{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HBQNWEDYQHMKTIPES7MNUPYUEU","short_pith_number":"pith:HBQNWEDY","schema_version":"1.0","canonical_sha256":"3860db107881d8a9a1e497d8da3f142520076fb5acc35d29893e75cd61db867b","source":{"kind":"arxiv","id":"2605.13467","version":1},"attestation_state":"computed","paper":{"title":"PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Decomposing confidence rewards into perception and reasoning clusters improves vision-language model training.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chang D. Yoo, Chong Luo, Eunseop Yoon, Gwanhyeong Koo, Hee Suk Yoon, Ji Woo Hong, Mark Hasegawa-Johnson, Qi Dai, SooHwan Eom","submitted_at":"2026-05-13T12:55:18Z","abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) traditionally relies on a sparse, outcome-based signal. Recent work shows that providing a fine-grained, model-intrinsic signal (rewarding the confidence growth in the ground-truth answer) effectively improves language reasoning training by providing step-level guidance without costly external models. While effective for unimodal text, we find that naively applying this global reward to vision-language (V-L) reasoning is a suboptimal strategy, as the task is a heterogeneous mix of sparse visual perception and dense textual reasoning. This g"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13467","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T12:55:18Z","cross_cats_sorted":[],"title_canon_sha256":"3e63b5f0621ec24924545486c7cccd4d1e39f027abe3486fe1716415d604e51d","abstract_canon_sha256":"65fbf67244486fa2246b4d2fada7fcf3f61708833de83bfe592dc929f3070947"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:41.611661Z","signature_b64":"XGS+T65y99iAewShMz7PQwQIyQiDxRjlNDrYrOMNkPRTpf7OUaB2qio2adZshUonn2Ku7jqVZn+yoMicYeYiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3860db107881d8a9a1e497d8da3f142520076fb5acc35d29893e75cd61db867b","last_reissued_at":"2026-05-18T02:44:41.611045Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:41.611045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Decomposing confidence rewards into perception and reasoning clusters improves vision-language model training.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chang D. Yoo, Chong Luo, Eunseop Yoon, Gwanhyeong Koo, Hee Suk Yoon, Ji Woo Hong, Mark Hasegawa-Johnson, Qi Dai, SooHwan Eom","submitted_at":"2026-05-13T12:55:18Z","abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) traditionally relies on a sparse, outcome-based signal. Recent work shows that providing a fine-grained, model-intrinsic signal (rewarding the confidence growth in the ground-truth answer) effectively improves language reasoning training by providing step-level guidance without costly external models. While effective for unimodal text, we find that naively applying this global reward to vision-language (V-L) reasoning is a suboptimal strategy, as the task is a heterogeneous mix of sparse visual perception and dense textual reasoning. This g"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We demonstrate that PDCR outperforms the naive, global-reward formulation and sparse-reward baselines on key V-L reasoning benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The unsupervised clustering driven by the model-internal Visual Dependence Score accurately partitions steps into perception and reasoning without any labeled supervision or external verification.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PDCR improves vision-language reasoning by computing separate normalized confidence advantages for perception steps and reasoning steps after unsupervised decomposition.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Decomposing confidence rewards into perception and reasoning clusters improves vision-language model training.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"714cd5196fa51bd7896d97721fa492f8bbceff8d1586e8100f653db7bb716ee2"},"source":{"id":"2605.13467","kind":"arxiv","version":1},"verdict":{"id":"d9383de8-b038-4d3c-bb25-311e4729b4d7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:16:10.963422Z","strongest_claim":"We demonstrate that PDCR outperforms the naive, global-reward formulation and sparse-reward baselines on key V-L reasoning benchmarks.","one_line_summary":"PDCR improves vision-language reasoning by computing separate normalized confidence advantages for perception steps and reasoning steps after unsupervised decomposition.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The unsupervised clustering driven by the model-internal Visual Dependence Score accurately partitions steps into perception and reasoning without any labeled supervision or external verification.","pith_extraction_headline":"Decomposing confidence rewards into perception and reasoning clusters improves vision-language model training."},"references":{"count":79,"sample":[{"doi":"","year":2023,"title":"Gpt-4v(ision) system card. 2023. 1","work_id":"a549d3c1-1572-4949-8f9e-de9af53432a9","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","ref_index":2,"cited_arxiv_id":"2502.13923","is_internal_anchor":true},{"doi":"","year":2025,"title":"Vrprm: Process reward modeling via visual reasoning.arXiv preprint arXiv:2508.03556, 2025","work_id":"673ea4d5-7e09-4f7f-acf3-106a8e69f259","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"arXiv preprint arXiv:2505.23558 , year=","work_id":"cc9e5e98-c226-4e12-bf74-ff438225c4c0","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Ultrafeedback: Boosting language models with scaled ai feedback","work_id":"bc448bac-e570-4911-b8b6-fc2bf33a532a","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":79,"snapshot_sha256":"eaa94caf858d0e6c7ba30d5f326c505e9c792d75883c64c48a8460a16dd29639","internal_anchors":12},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.13467","created_at":"2026-05-18T02:44:41.611143+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13467v1","created_at":"2026-05-18T02:44:41.611143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13467","created_at":"2026-05-18T02:44:41.611143+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBQNWEDYQHMK","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBQNWEDYQHMKTIPE","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBQNWEDY","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HBQNWEDYQHMKTIPES7MNUPYUEU","json":"https://pith.science/pith/HBQNWEDYQHMKTIPES7MNUPYUEU.json","graph_json":"https://pith.science/api/pith-number/HBQNWEDYQHMKTIPES7MNUPYUEU/graph.json","events_json":"https://pith.science/api/pith-number/HBQNWEDYQHMKTIPES7MNUPYUEU/events.json","paper":"https://pith.science/paper/HBQNWEDY"},"agent_actions":{"view_html":"https://pith.science/pith/HBQNWEDYQHMKTIPES7MNUPYUEU","download_json":"https://pith.science/pith/HBQNWEDYQHMKTIPES7MNUPYUEU.json","view_paper":"https://pith.science/paper/HBQNWEDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13467&json=true","fetch_graph":"https://pith.science/api/pith-number/HBQNWEDYQHMKTIPES7MNUPYUEU/graph.json","fetch_events":"https://pith.science/api/pith-number/HBQNWEDYQHMKTIPES7MNUPYUEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBQNWEDYQHMKTIPES7MNUPYUEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBQNWEDYQHMKTIPES7MNUPYUEU/action/storage_attestation","attest_author":"https://pith.science/pith/HBQNWEDYQHMKTIPES7MNUPYUEU/action/author_attestation","sign_citation":"https://pith.science/pith/HBQNWEDYQHMKTIPES7MNUPYUEU/action/citation_signature","submit_replication":"https://pith.science/pith/HBQNWEDYQHMKTIPES7MNUPYUEU/action/replication_record"}},"created_at":"2026-05-18T02:44:41.611143+00:00","updated_at":"2026-05-18T02:44:41.611143+00:00"}