{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OBERZTN4QKETOO2ADL5LVKNHWU","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":"e8e657301d2c437c783a07f1a5cd34f6ead69e4bcce0dde4d5731d1ae234c494","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T12:35:05Z","title_canon_sha256":"454e074abc95a0dfa79862ccaa6fd14bff4f77e9d319300a6cc95e538e038379"},"schema_version":"1.0","source":{"id":"2607.17884","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17884","created_at":"2026-07-21T02:22:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17884v1","created_at":"2026-07-21T02:22:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17884","created_at":"2026-07-21T02:22:04Z"},{"alias_kind":"pith_short_12","alias_value":"OBERZTN4QKET","created_at":"2026-07-21T02:22:04Z"},{"alias_kind":"pith_short_16","alias_value":"OBERZTN4QKETOO2A","created_at":"2026-07-21T02:22:04Z"},{"alias_kind":"pith_short_8","alias_value":"OBERZTN4","created_at":"2026-07-21T02:22:04Z"}],"graph_snapshots":[{"event_id":"sha256:d3c35a788b3df27bc2abeb5a72792fa467824930b64aa07bee8c4ae6db3a505b","target":"graph","created_at":"2026-07-21T02:22:04Z","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/2607.17884/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) achieve strong reasoning with Chain-of-Thought (CoT) prompting but incur high sequential-generation cost, error accumulation, and limited self-correction. Diffusion Multimodal Large Language Models (dMLLMs) unmask tokens in an order-agnostic process, improving efficiency and enabling iterative refinement, yet their reasoning and how to enhance it remain underexplored. We propose a training-free method, Spatio-Temporal Token Veto (ST-Veto), which leverages the ability to observe all token positions at each diffusion step. Rather than relying only on current-step co","authors_text":"Beomseok Lee, Hyunwoo Kim, Keuntae Kim, Yong Suk Choi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T12:35:05Z","title":"ST-Veto: Spatio-Temporal Token Veto for Diffusion MLLMs via Taylor Prediction and Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17884","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":"sha256:595f8295afe6a455eea83ed58622b1884cbc625bc661c2bbe40409749110a88e","target":"record","created_at":"2026-07-21T02:22:04Z","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":"e8e657301d2c437c783a07f1a5cd34f6ead69e4bcce0dde4d5731d1ae234c494","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T12:35:05Z","title_canon_sha256":"454e074abc95a0dfa79862ccaa6fd14bff4f77e9d319300a6cc95e538e038379"},"schema_version":"1.0","source":{"id":"2607.17884","kind":"arxiv","version":1}},"canonical_sha256":"70491ccdbc8289373b401afabaa9a7b52a760bfb1679e6ff2dd4d1d318d4cfc3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70491ccdbc8289373b401afabaa9a7b52a760bfb1679e6ff2dd4d1d318d4cfc3","first_computed_at":"2026-07-21T02:22:04.985829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T02:22:04.985829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rj4/Z/2LyzXRgs1T+zX7a1ufkSeClZXdkbdTILIW0DqZ2kDLHIEz+mkoO4GJPb6csmoW9t54f4Y3l/oSqO65CQ==","signature_status":"signed_v1","signed_at":"2026-07-21T02:22:04.986647Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.17884","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:595f8295afe6a455eea83ed58622b1884cbc625bc661c2bbe40409749110a88e","sha256:d3c35a788b3df27bc2abeb5a72792fa467824930b64aa07bee8c4ae6db3a505b"],"state_sha256":"979855c3668b37044353b3363dcad8f6abafa75b16e45babbb6f9e1d4f42b5f9"}