{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BHTDX4E6WD32YPPWTRA7HH7ITX","short_pith_number":"pith:BHTDX4E6","schema_version":"1.0","canonical_sha256":"09e63bf09eb0f7ac3df69c41f39fe89df4fc53ff64b7b62e55aa8b8488e5ff3c","source":{"kind":"arxiv","id":"2506.08927","version":1},"attestation_state":"computed","paper":{"title":"Socratic-MCTS: Test-Time Visual Reasoning by Asking the Right Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Amlan Kar, David Acuna, Hyunwoo Kim, Jaehun Jung, Sanja Fidler, Ximing Lu, Yejin Choi","submitted_at":"2025-06-10T15:51:16Z","abstract_excerpt":"Recent research in vision-language models (VLMs) has centered around the possibility of equipping them with implicit long-form chain-of-thought reasoning -- akin to the success observed in language models -- via distillation and reinforcement learning. But what about the non-reasoning models already trained and deployed across the internet? Should we simply abandon them, or is there hope for a search mechanism that can elicit hidden knowledge and induce long reasoning traces -- without any additional training or supervision? In this paper, we explore this possibility using a Monte Carlo Tree S"},"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":"2506.08927","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T15:51:16Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"64cdb2a4dd5a135f419d298e152dc8fd22493f095f0fd44c94baeb70e5bad1f4","abstract_canon_sha256":"17f35cc8887dcaae0fe7c903295a285e03c2c2de6675ae673e938bd5d3eec823"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:15.163619Z","signature_b64":"o3ubyDXSHtM/iYNYDfXhQ2Sf8RGcjdGAgEOFOEUQbouWgEE1Hk4BM+gsMmvZfDrmn6bbFx9MtaZGLnqGl+jlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09e63bf09eb0f7ac3df69c41f39fe89df4fc53ff64b7b62e55aa8b8488e5ff3c","last_reissued_at":"2026-07-05T11:19:15.163106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:15.163106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Socratic-MCTS: Test-Time Visual Reasoning by Asking the Right Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Amlan Kar, David Acuna, Hyunwoo Kim, Jaehun Jung, Sanja Fidler, Ximing Lu, Yejin Choi","submitted_at":"2025-06-10T15:51:16Z","abstract_excerpt":"Recent research in vision-language models (VLMs) has centered around the possibility of equipping them with implicit long-form chain-of-thought reasoning -- akin to the success observed in language models -- via distillation and reinforcement learning. But what about the non-reasoning models already trained and deployed across the internet? Should we simply abandon them, or is there hope for a search mechanism that can elicit hidden knowledge and induce long reasoning traces -- without any additional training or supervision? In this paper, we explore this possibility using a Monte Carlo Tree S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08927","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/2506.08927/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":"2506.08927","created_at":"2026-07-05T11:19:15.163169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08927v1","created_at":"2026-07-05T11:19:15.163169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08927","created_at":"2026-07-05T11:19:15.163169+00:00"},{"alias_kind":"pith_short_12","alias_value":"BHTDX4E6WD32","created_at":"2026-07-05T11:19:15.163169+00:00"},{"alias_kind":"pith_short_16","alias_value":"BHTDX4E6WD32YPPW","created_at":"2026-07-05T11:19:15.163169+00:00"},{"alias_kind":"pith_short_8","alias_value":"BHTDX4E6","created_at":"2026-07-05T11:19:15.163169+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/BHTDX4E6WD32YPPWTRA7HH7ITX","json":"https://pith.science/pith/BHTDX4E6WD32YPPWTRA7HH7ITX.json","graph_json":"https://pith.science/api/pith-number/BHTDX4E6WD32YPPWTRA7HH7ITX/graph.json","events_json":"https://pith.science/api/pith-number/BHTDX4E6WD32YPPWTRA7HH7ITX/events.json","paper":"https://pith.science/paper/BHTDX4E6"},"agent_actions":{"view_html":"https://pith.science/pith/BHTDX4E6WD32YPPWTRA7HH7ITX","download_json":"https://pith.science/pith/BHTDX4E6WD32YPPWTRA7HH7ITX.json","view_paper":"https://pith.science/paper/BHTDX4E6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08927&json=true","fetch_graph":"https://pith.science/api/pith-number/BHTDX4E6WD32YPPWTRA7HH7ITX/graph.json","fetch_events":"https://pith.science/api/pith-number/BHTDX4E6WD32YPPWTRA7HH7ITX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BHTDX4E6WD32YPPWTRA7HH7ITX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BHTDX4E6WD32YPPWTRA7HH7ITX/action/storage_attestation","attest_author":"https://pith.science/pith/BHTDX4E6WD32YPPWTRA7HH7ITX/action/author_attestation","sign_citation":"https://pith.science/pith/BHTDX4E6WD32YPPWTRA7HH7ITX/action/citation_signature","submit_replication":"https://pith.science/pith/BHTDX4E6WD32YPPWTRA7HH7ITX/action/replication_record"}},"created_at":"2026-07-05T11:19:15.163169+00:00","updated_at":"2026-07-05T11:19:15.163169+00:00"}