{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RPQUIKIEHEI7WHECRKATLUW7SF","short_pith_number":"pith:RPQUIKIE","schema_version":"1.0","canonical_sha256":"8be14429043911fb1c828a8135d2df916b13236019a42cf6fa6753b4b88a6b80","source":{"kind":"arxiv","id":"2405.16473","version":1},"attestation_state":"computed","paper":{"title":"M$^3$CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jin Zhang, Libo Qin, Qiguang Chen, Wanxiang Che, Xiao Xu, Zhi Chen","submitted_at":"2024-05-26T07:56:30Z","abstract_excerpt":"Multi-modal Chain-of-Thought (MCoT) requires models to leverage knowledge from both textual and visual modalities for step-by-step reasoning, which gains increasing attention. Nevertheless, the current MCoT benchmark still faces some challenges: (1) absence of visual modal reasoning, (2) single-step visual modal reasoning, and (3) Domain missing, thereby hindering the development of MCoT. Motivated by this, we introduce a novel benchmark (M$^3$CoT) to address the above challenges, advancing the multi-domain, multi-step, and multi-modal CoT. Additionally, we conduct a thorough evaluation involv"},"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":"2405.16473","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-26T07:56:30Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"629c3c75dee5e0d62d940f5d1c5af0bd9432ec1d9e29bfba782339f3e1a22753","abstract_canon_sha256":"82ce34464d506ccbaf2de3f97b31d226d3870eed57ded07a5716cc36e59f1946"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:30.974698Z","signature_b64":"ePMr3N48M1evDj6AbOFlTHScG4OkJwXL1hzoddIpO7pdg+NwZccQv92uATrvEpz6mZCz9/zmJCGNf22s1pICDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8be14429043911fb1c828a8135d2df916b13236019a42cf6fa6753b4b88a6b80","last_reissued_at":"2026-07-05T08:23:30.974244Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:30.974244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M$^3$CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jin Zhang, Libo Qin, Qiguang Chen, Wanxiang Che, Xiao Xu, Zhi Chen","submitted_at":"2024-05-26T07:56:30Z","abstract_excerpt":"Multi-modal Chain-of-Thought (MCoT) requires models to leverage knowledge from both textual and visual modalities for step-by-step reasoning, which gains increasing attention. Nevertheless, the current MCoT benchmark still faces some challenges: (1) absence of visual modal reasoning, (2) single-step visual modal reasoning, and (3) Domain missing, thereby hindering the development of MCoT. Motivated by this, we introduce a novel benchmark (M$^3$CoT) to address the above challenges, advancing the multi-domain, multi-step, and multi-modal CoT. Additionally, we conduct a thorough evaluation involv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16473","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/2405.16473/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":"2405.16473","created_at":"2026-07-05T08:23:30.974295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16473v1","created_at":"2026-07-05T08:23:30.974295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16473","created_at":"2026-07-05T08:23:30.974295+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPQUIKIEHEI7","created_at":"2026-07-05T08:23:30.974295+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPQUIKIEHEI7WHEC","created_at":"2026-07-05T08:23:30.974295+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPQUIKIE","created_at":"2026-07-05T08:23:30.974295+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.25699","citing_title":"AIM-CoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language Reasoning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2411.10442","citing_title":"Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2508.05748","citing_title":"WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05497","citing_title":"Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2504.10479","citing_title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14646","citing_title":"Targeted Exploration via Unified Entropy Control for Reinforcement Learning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15705","citing_title":"Towards Robust Endogenous Reasoning: Unifying Drift Adaptation in Non-Stationary Tuning","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPQUIKIEHEI7WHECRKATLUW7SF","json":"https://pith.science/pith/RPQUIKIEHEI7WHECRKATLUW7SF.json","graph_json":"https://pith.science/api/pith-number/RPQUIKIEHEI7WHECRKATLUW7SF/graph.json","events_json":"https://pith.science/api/pith-number/RPQUIKIEHEI7WHECRKATLUW7SF/events.json","paper":"https://pith.science/paper/RPQUIKIE"},"agent_actions":{"view_html":"https://pith.science/pith/RPQUIKIEHEI7WHECRKATLUW7SF","download_json":"https://pith.science/pith/RPQUIKIEHEI7WHECRKATLUW7SF.json","view_paper":"https://pith.science/paper/RPQUIKIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16473&json=true","fetch_graph":"https://pith.science/api/pith-number/RPQUIKIEHEI7WHECRKATLUW7SF/graph.json","fetch_events":"https://pith.science/api/pith-number/RPQUIKIEHEI7WHECRKATLUW7SF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPQUIKIEHEI7WHECRKATLUW7SF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPQUIKIEHEI7WHECRKATLUW7SF/action/storage_attestation","attest_author":"https://pith.science/pith/RPQUIKIEHEI7WHECRKATLUW7SF/action/author_attestation","sign_citation":"https://pith.science/pith/RPQUIKIEHEI7WHECRKATLUW7SF/action/citation_signature","submit_replication":"https://pith.science/pith/RPQUIKIEHEI7WHECRKATLUW7SF/action/replication_record"}},"created_at":"2026-07-05T08:23:30.974295+00:00","updated_at":"2026-07-05T08:23:30.974295+00:00"}