{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5ZD7LDJ2G2NE2KWDMWKAMXODG4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"07ab33e53171f4a805c1f8640b97652fb6a5047f070b80c0857d0f746c77e409","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-19T08:44:11Z","title_canon_sha256":"3e75df52ee0b63706fde8aa7c56fa08d6e9196228aecc4123cc314e3d404b348"},"schema_version":"1.0","source":{"id":"2107.08685","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.08685","created_at":"2026-07-05T02:58:51Z"},{"alias_kind":"arxiv_version","alias_value":"2107.08685v1","created_at":"2026-07-05T02:58:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.08685","created_at":"2026-07-05T02:58:51Z"},{"alias_kind":"pith_short_12","alias_value":"5ZD7LDJ2G2NE","created_at":"2026-07-05T02:58:51Z"},{"alias_kind":"pith_short_16","alias_value":"5ZD7LDJ2G2NE2KWD","created_at":"2026-07-05T02:58:51Z"},{"alias_kind":"pith_short_8","alias_value":"5ZD7LDJ2","created_at":"2026-07-05T02:58:51Z"}],"graph_snapshots":[{"event_id":"sha256:c24b206b85a2d2565f37eaf18ef8524e800e909b21d11727cf8f4d62992c7815","target":"graph","created_at":"2026-07-05T02:58:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2107.08685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ho-Jin Choi, Jaegul Choo, Nyoungwoo Lee, Sung-Hyun Myaeng, Suwon Shin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-19T08:44:11Z","title":"Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.08685","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8745255e42fdf97c3991af99c7b9f1322347f8b002fdcefe6cb3e70d417d04d5","target":"record","created_at":"2026-07-05T02:58:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"07ab33e53171f4a805c1f8640b97652fb6a5047f070b80c0857d0f746c77e409","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-19T08:44:11Z","title_canon_sha256":"3e75df52ee0b63706fde8aa7c56fa08d6e9196228aecc4123cc314e3d404b348"},"schema_version":"1.0","source":{"id":"2107.08685","kind":"arxiv","version":1}},"canonical_sha256":"ee47f58d3a369a4d2ac36594065dc337253bd64d643c28cc8ee68e95c1d666fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee47f58d3a369a4d2ac36594065dc337253bd64d643c28cc8ee68e95c1d666fb","first_computed_at":"2026-07-05T02:58:51.730373Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:58:51.730373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AdiyfD7q7KTAcwZbi+on6S27k24KugJ+3dBSa5o9osRSWuhwIfAvOgzElXx0NtbgB7g1rN0INUkW8cm5HbiyCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:58:51.730829Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.08685","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8745255e42fdf97c3991af99c7b9f1322347f8b002fdcefe6cb3e70d417d04d5","sha256:c24b206b85a2d2565f37eaf18ef8524e800e909b21d11727cf8f4d62992c7815"],"state_sha256":"2af3e2986f0d3cf8d7cb1ae3d1f28d13eeb40f407037736b7929ae563c498ff9"}