{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:64B6TC76OGHG4DONRBR5QBSWD3","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":"83731678cd73707db3ac0a47d7d7ad6c6add1814e6bdf6a9adc78428d8b18d26","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-25T05:40:00Z","title_canon_sha256":"ed3549a3591a4d3b239490cd8bb606b7160811fe2c847a199d224c193629e431"},"schema_version":"1.0","source":{"id":"2205.12502","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.12502","created_at":"2026-07-05T05:47:15Z"},{"alias_kind":"arxiv_version","alias_value":"2205.12502v2","created_at":"2026-07-05T05:47:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12502","created_at":"2026-07-05T05:47:15Z"},{"alias_kind":"pith_short_12","alias_value":"64B6TC76OGHG","created_at":"2026-07-05T05:47:15Z"},{"alias_kind":"pith_short_16","alias_value":"64B6TC76OGHG4DON","created_at":"2026-07-05T05:47:15Z"},{"alias_kind":"pith_short_8","alias_value":"64B6TC76","created_at":"2026-07-05T05:47:15Z"}],"graph_snapshots":[{"event_id":"sha256:b01f982cb7f2450858d46d35dfeb5b748267ac1c96e6b71ffe0506cbba1846bd","target":"graph","created_at":"2026-07-05T05:47:15Z","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/2205.12502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual dialog (VisDial) is a task of answering a sequence of questions grounded in an image, using the dialog history as context. Prior work has trained the dialog agents solely on VisDial data via supervised learning or leveraged pre-training on related vision-and-language datasets. This paper presents a semi-supervised learning approach for visually-grounded dialog, called Generative Self-Training (GST), to leverage unlabeled images on the Web. Specifically, GST first retrieves in-domain images through out-of-distribution detection and generates synthetic dialogs regarding the images via mul","authors_text":"Byoung-Tak Zhang, Donghyun Kwak, Gi-Cheon Kang, Jin-Hwa Kim, Sungdong Kim","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-25T05:40:00Z","title":"The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12502","kind":"arxiv","version":2},"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":"sha256:879c628cd989aefe69e0b12c348375f133e6787071d2fb68a2ea7276a2e66df6","target":"record","created_at":"2026-07-05T05:47:15Z","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":"83731678cd73707db3ac0a47d7d7ad6c6add1814e6bdf6a9adc78428d8b18d26","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-25T05:40:00Z","title_canon_sha256":"ed3549a3591a4d3b239490cd8bb606b7160811fe2c847a199d224c193629e431"},"schema_version":"1.0","source":{"id":"2205.12502","kind":"arxiv","version":2}},"canonical_sha256":"f703e98bfe718e6e0dcd8863d806561eeaf1f577acd21a2dbc7cedacdf12e5c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f703e98bfe718e6e0dcd8863d806561eeaf1f577acd21a2dbc7cedacdf12e5c3","first_computed_at":"2026-07-05T05:47:15.511529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:15.511529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lWPegAkT/JqgzP0JHJF8WPlq6lGLCnmQeBxJRc/Ub2BbEl5bdEWqnxyO/H5N6G05TqNPrfft9fN8fdYjPU/aBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:15.511935Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.12502","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:879c628cd989aefe69e0b12c348375f133e6787071d2fb68a2ea7276a2e66df6","sha256:b01f982cb7f2450858d46d35dfeb5b748267ac1c96e6b71ffe0506cbba1846bd"],"state_sha256":"aa2d519bcd5335fd6420f217086f4c886164dfbd8d05c05c4ed39b9913cdf935"}