{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6AURHEBXAM4HKHFWICXMSNFD5I","short_pith_number":"pith:6AURHEBX","schema_version":"1.0","canonical_sha256":"f0291390370338751cb640aec934a3ea0d0a2d293605ad9bf2203c46f3da7885","source":{"kind":"arxiv","id":"2606.02564","version":1},"attestation_state":"computed","paper":{"title":"VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Liao, Junhao Cheng, Kun Gai, Liang Hou, Pengfei Wan, Tianxiong Zhong, Xin Tao","submitted_at":"2026-06-01T17:54:26Z","abstract_excerpt":"The recent \"Reasoning with Video\" paradigm utilizes Video Generation Models (VGMs) to generate temporally coherent visual trajectories to complete reasoning tasks. Although state-of-the-art VGMs excel at visual quality, they often struggle to understand and follow task-specific rules, leading to logical failures across diverse reasoning scenarios. Existing efforts try to utilize Vision-Language Models (VLMs) as problem pre-solvers to produce or refine textual guidance for the VGM. However, textual descriptions fail to capture intricate spatiotemporal details, and VGMs often struggle to faithfu"},"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":"2606.02564","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T17:54:26Z","cross_cats_sorted":[],"title_canon_sha256":"39341bdc5ffeb6c519bd4c4b700faed55ea4a441aa25bb6dfe404bd3132ec276","abstract_canon_sha256":"cd471be83d55d425e5fb6e3f6dc5e531f3fbe301f8789b7228f5255b4080c76d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:05:10.240171Z","signature_b64":"X/LUHAlBuWeOyBl8n5vEh0VQxEjFR0bnpmSQHMMgbhWhh8R5ZeBvVO7m4dRZU2j61l/Kj/HW/7KOB3+BUTAgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0291390370338751cb640aec934a3ea0d0a2d293605ad9bf2203c46f3da7885","last_reissued_at":"2026-06-02T03:05:10.239857Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:05:10.239857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Liao, Junhao Cheng, Kun Gai, Liang Hou, Pengfei Wan, Tianxiong Zhong, Xin Tao","submitted_at":"2026-06-01T17:54:26Z","abstract_excerpt":"The recent \"Reasoning with Video\" paradigm utilizes Video Generation Models (VGMs) to generate temporally coherent visual trajectories to complete reasoning tasks. Although state-of-the-art VGMs excel at visual quality, they often struggle to understand and follow task-specific rules, leading to logical failures across diverse reasoning scenarios. Existing efforts try to utilize Vision-Language Models (VLMs) as problem pre-solvers to produce or refine textual guidance for the VGM. However, textual descriptions fail to capture intricate spatiotemporal details, and VGMs often struggle to faithfu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02564","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/2606.02564/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":"2606.02564","created_at":"2026-06-02T03:05:10.239900+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02564v1","created_at":"2026-06-02T03:05:10.239900+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02564","created_at":"2026-06-02T03:05:10.239900+00:00"},{"alias_kind":"pith_short_12","alias_value":"6AURHEBXAM4H","created_at":"2026-06-02T03:05:10.239900+00:00"},{"alias_kind":"pith_short_16","alias_value":"6AURHEBXAM4HKHFW","created_at":"2026-06-02T03:05:10.239900+00:00"},{"alias_kind":"pith_short_8","alias_value":"6AURHEBX","created_at":"2026-06-02T03:05:10.239900+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/6AURHEBXAM4HKHFWICXMSNFD5I","json":"https://pith.science/pith/6AURHEBXAM4HKHFWICXMSNFD5I.json","graph_json":"https://pith.science/api/pith-number/6AURHEBXAM4HKHFWICXMSNFD5I/graph.json","events_json":"https://pith.science/api/pith-number/6AURHEBXAM4HKHFWICXMSNFD5I/events.json","paper":"https://pith.science/paper/6AURHEBX"},"agent_actions":{"view_html":"https://pith.science/pith/6AURHEBXAM4HKHFWICXMSNFD5I","download_json":"https://pith.science/pith/6AURHEBXAM4HKHFWICXMSNFD5I.json","view_paper":"https://pith.science/paper/6AURHEBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02564&json=true","fetch_graph":"https://pith.science/api/pith-number/6AURHEBXAM4HKHFWICXMSNFD5I/graph.json","fetch_events":"https://pith.science/api/pith-number/6AURHEBXAM4HKHFWICXMSNFD5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6AURHEBXAM4HKHFWICXMSNFD5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6AURHEBXAM4HKHFWICXMSNFD5I/action/storage_attestation","attest_author":"https://pith.science/pith/6AURHEBXAM4HKHFWICXMSNFD5I/action/author_attestation","sign_citation":"https://pith.science/pith/6AURHEBXAM4HKHFWICXMSNFD5I/action/citation_signature","submit_replication":"https://pith.science/pith/6AURHEBXAM4HKHFWICXMSNFD5I/action/replication_record"}},"created_at":"2026-06-02T03:05:10.239900+00:00","updated_at":"2026-06-02T03:05:10.239900+00:00"}