{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:INYKEWFEURNSAAVE4AUCLTWDMU","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":"4f8af1456b6a805a470538bf6e0f82191774649c4ebd798748c8d01d7f021208","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T00:38:26Z","title_canon_sha256":"e80bf54f68b596737541dc951b3055114f87d6026e7ce1ad1957050cae691c1e"},"schema_version":"1.0","source":{"id":"2605.24794","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24794","created_at":"2026-05-26T01:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24794v1","created_at":"2026-05-26T01:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24794","created_at":"2026-05-26T01:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"INYKEWFEURNS","created_at":"2026-05-26T01:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"INYKEWFEURNSAAVE","created_at":"2026-05-26T01:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"INYKEWFE","created_at":"2026-05-26T01:03:58Z"}],"graph_snapshots":[{"event_id":"sha256:c2ded196ac0eaa50c7c33b2613505fb4db670510cfe24ad7bd887e7c2eb63066","target":"graph","created_at":"2026-05-26T01:03:58Z","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/2605.24794/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has emerged as an effective paradigm for improving the reasoning capability of vision-language models (VLMs). However, RL-based optimization typically depends on costly high-quality annotations that are difficult to scale. Existing unsupervised alternatives may drift toward biased solutions due to weak visual grounding and the lack of reliable verification signals. We propose a self-evolving post-training framework, DUEL, where supervision emerges from adversarial interactions between two policies initialized from the same pretrained VLM. A Challenger generates an i","authors_text":"Bingjun Sun, Guangdeng Liao, Hanqing Zeng, Ji Liu, Lin Qiu, Yao Liu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T00:38:26Z","title":"DUEL: Adversarial Self-Play for Multimodal Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24794","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:cc7a07e989ed538df3c47cf86d065cea96911ed7de94184b8f2c5341726e1da8","target":"record","created_at":"2026-05-26T01:03:58Z","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":"4f8af1456b6a805a470538bf6e0f82191774649c4ebd798748c8d01d7f021208","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T00:38:26Z","title_canon_sha256":"e80bf54f68b596737541dc951b3055114f87d6026e7ce1ad1957050cae691c1e"},"schema_version":"1.0","source":{"id":"2605.24794","kind":"arxiv","version":1}},"canonical_sha256":"4370a258a4a45b2002a4e02825cec36500c69acd3206c9239956417c60088bb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4370a258a4a45b2002a4e02825cec36500c69acd3206c9239956417c60088bb0","first_computed_at":"2026-05-26T01:03:58.744709Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:58.744709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b+owQSDrya+Kj4cSIjQjqr8w5v21im2KhkURBMEF4Nwb7j+6jM/WQ45vtF2pGBuduukiJUDcbe5GT9n6SaD/AQ==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:58.745281Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24794","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc7a07e989ed538df3c47cf86d065cea96911ed7de94184b8f2c5341726e1da8","sha256:c2ded196ac0eaa50c7c33b2613505fb4db670510cfe24ad7bd887e7c2eb63066"],"state_sha256":"5d857bbe7b202441c558dcf99b530bd57c52907a45dac5c93ce7053f7020dc52"}