{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:443FAUPAS23PTLBNLV744XM3XD","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":"9627cadb69aa69ad8e684ae540c54059152866d35ffbfe342548522d85f4aed6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-13T01:12:00Z","title_canon_sha256":"355c22f110541a844b03e50e8d4b7085ec85fda70924df4db6df49b8944b13d8"},"schema_version":"1.0","source":{"id":"2602.12506","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.12506","created_at":"2026-05-22T01:03:57Z"},{"alias_kind":"arxiv_version","alias_value":"2602.12506v3","created_at":"2026-05-22T01:03:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12506","created_at":"2026-05-22T01:03:57Z"},{"alias_kind":"pith_short_12","alias_value":"443FAUPAS23P","created_at":"2026-05-22T01:03:57Z"},{"alias_kind":"pith_short_16","alias_value":"443FAUPAS23PTLBN","created_at":"2026-05-22T01:03:57Z"},{"alias_kind":"pith_short_8","alias_value":"443FAUPA","created_at":"2026-05-22T01:03:57Z"}],"graph_snapshots":[{"event_id":"sha256:f68f8f271a7ea4d5719c9bf2ac4bb37846b33ac5a0413c7d6ad49a6b0c63c459","target":"graph","created_at":"2026-05-22T01:03:57Z","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/2602.12506/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) finetuning has become a key technique for enhancing large language models (LLMs) on reasoning-intensive tasks, motivating its extension to vision-language models (VLMs). While RL-tuned VLMs improve on visual reasoning benchmarks, they remain vulnerable to weak visual grounding, hallucinations, and over-reliance on textual cues. We show that simple, controlled textual perturbations, including misleading captions or incorrect chain-of-thought (CoT) traces, cause substantial drops in robustness and confidence, and that these effects are more pronounced when CoT consist","authors_text":"Anshul Shah, Arnab Mondal, Joerg Liebelt, Rosie Zhao, Xiaoyu Zhu, Xinke Deng, Yang Yang, Zhongyu Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-13T01:12:00Z","title":"On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.12506","kind":"arxiv","version":3},"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:de3c80a14cde39a9692c0ec8cda3d2622f38825a27d04a59b21c28e82ba9bfa1","target":"record","created_at":"2026-05-22T01:03:57Z","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":"9627cadb69aa69ad8e684ae540c54059152866d35ffbfe342548522d85f4aed6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-13T01:12:00Z","title_canon_sha256":"355c22f110541a844b03e50e8d4b7085ec85fda70924df4db6df49b8944b13d8"},"schema_version":"1.0","source":{"id":"2602.12506","kind":"arxiv","version":3}},"canonical_sha256":"e7365051e096b6f9ac2d5d7fce5d9bb8feca0a0694133c4f7e39cd9a3417a676","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7365051e096b6f9ac2d5d7fce5d9bb8feca0a0694133c4f7e39cd9a3417a676","first_computed_at":"2026-05-22T01:03:57.553834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:57.553834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZceJCchfLa9rnNuhZl7NT/c9ewZx9x0fpDro9NDII/W4Fl1VCu740X1s7KXvYTQP9zWeJR2F34cnATWbRYmHCA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:57.554766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.12506","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de3c80a14cde39a9692c0ec8cda3d2622f38825a27d04a59b21c28e82ba9bfa1","sha256:f68f8f271a7ea4d5719c9bf2ac4bb37846b33ac5a0413c7d6ad49a6b0c63c459"],"state_sha256":"10b06c69a9d733c0598c44f01f32f319f99aaabecd2f95cb9b2b2eb5149c5992"}