{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WUGTTVIDXKCXBQV3XNLZZFFDDA","short_pith_number":"pith:WUGTTVID","schema_version":"1.0","canonical_sha256":"b50d39d503ba8570c2bbbb579c94a3181c789a769a35b3218a3d73d542225207","source":{"kind":"arxiv","id":"2606.11576","version":1},"attestation_state":"computed","paper":{"title":"AVIS: Adaptive Test-Time Scaling for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ahmadreza Jeddi, Alex Levinshtein, Amirhossein Kazerouni, Babak Taati, Hakki Can Karaimer, Hue Nguyen, Iqbal Mohomed, Konstantinos G. Derpanis, Michael Brudno, Minh Ngoc Le, Radek Grzeszczuk","submitted_at":"2026-06-10T02:06:47Z","abstract_excerpt":"Modern Vision-Language Models (VLMs) benefit from chain-of-thought prompting and test-time scaling, but these gains often come with prohibitive inference cost due to large visual contexts and long decoding chains. We view this cost through two coupled axes: Visual Context Scaling (VCS), which controls how much visual evidence is passed to the language model, and Visual Reasoning Scaling (VRS), which controls how much inference-time reasoning search is performed. Existing methods typically optimize one axis at a time, leaving the joint allocation of compute across these axes underexplored. We i"},"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":"2606.11576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T02:06:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94ef82de0e6f471d99d7f6a4863c10cfad2f7593e5ddcf9754385441c1fcd195","abstract_canon_sha256":"2ce2058987fbec1b2b06723d7f3480023bf3b4fc153db1167d135067411d1647"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:57.043512Z","signature_b64":"oj6yTpvlfyCtlxuo8XTyQkcUO32fY/R0SMUhsRDCbPfhIz19hkN4UKIkmuBRkOUdfrK9r1Qg8rqGdzI/ECfnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b50d39d503ba8570c2bbbb579c94a3181c789a769a35b3218a3d73d542225207","last_reissued_at":"2026-06-11T01:09:57.042629Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:57.042629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AVIS: Adaptive Test-Time Scaling for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ahmadreza Jeddi, Alex Levinshtein, Amirhossein Kazerouni, Babak Taati, Hakki Can Karaimer, Hue Nguyen, Iqbal Mohomed, Konstantinos G. Derpanis, Michael Brudno, Minh Ngoc Le, Radek Grzeszczuk","submitted_at":"2026-06-10T02:06:47Z","abstract_excerpt":"Modern Vision-Language Models (VLMs) benefit from chain-of-thought prompting and test-time scaling, but these gains often come with prohibitive inference cost due to large visual contexts and long decoding chains. We view this cost through two coupled axes: Visual Context Scaling (VCS), which controls how much visual evidence is passed to the language model, and Visual Reasoning Scaling (VRS), which controls how much inference-time reasoning search is performed. Existing methods typically optimize one axis at a time, leaving the joint allocation of compute across these axes underexplored. We i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11576","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/2606.11576/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":"2606.11576","created_at":"2026-06-11T01:09:57.042773+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11576v1","created_at":"2026-06-11T01:09:57.042773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11576","created_at":"2026-06-11T01:09:57.042773+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUGTTVIDXKCX","created_at":"2026-06-11T01:09:57.042773+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUGTTVIDXKCXBQV3","created_at":"2026-06-11T01:09:57.042773+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUGTTVID","created_at":"2026-06-11T01:09:57.042773+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/WUGTTVIDXKCXBQV3XNLZZFFDDA","json":"https://pith.science/pith/WUGTTVIDXKCXBQV3XNLZZFFDDA.json","graph_json":"https://pith.science/api/pith-number/WUGTTVIDXKCXBQV3XNLZZFFDDA/graph.json","events_json":"https://pith.science/api/pith-number/WUGTTVIDXKCXBQV3XNLZZFFDDA/events.json","paper":"https://pith.science/paper/WUGTTVID"},"agent_actions":{"view_html":"https://pith.science/pith/WUGTTVIDXKCXBQV3XNLZZFFDDA","download_json":"https://pith.science/pith/WUGTTVIDXKCXBQV3XNLZZFFDDA.json","view_paper":"https://pith.science/paper/WUGTTVID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11576&json=true","fetch_graph":"https://pith.science/api/pith-number/WUGTTVIDXKCXBQV3XNLZZFFDDA/graph.json","fetch_events":"https://pith.science/api/pith-number/WUGTTVIDXKCXBQV3XNLZZFFDDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUGTTVIDXKCXBQV3XNLZZFFDDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUGTTVIDXKCXBQV3XNLZZFFDDA/action/storage_attestation","attest_author":"https://pith.science/pith/WUGTTVIDXKCXBQV3XNLZZFFDDA/action/author_attestation","sign_citation":"https://pith.science/pith/WUGTTVIDXKCXBQV3XNLZZFFDDA/action/citation_signature","submit_replication":"https://pith.science/pith/WUGTTVIDXKCXBQV3XNLZZFFDDA/action/replication_record"}},"created_at":"2026-06-11T01:09:57.042773+00:00","updated_at":"2026-06-11T01:09:57.042773+00:00"}