedcd12c772280c3075f73fa7a5aa205a45123ce52f1b26abfaf5ae550748","abstract_canon_sha256":"f03d7621c2a7f31c19ab906f1596d7ef884e4c57905b3db93b3f61728e698e4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:40.797854Z","signature_b64":"WbpvblPNsyg+nr3Rm4MLi1M4TqmY+/YNOLpr+WAuLy6CkQqPBID82HTEKpGwV/hSNOoEWONvJgkSkofvlMAyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7421a87ea589676ec794f09c3f4795e02aaf8a5bccf424ed313fbb3073b879c4","last_reissued_at":"2026-07-05T11:55:40.797386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:40.797386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Fusion with Semi-Supervised Learning Minimizes Annotation Quantity for Modeling Videoconference Conversation Experience","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.HC","cs.LG","cs.MM"],"primary_cat":"eess.AS","authors_text":"Andrew Chang, Chenkai Hu, David Poeppel, Dustin Freeman, Ji Qi, Kexin Zhang, Viswadruth Akkaraju, Zhuojian Wei","submitted_at":"2025-06-01T01:09:08Z","abstract_excerpt":"Group conversations over videoconferencing are a complex social behavior. However, the subjective moments of negative experience, where the conversation loses fluidity or enjoyment remain understudied. These moments are infrequent in naturalistic data, and thus training a supervised learning (SL) model requires costly manual data annotation. We applied semi-supervised learning (SSL) to leverage targeted labeled and unlabeled clips for training multimodal (audio, facial, text) deep features to predict non-fluid or unenjoyable moments in holdout videoconference sessions. The modality-fused co-tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13971","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/2506.13971/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":"2506.13971","created_at":"2026-07-05T11:55:40.797443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13971v1","created_at":"2026-07-05T11:55:40.797443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13971","created_at":"2026-07-05T11:55:40.797443+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQQ2Q7VFRFTW","created_at":"2026-07-05T11:55:40.797443+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQQ2Q7VFRFTW5R4U","created_at":"2026-07-05T11:55:40.797443+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQQ2Q7VF","created_at":"2026-07-05T11:55:40.797443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.13971","citing_title":"Multimodal Fusion with Semi-Supervised Learning Minimizes Annotation Quantity for Modeling Videoconference Conversation Experience","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQQ2Q7VFRFTW5R4U6COD6R4V4A","json":"https://pith.science/pith/OQQ2Q7VFRFTW5R4U6COD6R4V4A.json","graph_json":"https://pith.science/api/pith-number/OQQ2Q7VFRFTW5R4U6COD6R4V4A/graph.json","events_json":"https://pith.science/api/pith-number/OQQ2Q7VFRFTW5R4U6COD6R4V4A/events.json","paper":"https://pith.science/paper/OQQ2Q7VF"},"agent_actions":{"view_html":"https://pith.science/pith/OQQ2Q7VFRFTW5R4U6COD6R4V4A","download_json":"https://pith.science/pith/OQQ2Q7VFRFTW5R4U6COD6R4V4A.json","view_paper":"https://pith.science/paper/OQQ2Q7VF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13971&json=true","fetch_graph":"https://pith.science/api/pith-number/OQQ2Q7VFRFTW5R4U6COD6R4V4A/graph.json","fetch_events":"https://pith.science/api/pith-number/OQQ2Q7VFRFTW5R4U6COD6R4V4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQQ2Q7VFRFTW5R4U6COD6R4V4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQQ2Q7VFRFTW5R4U6COD6R4V4A/action/storage_attestation","attest_author":"https://pith.science/pith/OQQ2Q7VFRFTW5R4U6COD6R4V4A/action/author_attestation","sign_citation":"https://pith.science/pith/OQQ2Q7VFRFTW5R4U6COD6R4V4A/action/citation_signature","submit_replication":"https://pith.science/pith/OQQ2Q7VFRFTW5R4U6COD6R4V4A/action/replication_record"}},"created_at":"2026-07-05T11:55:40.797443+00:00","updated_at":"2026-07-05T11:55:40.797443+00:00"}