{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W5VGGY53FL2PH7ZBLOGURPCKL2","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":"72f2dea3d6497ad4a81382dc1244434dbf29c55d7794c0392ab89448e976173f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T21:58:07Z","title_canon_sha256":"7e1c44c2b953e6480e3b2b5ad3ba03f66b68f37bc5f9486917ca71bce1c3cc0c"},"schema_version":"1.0","source":{"id":"2502.02740","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02740","created_at":"2026-07-05T10:09:54Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02740v1","created_at":"2026-07-05T10:09:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02740","created_at":"2026-07-05T10:09:54Z"},{"alias_kind":"pith_short_12","alias_value":"W5VGGY53FL2P","created_at":"2026-07-05T10:09:54Z"},{"alias_kind":"pith_short_16","alias_value":"W5VGGY53FL2PH7ZB","created_at":"2026-07-05T10:09:54Z"},{"alias_kind":"pith_short_8","alias_value":"W5VGGY53","created_at":"2026-07-05T10:09:54Z"}],"graph_snapshots":[{"event_id":"sha256:ccd6371fffb61447b9373fdd2a6498e5416f82a1156943006276f0a74a215a97","target":"graph","created_at":"2026-07-05T10:09:54Z","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/2502.02740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing demand for high-quality, diverse training data poses a significant bottleneck in advancing vision-language models (VLMs). This paper presents VLM Dialog Games, a novel and scalable self-improvement framework for VLMs. Our approach leverages self-play between two agents engaged in a goal-oriented play centered around image identification. By filtering for successful game interactions, we automatically curate a high-quality dataset of interleaved images and text. We demonstrate that fine-tuning on this synthetic data leads to performance gains on downstream tasks and generalises a","authors_text":"Christos Kaplanis, Ksenia Konyushkova, Misha Denil, Serkan Cabi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T21:58:07Z","title":"Vision-Language Model Dialog Games for Self-Improvement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02740","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:d36588551034bebf26991929417a940a3ed7eabd148b4a2844ba3230b54cf2d0","target":"record","created_at":"2026-07-05T10:09:54Z","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":"72f2dea3d6497ad4a81382dc1244434dbf29c55d7794c0392ab89448e976173f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T21:58:07Z","title_canon_sha256":"7e1c44c2b953e6480e3b2b5ad3ba03f66b68f37bc5f9486917ca71bce1c3cc0c"},"schema_version":"1.0","source":{"id":"2502.02740","kind":"arxiv","version":1}},"canonical_sha256":"b76a6363bb2af4f3ff215b8d48bc4a5eaf4a8e5f90715cb6c25998e9f116e5fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b76a6363bb2af4f3ff215b8d48bc4a5eaf4a8e5f90715cb6c25998e9f116e5fe","first_computed_at":"2026-07-05T10:09:54.512986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:54.512986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nufWLKL39r/LREQ0qU3fRB4vfpvYuuV7WVn9KKf1D5tqL4tF6l4JTHe2+I638EIAnI+QZYyKoUobDqiOXEjrAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:54.513342Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02740","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d36588551034bebf26991929417a940a3ed7eabd148b4a2844ba3230b54cf2d0","sha256:ccd6371fffb61447b9373fdd2a6498e5416f82a1156943006276f0a74a215a97"],"state_sha256":"3d535fb59fa37ea9cc49e290bb580bab9587f3f8ea4613dc4abec724988aefe1"}