{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GBKI5NPL6WU4CFHEDEUJPXC4TF","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":"ed320cc57fdf501bdaa4a6350f5a0e1d7b724af7b3884273d0d80db9197202f4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-20T17:33:07Z","title_canon_sha256":"daa5ffa614144acb6d83d8496763d6037b720d1f83b1b2001ba78b126ade3b27"},"schema_version":"1.0","source":{"id":"2606.22158","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22158","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22158v1","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22158","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"GBKI5NPL6WU4","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"GBKI5NPL6WU4CFHE","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"GBKI5NPL","created_at":"2026-06-23T02:13:29Z"}],"graph_snapshots":[{"event_id":"sha256:0560cdeddc0001b0f42d668cf76f1da099f6fd410e07920f2d61cc055c8573d2","target":"graph","created_at":"2026-06-23T02:13:29Z","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/2606.22158/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Achieving human-like reasoning in Vision-Language Models (VLMs) remains a long-standing challenge. Recent approaches leverage Chain-of-Thought (CoT) rationales generated by human annotators or proprietary models to improve reasoning, which is costly and difficult to scale. Self-training offers a promising alternative by using models own outputs as supervision. However, existing methods often suffer from visual hallucinations -- where rationales describe non-existent visual content, and language shortcuts -- where predictions rely on textual priors rather than true visual grounding, as rational","authors_text":"Sadbhawna Thakur, Sonam Gupta, Sourabh Sharma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-20T17:33:07Z","title":"Improving Reasoning in Vision-Language Models via Perception Verified Self-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22158","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":"sha256:77c6e73226817d462f540123d747140b9d73acb2798db6077744f2f6a7aee93b","target":"record","created_at":"2026-06-23T02:13:29Z","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":"ed320cc57fdf501bdaa4a6350f5a0e1d7b724af7b3884273d0d80db9197202f4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-20T17:33:07Z","title_canon_sha256":"daa5ffa614144acb6d83d8496763d6037b720d1f83b1b2001ba78b126ade3b27"},"schema_version":"1.0","source":{"id":"2606.22158","kind":"arxiv","version":1}},"canonical_sha256":"30548eb5ebf5a9c114e4192897dc5c99782bda7ad7b87373664702f5e9fffa0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30548eb5ebf5a9c114e4192897dc5c99782bda7ad7b87373664702f5e9fffa0b","first_computed_at":"2026-06-23T02:13:29.876590Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:29.876590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8s3swfIKKZbrKsOm1zDRutm6mMNihUX5SWbNhfEwl1dTDH4fsvudxzQ/RACeVOfF8PJcTNutxYtEHDD98+GEDA==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:29.876969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22158","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77c6e73226817d462f540123d747140b9d73acb2798db6077744f2f6a7aee93b","sha256:0560cdeddc0001b0f42d668cf76f1da099f6fd410e07920f2d61cc055c8573d2"],"state_sha256":"1e69520bed2ff3dd22459c5ae0311dc600aa187ec7dca22cbb9445f5e23194e2"}