{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5ZD7LDJ2G2NE2KWDMWKAMXODG4","short_pith_number":"pith:5ZD7LDJ2","schema_version":"1.0","canonical_sha256":"ee47f58d3a369a4d2ac36594065dc337253bd64d643c28cc8ee68e95c1d666fb","source":{"kind":"arxiv","id":"2107.08685","version":1},"attestation_state":"computed","paper":{"title":"Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ho-Jin Choi, Jaegul Choo, Nyoungwoo Lee, Sung-Hyun Myaeng, Suwon Shin","submitted_at":"2021-07-19T08:44:11Z","abstract_excerpt":"In multi-modal dialogue systems, it is important to allow the use of images as part of a multi-turn conversation. Training such dialogue systems generally requires a large-scale dataset consisting of multi-turn dialogues that involve images, but such datasets rarely exist. In response, this paper proposes a 45k multi-modal dialogue dataset created with minimal human intervention. Our method to create such a dataset consists of (1) preparing and pre-processing text dialogue datasets, (2) creating image-mixed dialogues by using a text-to-image replacement technique, and (3) employing a contextua"},"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":"2107.08685","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-19T08:44:11Z","cross_cats_sorted":[],"title_canon_sha256":"3e75df52ee0b63706fde8aa7c56fa08d6e9196228aecc4123cc314e3d404b348","abstract_canon_sha256":"07ab33e53171f4a805c1f8640b97652fb6a5047f070b80c0857d0f746c77e409"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:51.730829Z","signature_b64":"AdiyfD7q7KTAcwZbi+on6S27k24KugJ+3dBSa5o9osRSWuhwIfAvOgzElXx0NtbgB7g1rN0INUkW8cm5HbiyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee47f58d3a369a4d2ac36594065dc337253bd64d643c28cc8ee68e95c1d666fb","last_reissued_at":"2026-07-05T02:58:51.730373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:51.730373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ho-Jin Choi, Jaegul Choo, Nyoungwoo Lee, Sung-Hyun Myaeng, Suwon Shin","submitted_at":"2021-07-19T08:44:11Z","abstract_excerpt":"In multi-modal dialogue systems, it is important to allow the use of images as part of a multi-turn conversation. Training such dialogue systems generally requires a large-scale dataset consisting of multi-turn dialogues that involve images, but such datasets rarely exist. In response, this paper proposes a 45k multi-modal dialogue dataset created with minimal human intervention. Our method to create such a dataset consists of (1) preparing and pre-processing text dialogue datasets, (2) creating image-mixed dialogues by using a text-to-image replacement technique, and (3) employing a contextua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.08685","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/2107.08685/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":"2107.08685","created_at":"2026-07-05T02:58:51.730438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.08685v1","created_at":"2026-07-05T02:58:51.730438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.08685","created_at":"2026-07-05T02:58:51.730438+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZD7LDJ2G2NE","created_at":"2026-07-05T02:58:51.730438+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZD7LDJ2G2NE2KWD","created_at":"2026-07-05T02:58:51.730438+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZD7LDJ2","created_at":"2026-07-05T02:58:51.730438+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":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ZD7LDJ2G2NE2KWDMWKAMXODG4","json":"https://pith.science/pith/5ZD7LDJ2G2NE2KWDMWKAMXODG4.json","graph_json":"https://pith.science/api/pith-number/5ZD7LDJ2G2NE2KWDMWKAMXODG4/graph.json","events_json":"https://pith.science/api/pith-number/5ZD7LDJ2G2NE2KWDMWKAMXODG4/events.json","paper":"https://pith.science/paper/5ZD7LDJ2"},"agent_actions":{"view_html":"https://pith.science/pith/5ZD7LDJ2G2NE2KWDMWKAMXODG4","download_json":"https://pith.science/pith/5ZD7LDJ2G2NE2KWDMWKAMXODG4.json","view_paper":"https://pith.science/paper/5ZD7LDJ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.08685&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZD7LDJ2G2NE2KWDMWKAMXODG4/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZD7LDJ2G2NE2KWDMWKAMXODG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZD7LDJ2G2NE2KWDMWKAMXODG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZD7LDJ2G2NE2KWDMWKAMXODG4/action/storage_attestation","attest_author":"https://pith.science/pith/5ZD7LDJ2G2NE2KWDMWKAMXODG4/action/author_attestation","sign_citation":"https://pith.science/pith/5ZD7LDJ2G2NE2KWDMWKAMXODG4/action/citation_signature","submit_replication":"https://pith.science/pith/5ZD7LDJ2G2NE2KWDMWKAMXODG4/action/replication_record"}},"created_at":"2026-07-05T02:58:51.730438+00:00","updated_at":"2026-07-05T02:58:51.730438+00:00"}