{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4UXBUXTTQ5WP526Y7XMD374SME","short_pith_number":"pith:4UXBUXTT","schema_version":"1.0","canonical_sha256":"e52e1a5e73876cfeebd8fdd83dff9261303f673b33bd9507ad27003e5a9be2a6","source":{"kind":"arxiv","id":"2503.16081","version":2},"attestation_state":"computed","paper":{"title":"OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Changwang Zhang, Feng Liu, Jun Wang, Ying Sun, Yuting Zhang, Zhiyuan Liu","submitted_at":"2025-03-20T12:22:18Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have gained significant traction for their ability to process diverse input data types and generate coherent, contextually relevant outputs across various applications. While supervised fine-tuning (SFT) has been the predominant approach to enhance MLLM capabilities in task-specific optimization, it often falls short in fostering crucial generalized reasoning abilities. Although reinforcement learning (RL) holds great promise in overcoming these limitations, it encounters two significant challenges: (1) its generalized capacities in multimodal tasks rem"},"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":"2503.16081","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-20T12:22:18Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"41ade33c1c1c7389306a8c41cc03dac3aca42f4a984ae97b491da584bf0aae98","abstract_canon_sha256":"23be11e5f02b223e64eec6325b71c0aa6db2f82d692eab5bae6b7d3009d2ead3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:41.075626Z","signature_b64":"RwlwI6RiqVUCt+JjX1nE4z+OxtfdYyHVw0u6SJ7Ec8Jh7BhFUe1Tdc7+DVy9klIWuBDQcwM5+gvHO3niLVmSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e52e1a5e73876cfeebd8fdd83dff9261303f673b33bd9507ad27003e5a9be2a6","last_reissued_at":"2026-07-05T10:40:41.075139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:41.075139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Changwang Zhang, Feng Liu, Jun Wang, Ying Sun, Yuting Zhang, Zhiyuan Liu","submitted_at":"2025-03-20T12:22:18Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have gained significant traction for their ability to process diverse input data types and generate coherent, contextually relevant outputs across various applications. While supervised fine-tuning (SFT) has been the predominant approach to enhance MLLM capabilities in task-specific optimization, it often falls short in fostering crucial generalized reasoning abilities. Although reinforcement learning (RL) holds great promise in overcoming these limitations, it encounters two significant challenges: (1) its generalized capacities in multimodal tasks rem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16081","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/2503.16081/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":"2503.16081","created_at":"2026-07-05T10:40:41.075198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16081v2","created_at":"2026-07-05T10:40:41.075198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16081","created_at":"2026-07-05T10:40:41.075198+00:00"},{"alias_kind":"pith_short_12","alias_value":"4UXBUXTTQ5WP","created_at":"2026-07-05T10:40:41.075198+00:00"},{"alias_kind":"pith_short_16","alias_value":"4UXBUXTTQ5WP526Y","created_at":"2026-07-05T10:40:41.075198+00:00"},{"alias_kind":"pith_short_8","alias_value":"4UXBUXTT","created_at":"2026-07-05T10:40:41.075198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":158,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4UXBUXTTQ5WP526Y7XMD374SME","json":"https://pith.science/pith/4UXBUXTTQ5WP526Y7XMD374SME.json","graph_json":"https://pith.science/api/pith-number/4UXBUXTTQ5WP526Y7XMD374SME/graph.json","events_json":"https://pith.science/api/pith-number/4UXBUXTTQ5WP526Y7XMD374SME/events.json","paper":"https://pith.science/paper/4UXBUXTT"},"agent_actions":{"view_html":"https://pith.science/pith/4UXBUXTTQ5WP526Y7XMD374SME","download_json":"https://pith.science/pith/4UXBUXTTQ5WP526Y7XMD374SME.json","view_paper":"https://pith.science/paper/4UXBUXTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16081&json=true","fetch_graph":"https://pith.science/api/pith-number/4UXBUXTTQ5WP526Y7XMD374SME/graph.json","fetch_events":"https://pith.science/api/pith-number/4UXBUXTTQ5WP526Y7XMD374SME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4UXBUXTTQ5WP526Y7XMD374SME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4UXBUXTTQ5WP526Y7XMD374SME/action/storage_attestation","attest_author":"https://pith.science/pith/4UXBUXTTQ5WP526Y7XMD374SME/action/author_attestation","sign_citation":"https://pith.science/pith/4UXBUXTTQ5WP526Y7XMD374SME/action/citation_signature","submit_replication":"https://pith.science/pith/4UXBUXTTQ5WP526Y7XMD374SME/action/replication_record"}},"created_at":"2026-07-05T10:40:41.075198+00:00","updated_at":"2026-07-05T10:40:41.075198+00:00"}