{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AXYVZRIVWGCUJBZYI4C4PTRL3V","short_pith_number":"pith:AXYVZRIV","schema_version":"1.0","canonical_sha256":"05f15cc515b1854487384705c7ce2bdd7a015be5780fc33f605a34a3e2855637","source":{"kind":"arxiv","id":"2504.11009","version":1},"attestation_state":"computed","paper":{"title":"MMC: Iterative Refinement of VLM Reasoning via MCTS-based Multimodal Critique","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Feng Ma, Jianqing Gao, Jianshu Zhang, Jiefeng Ma, Jun Du, Pengfei Hu, Qing Wang, Quan Liu, Shuhang Liu, Zhenrong Zhang","submitted_at":"2025-04-15T09:29:08Z","abstract_excerpt":"Visual language models (VLMs) have demonstrated strong performance across diverse multimodal reasoning tasks but still face challenges such as hallucinations, resulting in incorrect reasoning outcomes. Inspired by recent research on external feedback mechanisms in large language models (LLMs), we propose a multimodal actor-critic framework to enhance VLM reasoning capabilities. Specifically, the actor model generates step-by-step reasoning paths based on image and text inputs, while the critic model evaluates these reasoning paths and provides corrective feedback. The actor model iteratively r"},"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":"2504.11009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-04-15T09:29:08Z","cross_cats_sorted":[],"title_canon_sha256":"a51f0abe7e9121d203594cc407ac9fc073bfccc62c52b84b3c501d9226c8de76","abstract_canon_sha256":"b63e328807daf069992e906e3924b0ff1157c1b43e9cb0b886851c30bfc4fa8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:27.823335Z","signature_b64":"tE4FzYOvPYPzMObOwZaHrpa4KEMJxCchGPkgIycIu42fm1dGG8ELJcWXXOY96zvQTUkMwJdMitRG8hFxdgWnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05f15cc515b1854487384705c7ce2bdd7a015be5780fc33f605a34a3e2855637","last_reissued_at":"2026-07-05T10:49:27.822858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:27.822858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMC: Iterative Refinement of VLM Reasoning via MCTS-based Multimodal Critique","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Feng Ma, Jianqing Gao, Jianshu Zhang, Jiefeng Ma, Jun Du, Pengfei Hu, Qing Wang, Quan Liu, Shuhang Liu, Zhenrong Zhang","submitted_at":"2025-04-15T09:29:08Z","abstract_excerpt":"Visual language models (VLMs) have demonstrated strong performance across diverse multimodal reasoning tasks but still face challenges such as hallucinations, resulting in incorrect reasoning outcomes. Inspired by recent research on external feedback mechanisms in large language models (LLMs), we propose a multimodal actor-critic framework to enhance VLM reasoning capabilities. Specifically, the actor model generates step-by-step reasoning paths based on image and text inputs, while the critic model evaluates these reasoning paths and provides corrective feedback. The actor model iteratively r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11009","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/2504.11009/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":"2504.11009","created_at":"2026-07-05T10:49:27.822916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.11009v1","created_at":"2026-07-05T10:49:27.822916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11009","created_at":"2026-07-05T10:49:27.822916+00:00"},{"alias_kind":"pith_short_12","alias_value":"AXYVZRIVWGCU","created_at":"2026-07-05T10:49:27.822916+00:00"},{"alias_kind":"pith_short_16","alias_value":"AXYVZRIVWGCUJBZY","created_at":"2026-07-05T10:49:27.822916+00:00"},{"alias_kind":"pith_short_8","alias_value":"AXYVZRIV","created_at":"2026-07-05T10:49:27.822916+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/AXYVZRIVWGCUJBZYI4C4PTRL3V","json":"https://pith.science/pith/AXYVZRIVWGCUJBZYI4C4PTRL3V.json","graph_json":"https://pith.science/api/pith-number/AXYVZRIVWGCUJBZYI4C4PTRL3V/graph.json","events_json":"https://pith.science/api/pith-number/AXYVZRIVWGCUJBZYI4C4PTRL3V/events.json","paper":"https://pith.science/paper/AXYVZRIV"},"agent_actions":{"view_html":"https://pith.science/pith/AXYVZRIVWGCUJBZYI4C4PTRL3V","download_json":"https://pith.science/pith/AXYVZRIVWGCUJBZYI4C4PTRL3V.json","view_paper":"https://pith.science/paper/AXYVZRIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.11009&json=true","fetch_graph":"https://pith.science/api/pith-number/AXYVZRIVWGCUJBZYI4C4PTRL3V/graph.json","fetch_events":"https://pith.science/api/pith-number/AXYVZRIVWGCUJBZYI4C4PTRL3V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AXYVZRIVWGCUJBZYI4C4PTRL3V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AXYVZRIVWGCUJBZYI4C4PTRL3V/action/storage_attestation","attest_author":"https://pith.science/pith/AXYVZRIVWGCUJBZYI4C4PTRL3V/action/author_attestation","sign_citation":"https://pith.science/pith/AXYVZRIVWGCUJBZYI4C4PTRL3V/action/citation_signature","submit_replication":"https://pith.science/pith/AXYVZRIVWGCUJBZYI4C4PTRL3V/action/replication_record"}},"created_at":"2026-07-05T10:49:27.822916+00:00","updated_at":"2026-07-05T10:49:27.822916+00:00"}