{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AM4BYPOVTRXBKS6GX2V3MYBZHU","short_pith_number":"pith:AM4BYPOV","schema_version":"1.0","canonical_sha256":"03381c3dd59c6e154bc6beabb660393d09e63c250d97fa159ed7c17c58561880","source":{"kind":"arxiv","id":"2606.04323","version":1},"attestation_state":"computed","paper":{"title":"Answer Self-Consistency with Margin-Triggered Question Re-Arbitration for the CVPR 2026 VidLLMs Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hiroyasu Okuno, Tomoya Miyazawa","submitted_at":"2026-06-03T00:51:55Z","abstract_excerpt":"In this report, we present our solution for Track 2 of the CVPR 2026 VidLLMs Challenge. This track evaluates visual relational reasoning in videos, where models must infer relations that are not always explicitly visible. We propose Answer Self-Consistency with Margin-Triggered Question Re-Arbitration (ASC-MQRA), a training-free test-time reasoning framework built on a multimodal reasoning model. The core ASC component performs multiple stochastic video question-answering runs and aggregates their answer choices through answer-level self-consistency. This substantially improves over single-pas"},"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":"2606.04323","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T00:51:55Z","cross_cats_sorted":[],"title_canon_sha256":"728438cc0e61ea354e4385176098d2a17b381a5b51865cc87a196ec9e893015c","abstract_canon_sha256":"e2be47b11a2470e5561677215c2c3036e3ab825e50db89c25f53764f4d96e402"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:03.594935Z","signature_b64":"qWM9h4GwojitvNeSUy/XuUQD1yGPAXYziaknDs7+vDrrthXABKk4MZ3PXQhINc3/6PJmghp7EXU47lX6XNsZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03381c3dd59c6e154bc6beabb660393d09e63c250d97fa159ed7c17c58561880","last_reissued_at":"2026-06-04T01:09:03.594467Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:03.594467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Answer Self-Consistency with Margin-Triggered Question Re-Arbitration for the CVPR 2026 VidLLMs Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hiroyasu Okuno, Tomoya Miyazawa","submitted_at":"2026-06-03T00:51:55Z","abstract_excerpt":"In this report, we present our solution for Track 2 of the CVPR 2026 VidLLMs Challenge. This track evaluates visual relational reasoning in videos, where models must infer relations that are not always explicitly visible. We propose Answer Self-Consistency with Margin-Triggered Question Re-Arbitration (ASC-MQRA), a training-free test-time reasoning framework built on a multimodal reasoning model. The core ASC component performs multiple stochastic video question-answering runs and aggregates their answer choices through answer-level self-consistency. This substantially improves over single-pas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04323","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/2606.04323/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":"2606.04323","created_at":"2026-06-04T01:09:03.594538+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04323v1","created_at":"2026-06-04T01:09:03.594538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04323","created_at":"2026-06-04T01:09:03.594538+00:00"},{"alias_kind":"pith_short_12","alias_value":"AM4BYPOVTRXB","created_at":"2026-06-04T01:09:03.594538+00:00"},{"alias_kind":"pith_short_16","alias_value":"AM4BYPOVTRXBKS6G","created_at":"2026-06-04T01:09:03.594538+00:00"},{"alias_kind":"pith_short_8","alias_value":"AM4BYPOV","created_at":"2026-06-04T01:09:03.594538+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/AM4BYPOVTRXBKS6GX2V3MYBZHU","json":"https://pith.science/pith/AM4BYPOVTRXBKS6GX2V3MYBZHU.json","graph_json":"https://pith.science/api/pith-number/AM4BYPOVTRXBKS6GX2V3MYBZHU/graph.json","events_json":"https://pith.science/api/pith-number/AM4BYPOVTRXBKS6GX2V3MYBZHU/events.json","paper":"https://pith.science/paper/AM4BYPOV"},"agent_actions":{"view_html":"https://pith.science/pith/AM4BYPOVTRXBKS6GX2V3MYBZHU","download_json":"https://pith.science/pith/AM4BYPOVTRXBKS6GX2V3MYBZHU.json","view_paper":"https://pith.science/paper/AM4BYPOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04323&json=true","fetch_graph":"https://pith.science/api/pith-number/AM4BYPOVTRXBKS6GX2V3MYBZHU/graph.json","fetch_events":"https://pith.science/api/pith-number/AM4BYPOVTRXBKS6GX2V3MYBZHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AM4BYPOVTRXBKS6GX2V3MYBZHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AM4BYPOVTRXBKS6GX2V3MYBZHU/action/storage_attestation","attest_author":"https://pith.science/pith/AM4BYPOVTRXBKS6GX2V3MYBZHU/action/author_attestation","sign_citation":"https://pith.science/pith/AM4BYPOVTRXBKS6GX2V3MYBZHU/action/citation_signature","submit_replication":"https://pith.science/pith/AM4BYPOVTRXBKS6GX2V3MYBZHU/action/replication_record"}},"created_at":"2026-06-04T01:09:03.594538+00:00","updated_at":"2026-06-04T01:09:03.594538+00:00"}