{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4UXBUXTTQ5WP526Y7XMD374SME","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"23be11e5f02b223e64eec6325b71c0aa6db2f82d692eab5bae6b7d3009d2ead3","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-20T12:22:18Z","title_canon_sha256":"41ade33c1c1c7389306a8c41cc03dac3aca42f4a984ae97b491da584bf0aae98"},"schema_version":"1.0","source":{"id":"2503.16081","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.16081","created_at":"2026-07-05T10:40:41Z"},{"alias_kind":"arxiv_version","alias_value":"2503.16081v2","created_at":"2026-07-05T10:40:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16081","created_at":"2026-07-05T10:40:41Z"},{"alias_kind":"pith_short_12","alias_value":"4UXBUXTTQ5WP","created_at":"2026-07-05T10:40:41Z"},{"alias_kind":"pith_short_16","alias_value":"4UXBUXTTQ5WP526Y","created_at":"2026-07-05T10:40:41Z"},{"alias_kind":"pith_short_8","alias_value":"4UXBUXTT","created_at":"2026-07-05T10:40:41Z"}],"graph_snapshots":[{"event_id":"sha256:331cfe6d7558f8548ee906c034a60c6a12244abee677b8387b1876d6fba78d96","target":"graph","created_at":"2026-07-05T10:40:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.16081/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Changwang Zhang, Feng Liu, Jun Wang, Ying Sun, Yuting Zhang, Zhiyuan Liu","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-20T12:22:18Z","title":"OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16081","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:316625ef15f809b9d1d8373f767e9f487d3f1a55dfdbceaccf21769cc97480e8","target":"record","created_at":"2026-07-05T10:40:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"23be11e5f02b223e64eec6325b71c0aa6db2f82d692eab5bae6b7d3009d2ead3","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-20T12:22:18Z","title_canon_sha256":"41ade33c1c1c7389306a8c41cc03dac3aca42f4a984ae97b491da584bf0aae98"},"schema_version":"1.0","source":{"id":"2503.16081","kind":"arxiv","version":2}},"canonical_sha256":"e52e1a5e73876cfeebd8fdd83dff9261303f673b33bd9507ad27003e5a9be2a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e52e1a5e73876cfeebd8fdd83dff9261303f673b33bd9507ad27003e5a9be2a6","first_computed_at":"2026-07-05T10:40:41.075139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:41.075139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RwlwI6RiqVUCt+JjX1nE4z+OxtfdYyHVw0u6SJ7Ec8Jh7BhFUe1Tdc7+DVy9klIWuBDQcwM5+gvHO3niLVmSAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:41.075626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.16081","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:316625ef15f809b9d1d8373f767e9f487d3f1a55dfdbceaccf21769cc97480e8","sha256:331cfe6d7558f8548ee906c034a60c6a12244abee677b8387b1876d6fba78d96"],"state_sha256":"3555f0994f9d5ec9d2dea9267e71d3b6d5c90b64e542cb02c1233521c740ac7e"}