{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LJ5CNM6XR66DPEWK6JA6ISKFXW","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":"5d6f66b121cf943aebe8fa38a0002b8de2411d362734c46e9e52e8f184358b90","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-07T16:06:29Z","title_canon_sha256":"b9e054fafb142e282f00abccbe4053245d3b0c103fe0481c603d000f67ea917f"},"schema_version":"1.0","source":{"id":"2606.08708","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08708","created_at":"2026-06-09T01:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08708v1","created_at":"2026-06-09T01:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08708","created_at":"2026-06-09T01:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"LJ5CNM6XR66D","created_at":"2026-06-09T01:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"LJ5CNM6XR66DPEWK","created_at":"2026-06-09T01:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"LJ5CNM6X","created_at":"2026-06-09T01:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:ae790fa7fdf12a16afc29ad60069b322c4480960051d7b4b8c4e7d488afb1de1","target":"graph","created_at":"2026-06-09T01:05:47Z","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/2606.08708/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective paradigm for improving the reasoning capability of Large Vision-Language Models (LVLMs). However, existing RLVR methods primarily rely on trajectory-level outcome rewards, which assign identical learning signals across all generated tokens. This coarse-grained credit assignment is fundamentally mismatched to multimodal reasoning, where only a sparse subset of tokens is causally grounded in visual evidence. Consequently, these pivotal perceptual tokens receive weak supervision and are often overwhelmed by language pri","authors_text":"Hangyu Li, Kaitao Jiang, Kangning Niu, Mu Xu, Qiming Li, Ruiyan Gong, Tianlun Li, Xiaolong Cheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-07T16:06:29Z","title":"PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08708","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:ced7cf5245f5fcb7e27952c9553f23f7077f57fdfd2149fca6bed65e22daf1c5","target":"record","created_at":"2026-06-09T01:05:47Z","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":"5d6f66b121cf943aebe8fa38a0002b8de2411d362734c46e9e52e8f184358b90","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-07T16:06:29Z","title_canon_sha256":"b9e054fafb142e282f00abccbe4053245d3b0c103fe0481c603d000f67ea917f"},"schema_version":"1.0","source":{"id":"2606.08708","kind":"arxiv","version":1}},"canonical_sha256":"5a7a26b3d78fbc3792caf241e44945bd8a704e9678ee1c4f830b98e6e09e0877","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a7a26b3d78fbc3792caf241e44945bd8a704e9678ee1c4f830b98e6e09e0877","first_computed_at":"2026-06-09T01:05:47.947029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:47.947029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mFedTNqT0VMbRov6BRyyNGnx5AmRapk9vcOK3aAnjGjF57QNr6C3lmiXp5jjw7eLoyPWY31/hICB7tsc+qqgBA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:47.947436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08708","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ced7cf5245f5fcb7e27952c9553f23f7077f57fdfd2149fca6bed65e22daf1c5","sha256:ae790fa7fdf12a16afc29ad60069b322c4480960051d7b4b8c4e7d488afb1de1"],"state_sha256":"57a4a693d49507e8b55039efc8a72bec70ac787c3c40aa8b2ead5b1c86232dcb"}