{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OB5JSRVOIEQGP3RKBW2BCLCE77","short_pith_number":"pith:OB5JSRVO","schema_version":"1.0","canonical_sha256":"707a9946ae412067ee2a0db4112c44fffb6ff9af7327a2d3fff0fdeedcd01a1a","source":{"kind":"arxiv","id":"2211.05719","version":3},"attestation_state":"computed","paper":{"title":"MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.CL","authors_text":"Can Xu, Chongyang Tao, Dongyan Zhao, Jiazhan Feng, Pu Zhao, Qingfeng Sun, Qingwei Lin, Yaming Yang","submitted_at":"2022-11-10T17:37:04Z","abstract_excerpt":"Responding with multi-modal content has been recognized as an essential capability for an intelligent conversational agent. In this paper, we introduce the MMDialog dataset to better facilitate multi-modal conversation. MMDialog is composed of a curated set of 1.08 million real-world dialogues with 1.53 million unique images across 4,184 topics. MMDialog has two main and unique advantages. First, it is the largest multi-modal conversation dataset by the number of dialogues by 88x. Second, it contains massive topics to generalize the open-domain. To build engaging dialogue system with this data"},"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":"2211.05719","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-10T17:37:04Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MM"],"title_canon_sha256":"94b6857865acc6aef21c0a5ee1f1778c3d5b13e44613a136f839e7ff14867e6d","abstract_canon_sha256":"c14b1212097596bf59f1ec6edba7523d748c540a0985f6b726e5b6d6e68b0951"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:20.444456Z","signature_b64":"iBbv9QdB+yH4X3UGwRrbEYpTe1mUDEU9o8poXYDCur1o5kp1qpw9ROLfTA2ZSsAwkHowftlOsgMqO45pmfhhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"707a9946ae412067ee2a0db4112c44fffb6ff9af7327a2d3fff0fdeedcd01a1a","last_reissued_at":"2026-07-05T05:27:20.443960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:20.443960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.CL","authors_text":"Can Xu, Chongyang Tao, Dongyan Zhao, Jiazhan Feng, Pu Zhao, Qingfeng Sun, Qingwei Lin, Yaming Yang","submitted_at":"2022-11-10T17:37:04Z","abstract_excerpt":"Responding with multi-modal content has been recognized as an essential capability for an intelligent conversational agent. In this paper, we introduce the MMDialog dataset to better facilitate multi-modal conversation. MMDialog is composed of a curated set of 1.08 million real-world dialogues with 1.53 million unique images across 4,184 topics. MMDialog has two main and unique advantages. First, it is the largest multi-modal conversation dataset by the number of dialogues by 88x. Second, it contains massive topics to generalize the open-domain. To build engaging dialogue system with this data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.05719","kind":"arxiv","version":3},"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/2211.05719/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":"2211.05719","created_at":"2026-07-05T05:27:20.444017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.05719v3","created_at":"2026-07-05T05:27:20.444017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05719","created_at":"2026-07-05T05:27:20.444017+00:00"},{"alias_kind":"pith_short_12","alias_value":"OB5JSRVOIEQG","created_at":"2026-07-05T05:27:20.444017+00:00"},{"alias_kind":"pith_short_16","alias_value":"OB5JSRVOIEQGP3RK","created_at":"2026-07-05T05:27:20.444017+00:00"},{"alias_kind":"pith_short_8","alias_value":"OB5JSRVO","created_at":"2026-07-05T05:27:20.444017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.08128","citing_title":"Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2306.05685","citing_title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OB5JSRVOIEQGP3RKBW2BCLCE77","json":"https://pith.science/pith/OB5JSRVOIEQGP3RKBW2BCLCE77.json","graph_json":"https://pith.science/api/pith-number/OB5JSRVOIEQGP3RKBW2BCLCE77/graph.json","events_json":"https://pith.science/api/pith-number/OB5JSRVOIEQGP3RKBW2BCLCE77/events.json","paper":"https://pith.science/paper/OB5JSRVO"},"agent_actions":{"view_html":"https://pith.science/pith/OB5JSRVOIEQGP3RKBW2BCLCE77","download_json":"https://pith.science/pith/OB5JSRVOIEQGP3RKBW2BCLCE77.json","view_paper":"https://pith.science/paper/OB5JSRVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.05719&json=true","fetch_graph":"https://pith.science/api/pith-number/OB5JSRVOIEQGP3RKBW2BCLCE77/graph.json","fetch_events":"https://pith.science/api/pith-number/OB5JSRVOIEQGP3RKBW2BCLCE77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OB5JSRVOIEQGP3RKBW2BCLCE77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OB5JSRVOIEQGP3RKBW2BCLCE77/action/storage_attestation","attest_author":"https://pith.science/pith/OB5JSRVOIEQGP3RKBW2BCLCE77/action/author_attestation","sign_citation":"https://pith.science/pith/OB5JSRVOIEQGP3RKBW2BCLCE77/action/citation_signature","submit_replication":"https://pith.science/pith/OB5JSRVOIEQGP3RKBW2BCLCE77/action/replication_record"}},"created_at":"2026-07-05T05:27:20.444017+00:00","updated_at":"2026-07-05T05:27:20.444017+00:00"}