{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VC5XR6NDM2XCJ3SSWLNZ45HXOV","merge_version":"pith-open-graph-merge-v1","event_count":12,"valid_event_count":12,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2213cbd89b3e79e5ad300758e79f2d652126ca31e96b7bb3eb005603a267aede","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T17:58:40Z","title_canon_sha256":"a10070eaf367e50fea04f65a7e478307f528e2a5fda74bf2261a79b9b78b51e0"},"schema_version":"1.0","source":{"id":"2605.20177","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20177","created_at":"2026-05-20T02:06:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20177v1","created_at":"2026-05-20T02:06:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20177","created_at":"2026-05-20T02:06:06Z"},{"alias_kind":"pith_short_12","alias_value":"VC5XR6NDM2XC","created_at":"2026-05-20T02:06:06Z"},{"alias_kind":"pith_short_16","alias_value":"VC5XR6NDM2XCJ3SS","created_at":"2026-05-20T02:06:06Z"},{"alias_kind":"pith_short_8","alias_value":"VC5XR6ND","created_at":"2026-05-20T02:06:06Z"}],"graph_snapshots":[{"event_id":"sha256:63312a22923791bff08be20bc36a7afbcb010ebbc1969af883f9c2f853da9c51","target":"graph","created_at":"2026-05-20T02:06:06Z","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/2605.20177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in vision-language models (VLMs) emphasize long chain-of-thought reasoning; yet, we find that their performance on visual tasks is primarily limited by a lack of visual perception as opposed to reasoning itself. In this work, we systematically study the interplay between perception and reasoning in VLM post-training by decomposing their capabilities into three separate training stages: visual perception, visual reasoning, and textual reasoning, incorporating specialized training data. We demonstrate that visual perception (a) requires targeted optimization with specialized data","authors_text":"Cihang Xie, Freda Shi, Hanqing Lu, Haoqin Tu, Hardy Chen, Hui Liu, Juncheng Wu, Xianfeng Tang, Yuyin Zhou","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T17:58:40Z","title":"From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20177","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":"sha256:97ca85cd5cb89c87ec84d243a17d6bf48a7b799e476b68421e92a748c02af4a3","target":"record","created_at":"2026-05-20T02:06:06Z","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":"2213cbd89b3e79e5ad300758e79f2d652126ca31e96b7bb3eb005603a267aede","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T17:58:40Z","title_canon_sha256":"a10070eaf367e50fea04f65a7e478307f528e2a5fda74bf2261a79b9b78b51e0"},"schema_version":"1.0","source":{"id":"2605.20177","kind":"arxiv","version":1}},"canonical_sha256":"a8bb78f9a366ae24ee52b2db9e74f7756cfc4b29f4499349444a679f2fbb4be6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8bb78f9a366ae24ee52b2db9e74f7756cfc4b29f4499349444a679f2fbb4be6","first_computed_at":"2026-05-20T02:06:06.423579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T02:06:06.423579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GjFDA8fsA+u9AJ1OkMC85yf4onHSL4A1Hm/cUYPl36Av0G1phZqcrktC6TED5p6oFh5VcMtzSiG1IAU10B0zDA==","signature_status":"signed_v1","signed_at":"2026-05-20T02:06:06.424408Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20177","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:36fe164d995f738ce49b03e5e6cf30491cc3b3e0237e52fcdf733089833714b0","sha256:4228cc874aeacde671911e7f15f292f117bf6a81937b353cd2e3e19fc5ed4dba","sha256:4c3dea3210200a10be0665635489b89781e7d7e1357c1bbf4f192c8b0935fea4","sha256:5a41202727f4dedb1004b3e727f290f5651a0f4f499caeaab3d0436c3ba5e662","sha256:8161d2e77c80b684de7ad01e7a39fe8066d66ca6bb419efbb7c1151517c08795","sha256:9dc48a7765e10b136738fc2fef42f285b7660aad6b35ebae86f80554af8c9012","sha256:a48e61d704c44eaf343c03b3dfe8c3ed76a3be53b964077efce6a08e72e13d81","sha256:d1bac01b18f39c9918af303ca0bfce634baa321ab9b1bd902def0fc5451ac1c4","sha256:daced8252ea819ac19a67c15b6d01e2d7c706740b65eb995eb0aa352ce6ac09a","sha256:f8ca91ab99373a72c617410d0dba93aafefe753a01d2bd66cac1c3f594385118"]}],"invalid_events":[],"applied_event_ids":["sha256:97ca85cd5cb89c87ec84d243a17d6bf48a7b799e476b68421e92a748c02af4a3","sha256:63312a22923791bff08be20bc36a7afbcb010ebbc1969af883f9c2f853da9c51"],"state_sha256":"f9178fcddd7940a5bc9ad3aade1fb1ab9103eed83793a614ea022edd1c5956f2"}