{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OBERZTN4QKETOO2ADL5LVKNHWU","short_pith_number":"pith:OBERZTN4","schema_version":"1.0","canonical_sha256":"70491ccdbc8289373b401afabaa9a7b52a760bfb1679e6ff2dd4d1d318d4cfc3","source":{"kind":"arxiv","id":"2607.17884","version":1},"attestation_state":"computed","paper":{"title":"ST-Veto: Spatio-Temporal Token Veto for Diffusion MLLMs via Taylor Prediction and Visual Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Beomseok Lee, Hyunwoo Kim, Keuntae Kim, Yong Suk Choi","submitted_at":"2026-07-20T12:35:05Z","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"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.17884","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T12:35:05Z","cross_cats_sorted":[],"title_canon_sha256":"454e074abc95a0dfa79862ccaa6fd14bff4f77e9d319300a6cc95e538e038379","abstract_canon_sha256":"e8e657301d2c437c783a07f1a5cd34f6ead69e4bcce0dde4d5731d1ae234c494"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T02:22:04.986647Z","signature_b64":"rj4/Z/2LyzXRgs1T+zX7a1ufkSeClZXdkbdTILIW0DqZ2kDLHIEz+mkoO4GJPb6csmoW9t54f4Y3l/oSqO65CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70491ccdbc8289373b401afabaa9a7b52a760bfb1679e6ff2dd4d1d318d4cfc3","last_reissued_at":"2026-07-21T02:22:04.985829Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T02:22:04.985829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ST-Veto: Spatio-Temporal Token Veto for Diffusion MLLMs via Taylor Prediction and Visual Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Beomseok Lee, Hyunwoo Kim, Keuntae Kim, Yong Suk Choi","submitted_at":"2026-07-20T12:35:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17884","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.17884/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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":"2607.17884","created_at":"2026-07-21T02:22:04.986252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17884v1","created_at":"2026-07-21T02:22:04.986252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17884","created_at":"2026-07-21T02:22:04.986252+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBERZTN4QKET","created_at":"2026-07-21T02:22:04.986252+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBERZTN4QKETOO2A","created_at":"2026-07-21T02:22:04.986252+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBERZTN4","created_at":"2026-07-21T02:22:04.986252+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/OBERZTN4QKETOO2ADL5LVKNHWU","json":"https://pith.science/pith/OBERZTN4QKETOO2ADL5LVKNHWU.json","graph_json":"https://pith.science/api/pith-number/OBERZTN4QKETOO2ADL5LVKNHWU/graph.json","events_json":"https://pith.science/api/pith-number/OBERZTN4QKETOO2ADL5LVKNHWU/events.json","paper":"https://pith.science/paper/OBERZTN4"},"agent_actions":{"view_html":"https://pith.science/pith/OBERZTN4QKETOO2ADL5LVKNHWU","download_json":"https://pith.science/pith/OBERZTN4QKETOO2ADL5LVKNHWU.json","view_paper":"https://pith.science/paper/OBERZTN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17884&json=true","fetch_graph":"https://pith.science/api/pith-number/OBERZTN4QKETOO2ADL5LVKNHWU/graph.json","fetch_events":"https://pith.science/api/pith-number/OBERZTN4QKETOO2ADL5LVKNHWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBERZTN4QKETOO2ADL5LVKNHWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBERZTN4QKETOO2ADL5LVKNHWU/action/storage_attestation","attest_author":"https://pith.science/pith/OBERZTN4QKETOO2ADL5LVKNHWU/action/author_attestation","sign_citation":"https://pith.science/pith/OBERZTN4QKETOO2ADL5LVKNHWU/action/citation_signature","submit_replication":"https://pith.science/pith/OBERZTN4QKETOO2ADL5LVKNHWU/action/replication_record"}},"created_at":"2026-07-21T02:22:04.986252+00:00","updated_at":"2026-07-21T02:22:04.986252+00:00"}