{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:W5VGGY53FL2PH7ZBLOGURPCKL2","short_pith_number":"pith:W5VGGY53","canonical_record":{"source":{"id":"2502.02740","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T21:58:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7e1c44c2b953e6480e3b2b5ad3ba03f66b68f37bc5f9486917ca71bce1c3cc0c","abstract_canon_sha256":"72f2dea3d6497ad4a81382dc1244434dbf29c55d7794c0392ab89448e976173f"},"schema_version":"1.0"},"canonical_sha256":"b76a6363bb2af4f3ff215b8d48bc4a5eaf4a8e5f90715cb6c25998e9f116e5fe","source":{"kind":"arxiv","id":"2502.02740","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:W5VGGY53FL2PH7ZBLOGURPCKL2","target":"record","payload":{"canonical_record":{"source":{"id":"2502.02740","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T21:58:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7e1c44c2b953e6480e3b2b5ad3ba03f66b68f37bc5f9486917ca71bce1c3cc0c","abstract_canon_sha256":"72f2dea3d6497ad4a81382dc1244434dbf29c55d7794c0392ab89448e976173f"},"schema_version":"1.0"},"canonical_sha256":"b76a6363bb2af4f3ff215b8d48bc4a5eaf4a8e5f90715cb6c25998e9f116e5fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:54.513342Z","signature_b64":"nufWLKL39r/LREQ0qU3fRB4vfpvYuuV7WVn9KKf1D5tqL4tF6l4JTHe2+I638EIAnI+QZYyKoUobDqiOXEjrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b76a6363bb2af4f3ff215b8d48bc4a5eaf4a8e5f90715cb6c25998e9f116e5fe","last_reissued_at":"2026-07-05T10:09:54.512986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:54.512986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.02740","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X4ibVku6PEJ6TspttyybaUsW5+dBu9J4bvtJ2lfNEFQnTr0DUSM2JQgeCVpV2ZOIV0Gt4u39g6FRCVOGsD2gBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:30:43.737069Z"},"content_sha256":"d36588551034bebf26991929417a940a3ed7eabd148b4a2844ba3230b54cf2d0","schema_version":"1.0","event_id":"sha256:d36588551034bebf26991929417a940a3ed7eabd148b4a2844ba3230b54cf2d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:W5VGGY53FL2PH7ZBLOGURPCKL2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vision-Language Model Dialog Games for Self-Improvement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Christos Kaplanis, Ksenia Konyushkova, Misha Denil, Serkan Cabi","submitted_at":"2025-02-04T21:58:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02740","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/2502.02740/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HNPO4C8bwOLSiVPWU5+Bz/0LJEh8dOjxfOFH76KMg8RZ/wpvcXxsUApFNQ3gQMmtxAsoR4kPLNgG8cXQZQiGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:30:43.778146Z"},"content_sha256":"ccd6371fffb61447b9373fdd2a6498e5416f82a1156943006276f0a74a215a97","schema_version":"1.0","event_id":"sha256:ccd6371fffb61447b9373fdd2a6498e5416f82a1156943006276f0a74a215a97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W5VGGY53FL2PH7ZBLOGURPCKL2/bundle.json","state_url":"https://pith.science/pith/W5VGGY53FL2PH7ZBLOGURPCKL2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W5VGGY53FL2PH7ZBLOGURPCKL2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T22:30:43Z","links":{"resolver":"https://pith.science/pith/W5VGGY53FL2PH7ZBLOGURPCKL2","bundle":"https://pith.science/pith/W5VGGY53FL2PH7ZBLOGURPCKL2/bundle.json","state":"https://pith.science/pith/W5VGGY53FL2PH7ZBLOGURPCKL2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W5VGGY53FL2PH7ZBLOGURPCKL2/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W5SmZO/COb5PUBPSatEXPgqzAX4QFIpEfCapMXO6m/irlEXOg5rfIw55PJLjTaFPygGz6nH/TvJFOmObCP8DDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:30:43.800303Z","bundle_sha256":"272a200c5cf4a19cfa2a49c5a5fbc4778ff8a2edf052db195ab57b108b61e405"}}