{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CVJE7BZESSRMLKGJXZ4K3AFYHT","short_pith_number":"pith:CVJE7BZE","schema_version":"1.0","canonical_sha256":"15524f872494a2c5a8c9be78ad80b83cee94d1b7ade96900a9ab558437837a1d","source":{"kind":"arxiv","id":"2606.28864","version":1},"attestation_state":"computed","paper":{"title":"On Test-Time Scaling for Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fawaz Sammani, Nikos Deligiannis, Tzoulio Chamiti","submitted_at":"2026-06-27T11:12:42Z","abstract_excerpt":"Test-time scaling is a paradigm where large models use additional compute at inference to achieve better performance, without changing model weights. While it has been widely studied for Large Language Models (LLMs), its applicability to Large Vision-Language Models (LVLMs) remains less explored and analyzed, with limited analysis of whether, when, and to what extent these approaches transfer to LVLMs. In this work, we ask a simple but fundamental question: can conventional test-time scaling methods developed for LLMs be directly applied to LVLMs? We present the first comprehensive study of te"},"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":"2606.28864","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-27T11:12:42Z","cross_cats_sorted":[],"title_canon_sha256":"cb67624f5ee81e2de7fd44996165ab2c9244620e707f743fe0332fb0cbc215f4","abstract_canon_sha256":"c3244cc051c5ac87f902184240d644bb1e8c83ca428dcf8dac05f488124fa641"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:55.016594Z","signature_b64":"v2Od+qjr3qinsHbaJNpcUCxJeWnCmorRBO4tf5hVxGKO7HUIHGvEcAltM0J5YKcZFOc/EmFh6TWme9RTlbdaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15524f872494a2c5a8c9be78ad80b83cee94d1b7ade96900a9ab558437837a1d","last_reissued_at":"2026-06-30T01:16:55.015939Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:55.015939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Test-Time Scaling for Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fawaz Sammani, Nikos Deligiannis, Tzoulio Chamiti","submitted_at":"2026-06-27T11:12:42Z","abstract_excerpt":"Test-time scaling is a paradigm where large models use additional compute at inference to achieve better performance, without changing model weights. While it has been widely studied for Large Language Models (LLMs), its applicability to Large Vision-Language Models (LVLMs) remains less explored and analyzed, with limited analysis of whether, when, and to what extent these approaches transfer to LVLMs. In this work, we ask a simple but fundamental question: can conventional test-time scaling methods developed for LLMs be directly applied to LVLMs? We present the first comprehensive study of te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28864","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/2606.28864/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":"2606.28864","created_at":"2026-06-30T01:16:55.016035+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28864v1","created_at":"2026-06-30T01:16:55.016035+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28864","created_at":"2026-06-30T01:16:55.016035+00:00"},{"alias_kind":"pith_short_12","alias_value":"CVJE7BZESSRM","created_at":"2026-06-30T01:16:55.016035+00:00"},{"alias_kind":"pith_short_16","alias_value":"CVJE7BZESSRMLKGJ","created_at":"2026-06-30T01:16:55.016035+00:00"},{"alias_kind":"pith_short_8","alias_value":"CVJE7BZE","created_at":"2026-06-30T01:16:55.016035+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/CVJE7BZESSRMLKGJXZ4K3AFYHT","json":"https://pith.science/pith/CVJE7BZESSRMLKGJXZ4K3AFYHT.json","graph_json":"https://pith.science/api/pith-number/CVJE7BZESSRMLKGJXZ4K3AFYHT/graph.json","events_json":"https://pith.science/api/pith-number/CVJE7BZESSRMLKGJXZ4K3AFYHT/events.json","paper":"https://pith.science/paper/CVJE7BZE"},"agent_actions":{"view_html":"https://pith.science/pith/CVJE7BZESSRMLKGJXZ4K3AFYHT","download_json":"https://pith.science/pith/CVJE7BZESSRMLKGJXZ4K3AFYHT.json","view_paper":"https://pith.science/paper/CVJE7BZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28864&json=true","fetch_graph":"https://pith.science/api/pith-number/CVJE7BZESSRMLKGJXZ4K3AFYHT/graph.json","fetch_events":"https://pith.science/api/pith-number/CVJE7BZESSRMLKGJXZ4K3AFYHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CVJE7BZESSRMLKGJXZ4K3AFYHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CVJE7BZESSRMLKGJXZ4K3AFYHT/action/storage_attestation","attest_author":"https://pith.science/pith/CVJE7BZESSRMLKGJXZ4K3AFYHT/action/author_attestation","sign_citation":"https://pith.science/pith/CVJE7BZESSRMLKGJXZ4K3AFYHT/action/citation_signature","submit_replication":"https://pith.science/pith/CVJE7BZESSRMLKGJXZ4K3AFYHT/action/replication_record"}},"created_at":"2026-06-30T01:16:55.016035+00:00","updated_at":"2026-06-30T01:16:55.016035+00:00"}