{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FWOGLRAUWPMZOLGUCPM4XHDQCI","short_pith_number":"pith:FWOGLRAU","schema_version":"1.0","canonical_sha256":"2d9c65c414b3d9972cd413d9cb9c70121922438b38673e9528ef574cc52eee77","source":{"kind":"arxiv","id":"2502.11514","version":2},"attestation_state":"computed","paper":{"title":"Investigating Inference-time Scaling for Chain of Multi-modal Thought: A Preliminary Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ante Wang, Hao Liu, Jingyao Liu, Jinsong Su, Moye Chen, Xinyan Xiao, Yujie Lin","submitted_at":"2025-02-17T07:29:01Z","abstract_excerpt":"Recently, inference-time scaling of chain-of-thought (CoT) has been demonstrated as a promising approach for addressing multi-modal reasoning tasks. While existing studies have predominantly centered on text-based thinking, the integration of both visual and textual modalities within the reasoning process remains unexplored. In this study, we pioneer the exploration of inference-time scaling with multi-modal thought, aiming to bridge this gap. To provide a comprehensive analysis, we systematically investigate popular sampling-based and tree search-based inference-time scaling methods on 10 cha"},"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":"2502.11514","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T07:29:01Z","cross_cats_sorted":[],"title_canon_sha256":"73f004c808e115e4c398bb02e353a9d00f50565158658fc1d4211493f4387172","abstract_canon_sha256":"edbe59412ea88437dd6aa111da5c63f1e8f7089bd83d372023c36c6e36790c5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:08.544711Z","signature_b64":"MyXHuIbNJDxEGqFa45Y3M7V+oOGzoITfViptiQG5al57YPUb53+mLB5/yC/+NdHU666TEMNqGQeBuUcnPnBNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d9c65c414b3d9972cd413d9cb9c70121922438b38673e9528ef574cc52eee77","last_reissued_at":"2026-07-05T11:09:08.544247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:08.544247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigating Inference-time Scaling for Chain of Multi-modal Thought: A Preliminary Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ante Wang, Hao Liu, Jingyao Liu, Jinsong Su, Moye Chen, Xinyan Xiao, Yujie Lin","submitted_at":"2025-02-17T07:29:01Z","abstract_excerpt":"Recently, inference-time scaling of chain-of-thought (CoT) has been demonstrated as a promising approach for addressing multi-modal reasoning tasks. While existing studies have predominantly centered on text-based thinking, the integration of both visual and textual modalities within the reasoning process remains unexplored. In this study, we pioneer the exploration of inference-time scaling with multi-modal thought, aiming to bridge this gap. To provide a comprehensive analysis, we systematically investigate popular sampling-based and tree search-based inference-time scaling methods on 10 cha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11514","kind":"arxiv","version":2},"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/2502.11514/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":"2502.11514","created_at":"2026-07-05T11:09:08.544304+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11514v2","created_at":"2026-07-05T11:09:08.544304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11514","created_at":"2026-07-05T11:09:08.544304+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWOGLRAUWPMZ","created_at":"2026-07-05T11:09:08.544304+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWOGLRAUWPMZOLGU","created_at":"2026-07-05T11:09:08.544304+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWOGLRAU","created_at":"2026-07-05T11:09:08.544304+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14805","citing_title":"Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes?","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FWOGLRAUWPMZOLGUCPM4XHDQCI","json":"https://pith.science/pith/FWOGLRAUWPMZOLGUCPM4XHDQCI.json","graph_json":"https://pith.science/api/pith-number/FWOGLRAUWPMZOLGUCPM4XHDQCI/graph.json","events_json":"https://pith.science/api/pith-number/FWOGLRAUWPMZOLGUCPM4XHDQCI/events.json","paper":"https://pith.science/paper/FWOGLRAU"},"agent_actions":{"view_html":"https://pith.science/pith/FWOGLRAUWPMZOLGUCPM4XHDQCI","download_json":"https://pith.science/pith/FWOGLRAUWPMZOLGUCPM4XHDQCI.json","view_paper":"https://pith.science/paper/FWOGLRAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11514&json=true","fetch_graph":"https://pith.science/api/pith-number/FWOGLRAUWPMZOLGUCPM4XHDQCI/graph.json","fetch_events":"https://pith.science/api/pith-number/FWOGLRAUWPMZOLGUCPM4XHDQCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWOGLRAUWPMZOLGUCPM4XHDQCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWOGLRAUWPMZOLGUCPM4XHDQCI/action/storage_attestation","attest_author":"https://pith.science/pith/FWOGLRAUWPMZOLGUCPM4XHDQCI/action/author_attestation","sign_citation":"https://pith.science/pith/FWOGLRAUWPMZOLGUCPM4XHDQCI/action/citation_signature","submit_replication":"https://pith.science/pith/FWOGLRAUWPMZOLGUCPM4XHDQCI/action/replication_record"}},"created_at":"2026-07-05T11:09:08.544304+00:00","updated_at":"2026-07-05T11:09:08.544304+00:00"}