{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5DT3YTZOTOHGXT3UXAI3IWWVQX","short_pith_number":"pith:5DT3YTZO","schema_version":"1.0","canonical_sha256":"e8e7bc4f2e9b8e6bcf74b811b45ad585ce5c1e61ada338c92fc00f7934bc5623","source":{"kind":"arxiv","id":"2606.30217","version":1},"attestation_state":"computed","paper":{"title":"Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caifeng Shan, Chen Ma, Haokun Lin, Li Zhu, Teng Wang, Yichen Wu, Yinan Zhou, Ying Shan, Yuxin Chen, Zhenan Sun","submitted_at":"2026-06-29T12:30:24Z","abstract_excerpt":"Large multimodal models have achieved strong reasoning on complex visual tasks, but their inference efficiency is often restricted by long chains of thought. A promising solution is to pair a small draft model with a large target model, enabling cooperative inference employing a routing signal that adaptively routes queries to either the draft or target model based on their difficulties for optimal efficiency and accuracy. Yet, the remaining bottleneck is to establish a reliable query difficulty signal under multimodal settings. Existing approaches designed for language models either rely on p"},"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":"2606.30217","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T12:30:24Z","cross_cats_sorted":[],"title_canon_sha256":"1288f15a8092cb987dd72b1865ceab91ea6e6586d3557a6b9f90f45e9442885b","abstract_canon_sha256":"e21c75d0c226739aa1cfd203a399d3808acbcc0cc5f9f5ac9cf95cf4c10b50dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:54.833458Z","signature_b64":"HDm0QciCUv9b9Cqos+e+nuTWrDC5ogZvxwUj6xBj6QRKDnwkEdNbXD3zfLaAwTEKgWm5cqWL/8jsisi2jce7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8e7bc4f2e9b8e6bcf74b811b45ad585ce5c1e61ada338c92fc00f7934bc5623","last_reissued_at":"2026-06-30T02:17:54.832841Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:54.832841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caifeng Shan, Chen Ma, Haokun Lin, Li Zhu, Teng Wang, Yichen Wu, Yinan Zhou, Ying Shan, Yuxin Chen, Zhenan Sun","submitted_at":"2026-06-29T12:30:24Z","abstract_excerpt":"Large multimodal models have achieved strong reasoning on complex visual tasks, but their inference efficiency is often restricted by long chains of thought. A promising solution is to pair a small draft model with a large target model, enabling cooperative inference employing a routing signal that adaptively routes queries to either the draft or target model based on their difficulties for optimal efficiency and accuracy. Yet, the remaining bottleneck is to establish a reliable query difficulty signal under multimodal settings. Existing approaches designed for language models either rely on p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30217","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/2606.30217/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":"2606.30217","created_at":"2026-06-30T02:17:54.832940+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30217v1","created_at":"2026-06-30T02:17:54.832940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30217","created_at":"2026-06-30T02:17:54.832940+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DT3YTZOTOHG","created_at":"2026-06-30T02:17:54.832940+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DT3YTZOTOHGXT3U","created_at":"2026-06-30T02:17:54.832940+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DT3YTZO","created_at":"2026-06-30T02:17:54.832940+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/5DT3YTZOTOHGXT3UXAI3IWWVQX","json":"https://pith.science/pith/5DT3YTZOTOHGXT3UXAI3IWWVQX.json","graph_json":"https://pith.science/api/pith-number/5DT3YTZOTOHGXT3UXAI3IWWVQX/graph.json","events_json":"https://pith.science/api/pith-number/5DT3YTZOTOHGXT3UXAI3IWWVQX/events.json","paper":"https://pith.science/paper/5DT3YTZO"},"agent_actions":{"view_html":"https://pith.science/pith/5DT3YTZOTOHGXT3UXAI3IWWVQX","download_json":"https://pith.science/pith/5DT3YTZOTOHGXT3UXAI3IWWVQX.json","view_paper":"https://pith.science/paper/5DT3YTZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30217&json=true","fetch_graph":"https://pith.science/api/pith-number/5DT3YTZOTOHGXT3UXAI3IWWVQX/graph.json","fetch_events":"https://pith.science/api/pith-number/5DT3YTZOTOHGXT3UXAI3IWWVQX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DT3YTZOTOHGXT3UXAI3IWWVQX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DT3YTZOTOHGXT3UXAI3IWWVQX/action/storage_attestation","attest_author":"https://pith.science/pith/5DT3YTZOTOHGXT3UXAI3IWWVQX/action/author_attestation","sign_citation":"https://pith.science/pith/5DT3YTZOTOHGXT3UXAI3IWWVQX/action/citation_signature","submit_replication":"https://pith.science/pith/5DT3YTZOTOHGXT3UXAI3IWWVQX/action/replication_record"}},"created_at":"2026-06-30T02:17:54.832940+00:00","updated_at":"2026-06-30T02:17:54.832940+00:00"}