{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZYPW6L6ICFDWKJGGNJBJXO7KOF","short_pith_number":"pith:ZYPW6L6I","schema_version":"1.0","canonical_sha256":"ce1f6f2fc811476524c66a429bbbea7174bf1b21c6088e999aef763356820094","source":{"kind":"arxiv","id":"2608.10665","version":1},"attestation_state":"computed","paper":{"title":"VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensus","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.GT"],"primary_cat":"cs.AI","authors_text":"Amit Sharma, Kunal Tilaganji, Nagarajan Natarajan, Rohit Sinha, Tanuja Ganu, Vineeth Balasubramanian","submitted_at":"2026-08-11T08:46:38Z","abstract_excerpt":"Multimodal large language models often generate reasoning chains containing subtle errors that lead to incorrect answers. Current verification approaches have notable limitations. Existing approaches either require expensive labelled supervision with inconsistent cross-task performance or aggregate scores from multiple sources by simple aggregations, missing a key insight: when these scores disagree, that disagreement itself carries important information about whether a reasoning step is truly valid or not. We formalise this as a coupled scoring problem among disparate, frozen verifiers, inter"},"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":"2608.10665","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-11T08:46:38Z","cross_cats_sorted":["cs.CV","cs.GT"],"title_canon_sha256":"a7dd32e87d955671a2a70865bc23ec2e661976f5e6a8946d7dd93d7a7180a7bc","abstract_canon_sha256":"d5bc5ad49f0e3b75a794e743cf9527b916803c0882ec34f8d0891471f5db88bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:22:58.656168Z","signature_b64":"pt+CuxJwNSP4rs5w8iYRMJcYFhxmFSrZbw4vIo9GoNbrFD1M/omPv0tWFw2NYXDJzbXp4uv3oWc9B1QjY7bzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce1f6f2fc811476524c66a429bbbea7174bf1b21c6088e999aef763356820094","last_reissued_at":"2026-08-12T01:22:58.654571Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:22:58.654571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensus","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.GT"],"primary_cat":"cs.AI","authors_text":"Amit Sharma, Kunal Tilaganji, Nagarajan Natarajan, Rohit Sinha, Tanuja Ganu, Vineeth Balasubramanian","submitted_at":"2026-08-11T08:46:38Z","abstract_excerpt":"Multimodal large language models often generate reasoning chains containing subtle errors that lead to incorrect answers. Current verification approaches have notable limitations. Existing approaches either require expensive labelled supervision with inconsistent cross-task performance or aggregate scores from multiple sources by simple aggregations, missing a key insight: when these scores disagree, that disagreement itself carries important information about whether a reasoning step is truly valid or not. We formalise this as a coupled scoring problem among disparate, frozen verifiers, inter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10665","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/2608.10665/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":"2608.10665","created_at":"2026-08-12T01:22:58.658339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.10665v1","created_at":"2026-08-12T01:22:58.658339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10665","created_at":"2026-08-12T01:22:58.658339+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZYPW6L6ICFDW","created_at":"2026-08-12T01:22:58.658339+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZYPW6L6ICFDWKJGG","created_at":"2026-08-12T01:22:58.658339+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZYPW6L6I","created_at":"2026-08-12T01:22:58.658339+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/ZYPW6L6ICFDWKJGGNJBJXO7KOF","json":"https://pith.science/pith/ZYPW6L6ICFDWKJGGNJBJXO7KOF.json","graph_json":"https://pith.science/api/pith-number/ZYPW6L6ICFDWKJGGNJBJXO7KOF/graph.json","events_json":"https://pith.science/api/pith-number/ZYPW6L6ICFDWKJGGNJBJXO7KOF/events.json","paper":"https://pith.science/paper/ZYPW6L6I"},"agent_actions":{"view_html":"https://pith.science/pith/ZYPW6L6ICFDWKJGGNJBJXO7KOF","download_json":"https://pith.science/pith/ZYPW6L6ICFDWKJGGNJBJXO7KOF.json","view_paper":"https://pith.science/paper/ZYPW6L6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.10665&json=true","fetch_graph":"https://pith.science/api/pith-number/ZYPW6L6ICFDWKJGGNJBJXO7KOF/graph.json","fetch_events":"https://pith.science/api/pith-number/ZYPW6L6ICFDWKJGGNJBJXO7KOF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZYPW6L6ICFDWKJGGNJBJXO7KOF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZYPW6L6ICFDWKJGGNJBJXO7KOF/action/storage_attestation","attest_author":"https://pith.science/pith/ZYPW6L6ICFDWKJGGNJBJXO7KOF/action/author_attestation","sign_citation":"https://pith.science/pith/ZYPW6L6ICFDWKJGGNJBJXO7KOF/action/citation_signature","submit_replication":"https://pith.science/pith/ZYPW6L6ICFDWKJGGNJBJXO7KOF/action/replication_record"}},"created_at":"2026-08-12T01:22:58.658339+00:00","updated_at":"2026-08-12T01:22:58.658339+00:00"}