{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3LOHOJXSW5QCLE6N5ZE4DOJLU3","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":"8cd6cc29c0c6345b09f8c6d99359dc3dbf7ba428a6ee53a06fdbde26d1e6f368","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T07:20:49Z","title_canon_sha256":"d02f2912182669ffbdd4666ea53bd128502fe43987fe883493912e9f4b3a35ae"},"schema_version":"1.0","source":{"id":"2605.29496","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29496","created_at":"2026-05-29T01:05:42Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29496v1","created_at":"2026-05-29T01:05:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29496","created_at":"2026-05-29T01:05:42Z"},{"alias_kind":"pith_short_12","alias_value":"3LOHOJXSW5QC","created_at":"2026-05-29T01:05:42Z"},{"alias_kind":"pith_short_16","alias_value":"3LOHOJXSW5QCLE6N","created_at":"2026-05-29T01:05:42Z"},{"alias_kind":"pith_short_8","alias_value":"3LOHOJXS","created_at":"2026-05-29T01:05:42Z"}],"graph_snapshots":[{"event_id":"sha256:2cbd8f3266f060dec218de37bb9c7e747f7ae4e4d16b601582c1e3fd19c9963a","target":"graph","created_at":"2026-05-29T01:05:42Z","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/2605.29496/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training has greatly improved reasoning in frontier vision-language models, yet its gains for perception remain comparatively limited, creating a bottleneck for end-to-end visual reasoning. To investigate this gap, we introduce a controlled diagnostic framework with two synthetic tasks that disentangle perception from reasoning. Our analysis reveals a consistent perception-reasoning asymmetry: posttraining improves reasoning more substantially than perception, though the underlying mechanism differs by training paradigm. For supervised fine-tuning (SFT), this asymmetry stems from token im","authors_text":"Kai-Wei Chang, Nanyun Peng, Xueqing Wu, Yu-Chi Lin","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T07:20:49Z","title":"On Asymmetric Optimization of Reasoning and Perception in Vision-Language Model Post-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29496","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":"sha256:1db0cc492786e0c06471ea60ec46a466f2f02214243683f68adfec0b7a618341","target":"record","created_at":"2026-05-29T01:05:42Z","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":"8cd6cc29c0c6345b09f8c6d99359dc3dbf7ba428a6ee53a06fdbde26d1e6f368","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T07:20:49Z","title_canon_sha256":"d02f2912182669ffbdd4666ea53bd128502fe43987fe883493912e9f4b3a35ae"},"schema_version":"1.0","source":{"id":"2605.29496","kind":"arxiv","version":1}},"canonical_sha256":"dadc7726f2b7602593cdee49c1b92ba6eba3160d4aefdda68ce21769c2d3f0d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dadc7726f2b7602593cdee49c1b92ba6eba3160d4aefdda68ce21769c2d3f0d7","first_computed_at":"2026-05-29T01:05:42.789063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:42.789063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+k2km2OjUkYQp/Kyp3Tric7Z2T0Xyqy/i1b6m6OECPs4n3wHsz3QPpY7htqx9qvqDgHZcLl3n2MISBMoPMZeBA==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:42.789960Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29496","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1db0cc492786e0c06471ea60ec46a466f2f02214243683f68adfec0b7a618341","sha256:2cbd8f3266f060dec218de37bb9c7e747f7ae4e4d16b601582c1e3fd19c9963a"],"state_sha256":"e87d821b3796ab9bda0ec3678d1101f705441d2ed17a9f6799f45a3b0169285c"}