{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FZJCVSC67JZ4VM5FBAZ2QEHT7S","short_pith_number":"pith:FZJCVSC6","schema_version":"1.0","canonical_sha256":"2e522ac85efa73cab3a50833a810f3fc9dd57191c3f689d8db828e58ac6c0b9b","source":{"kind":"arxiv","id":"2108.07154","version":3},"attestation_state":"computed","paper":{"title":"MMChat: Multi-Modal Chat Dataset on Social Media","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Guanyi Chen, Jian Sun, Xin Liu, Yinhe Zheng","submitted_at":"2021-08-16T15:27:49Z","abstract_excerpt":"Incorporating multi-modal contexts in conversation is important for developing more engaging dialogue systems. In this work, we explore this direction by introducing MMChat: a large-scale Chinese multi-modal dialogue corpus (32.4M raw dialogues and 120.84K filtered dialogues). Unlike previous corpora that are crowd-sourced or collected from fictitious movies, MMChat contains image-grounded dialogues collected from real conversations on social media, in which the sparsity issue is observed. Specifically, image-initiated dialogues in common communications may deviate to some non-image-grounded t"},"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":"2108.07154","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-16T15:27:49Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0c2e05655b2956cd909d7efbb7e300bc91f339dc5faff82ab7d015008deae319","abstract_canon_sha256":"0338894b6fb37a868a830fe17d4258c515c81242dda27bc816c6127ffd558583"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:02.760626Z","signature_b64":"RdLaMCjnQznr+akcOBfm75M0p1F0DuCZyoYKFqU/AHAC3PdG/fdfGdhxVV76+r9QbuTwaQ5tDSp6U0X+2UxXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e522ac85efa73cab3a50833a810f3fc9dd57191c3f689d8db828e58ac6c0b9b","last_reissued_at":"2026-07-05T04:19:02.758806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:02.758806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMChat: Multi-Modal Chat Dataset on Social Media","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Guanyi Chen, Jian Sun, Xin Liu, Yinhe Zheng","submitted_at":"2021-08-16T15:27:49Z","abstract_excerpt":"Incorporating multi-modal contexts in conversation is important for developing more engaging dialogue systems. In this work, we explore this direction by introducing MMChat: a large-scale Chinese multi-modal dialogue corpus (32.4M raw dialogues and 120.84K filtered dialogues). Unlike previous corpora that are crowd-sourced or collected from fictitious movies, MMChat contains image-grounded dialogues collected from real conversations on social media, in which the sparsity issue is observed. Specifically, image-initiated dialogues in common communications may deviate to some non-image-grounded t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.07154","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/2108.07154/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":"2108.07154","created_at":"2026-07-05T04:19:02.760133+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.07154v3","created_at":"2026-07-05T04:19:02.760133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.07154","created_at":"2026-07-05T04:19:02.760133+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZJCVSC67JZ4","created_at":"2026-07-05T04:19:02.760133+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZJCVSC67JZ4VM5F","created_at":"2026-07-05T04:19:02.760133+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZJCVSC6","created_at":"2026-07-05T04:19:02.760133+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05887","citing_title":"MTPChat: A Multimodal Time-Aware Persona Dataset for Conversational Agents","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZJCVSC67JZ4VM5FBAZ2QEHT7S","json":"https://pith.science/pith/FZJCVSC67JZ4VM5FBAZ2QEHT7S.json","graph_json":"https://pith.science/api/pith-number/FZJCVSC67JZ4VM5FBAZ2QEHT7S/graph.json","events_json":"https://pith.science/api/pith-number/FZJCVSC67JZ4VM5FBAZ2QEHT7S/events.json","paper":"https://pith.science/paper/FZJCVSC6"},"agent_actions":{"view_html":"https://pith.science/pith/FZJCVSC67JZ4VM5FBAZ2QEHT7S","download_json":"https://pith.science/pith/FZJCVSC67JZ4VM5FBAZ2QEHT7S.json","view_paper":"https://pith.science/paper/FZJCVSC6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.07154&json=true","fetch_graph":"https://pith.science/api/pith-number/FZJCVSC67JZ4VM5FBAZ2QEHT7S/graph.json","fetch_events":"https://pith.science/api/pith-number/FZJCVSC67JZ4VM5FBAZ2QEHT7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZJCVSC67JZ4VM5FBAZ2QEHT7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZJCVSC67JZ4VM5FBAZ2QEHT7S/action/storage_attestation","attest_author":"https://pith.science/pith/FZJCVSC67JZ4VM5FBAZ2QEHT7S/action/author_attestation","sign_citation":"https://pith.science/pith/FZJCVSC67JZ4VM5FBAZ2QEHT7S/action/citation_signature","submit_replication":"https://pith.science/pith/FZJCVSC67JZ4VM5FBAZ2QEHT7S/action/replication_record"}},"created_at":"2026-07-05T04:19:02.760133+00:00","updated_at":"2026-07-05T04:19:02.760133+00:00"}