{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:REN7Y46SDJHG6X7BRMTBP4M5KX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"31a5f23af1e38cf015af5443fa967b87ddb902b47de41d7cef3cb34cab351014","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T01:06:38Z","title_canon_sha256":"312892f7f53b9f68211a5a5039c57ed0bf639e65f322c12c69997d1817d402d8"},"schema_version":"1.0","source":{"id":"2605.30713","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30713","created_at":"2026-06-01T01:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30713v1","created_at":"2026-06-01T01:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30713","created_at":"2026-06-01T01:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"REN7Y46SDJHG","created_at":"2026-06-01T01:03:11Z"},{"alias_kind":"pith_short_16","alias_value":"REN7Y46SDJHG6X7B","created_at":"2026-06-01T01:03:11Z"},{"alias_kind":"pith_short_8","alias_value":"REN7Y46S","created_at":"2026-06-01T01:03:11Z"}],"graph_snapshots":[{"event_id":"sha256:17bd8d11797faf503a4c864c925de9ddb28f070f94a7661f19717f47411f9be7","target":"graph","created_at":"2026-06-01T01:03:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.30713/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Test-time compute (TTC) strategies have emerged as a lightweight approach to boost reasoning in large language models (LLMs). However, their application and benefits for vision-language models (VLMs) remain underexplored. We present a systematic study of TTC across seven VLMs and six benchmarks, specifically analyzing feature-based scoring and majority voting methods. We find that feature heuristics fail and voting yields only modest gains in single-model settings. We theoretically show that this limitation stems from a lack of prediction diversity: when outputs are highly correlated, voting p","authors_text":"Antoine Bosselut, Mrinmaya Sachan, Shaobo Cui, Yifan Hou, Yijie Tong","cross_cats":["cs.CV","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T01:06:38Z","title":"Diversity Matters: Revisiting Test-Time Compute in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30713","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:980c28d1d3e616185eb5843352f3a7c5c77a2fcae02e1e90d240c3c031e93ca9","target":"record","created_at":"2026-06-01T01:03:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"31a5f23af1e38cf015af5443fa967b87ddb902b47de41d7cef3cb34cab351014","cross_cats_sorted":["cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T01:06:38Z","title_canon_sha256":"312892f7f53b9f68211a5a5039c57ed0bf639e65f322c12c69997d1817d402d8"},"schema_version":"1.0","source":{"id":"2605.30713","kind":"arxiv","version":1}},"canonical_sha256":"891bfc73d21a4e6f5fe18b2617f19d55ddb644469491db3a53ce10c40372ac6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"891bfc73d21a4e6f5fe18b2617f19d55ddb644469491db3a53ce10c40372ac6f","first_computed_at":"2026-06-01T01:03:11.834701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:11.834701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h9BbJPT+wfOgZwCe/Xp2+mxaqsWG9OHWkIkUbNJzuY/F/L7GgZxlLT5t3R6NXDh6k6u4ilcKK/9gOAuYcrqRCw==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:11.835477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30713","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:980c28d1d3e616185eb5843352f3a7c5c77a2fcae02e1e90d240c3c031e93ca9","sha256:17bd8d11797faf503a4c864c925de9ddb28f070f94a7661f19717f47411f9be7"],"state_sha256":"75110f9a1d5af487d1167253ee871de3bd6bab0f28022ea6f1866cd260101e19"}