{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MDW2KN6CDFVFQOVKIP2QC3HZPW","short_pith_number":"pith:MDW2KN6C","schema_version":"1.0","canonical_sha256":"60eda537c2196a583aaa43f5016cf97da53fe71d6cfa6eca1ddf3f8763a0b798","source":{"kind":"arxiv","id":"2205.06907","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Conversational AI: A Survey of Datasets and Approaches","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anirudh Sundar, Larry Heck","submitted_at":"2022-05-13T21:51:42Z","abstract_excerpt":"As humans, we experience the world with all our senses or modalities (sound, sight, touch, smell, and taste). We use these modalities, particularly sight and touch, to convey and interpret specific meanings. Multimodal expressions are central to conversations; a rich set of modalities amplify and often compensate for each other. A multimodal conversational AI system answers questions, fulfills tasks, and emulates human conversations by understanding and expressing itself via multiple modalities. This paper motivates, defines, and mathematically formulates the multimodal conversational research"},"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":"2205.06907","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-13T21:51:42Z","cross_cats_sorted":[],"title_canon_sha256":"33479b41efa891de6c0e029e73e873a8391bc7324a9ee7e8a5427cf1870a8f7e","abstract_canon_sha256":"524ec31dec793bac11dd2b7ff933c2a6098e846c25b6b4739667468f8a533571"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:23:09.904373Z","signature_b64":"q7v0xms5kuyOxcIhNXfmVRq5XHONsMEwjAPeE5Gq5nWdtudgZ+erquZtu/q539vlHMR5cPasxM3BQps7tNjVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60eda537c2196a583aaa43f5016cf97da53fe71d6cfa6eca1ddf3f8763a0b798","last_reissued_at":"2026-07-05T04:23:09.903896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:23:09.903896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Conversational AI: A Survey of Datasets and Approaches","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anirudh Sundar, Larry Heck","submitted_at":"2022-05-13T21:51:42Z","abstract_excerpt":"As humans, we experience the world with all our senses or modalities (sound, sight, touch, smell, and taste). We use these modalities, particularly sight and touch, to convey and interpret specific meanings. Multimodal expressions are central to conversations; a rich set of modalities amplify and often compensate for each other. A multimodal conversational AI system answers questions, fulfills tasks, and emulates human conversations by understanding and expressing itself via multiple modalities. This paper motivates, defines, and mathematically formulates the multimodal conversational research"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.06907","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/2205.06907/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":"2205.06907","created_at":"2026-07-05T04:23:09.903956+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.06907v1","created_at":"2026-07-05T04:23:09.903956+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.06907","created_at":"2026-07-05T04:23:09.903956+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDW2KN6CDFVF","created_at":"2026-07-05T04:23:09.903956+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDW2KN6CDFVFQOVK","created_at":"2026-07-05T04:23:09.903956+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDW2KN6C","created_at":"2026-07-05T04:23:09.903956+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06649","citing_title":"POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2506.09522","citing_title":"Revisit What You See: Revealing Visual Semantics in Vision Tokens to Guide LVLM Decoding","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MDW2KN6CDFVFQOVKIP2QC3HZPW","json":"https://pith.science/pith/MDW2KN6CDFVFQOVKIP2QC3HZPW.json","graph_json":"https://pith.science/api/pith-number/MDW2KN6CDFVFQOVKIP2QC3HZPW/graph.json","events_json":"https://pith.science/api/pith-number/MDW2KN6CDFVFQOVKIP2QC3HZPW/events.json","paper":"https://pith.science/paper/MDW2KN6C"},"agent_actions":{"view_html":"https://pith.science/pith/MDW2KN6CDFVFQOVKIP2QC3HZPW","download_json":"https://pith.science/pith/MDW2KN6CDFVFQOVKIP2QC3HZPW.json","view_paper":"https://pith.science/paper/MDW2KN6C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.06907&json=true","fetch_graph":"https://pith.science/api/pith-number/MDW2KN6CDFVFQOVKIP2QC3HZPW/graph.json","fetch_events":"https://pith.science/api/pith-number/MDW2KN6CDFVFQOVKIP2QC3HZPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDW2KN6CDFVFQOVKIP2QC3HZPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDW2KN6CDFVFQOVKIP2QC3HZPW/action/storage_attestation","attest_author":"https://pith.science/pith/MDW2KN6CDFVFQOVKIP2QC3HZPW/action/author_attestation","sign_citation":"https://pith.science/pith/MDW2KN6CDFVFQOVKIP2QC3HZPW/action/citation_signature","submit_replication":"https://pith.science/pith/MDW2KN6CDFVFQOVKIP2QC3HZPW/action/replication_record"}},"created_at":"2026-07-05T04:23:09.903956+00:00","updated_at":"2026-07-05T04:23:09.903956+00:00"}