{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:F5GMLN42OAAW6ZLVWLCFZDLBMU","short_pith_number":"pith:F5GMLN42","canonical_record":{"source":{"id":"2504.21277","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-30T03:14:28Z","cross_cats_sorted":[],"title_canon_sha256":"1195d9b47d92859b8be5b965a478e076f01123c836a052a18d884d38822964c5","abstract_canon_sha256":"4575f098458dba8306ad39506e15d0296667e8f8dd5c2078ac1f8887301a7526"},"schema_version":"1.0"},"canonical_sha256":"2f4cc5b79a70016f6575b2c45c8d61651f50351f1d4c3243d31837c4363a0977","source":{"kind":"arxiv","id":"2504.21277","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21277","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21277v2","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21277","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"F5GMLN42OAAW","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"F5GMLN42OAAW6ZLV","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"F5GMLN42","created_at":"2026-07-05T11:06:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:F5GMLN42OAAW6ZLVWLCFZDLBMU","target":"record","payload":{"canonical_record":{"source":{"id":"2504.21277","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-30T03:14:28Z","cross_cats_sorted":[],"title_canon_sha256":"1195d9b47d92859b8be5b965a478e076f01123c836a052a18d884d38822964c5","abstract_canon_sha256":"4575f098458dba8306ad39506e15d0296667e8f8dd5c2078ac1f8887301a7526"},"schema_version":"1.0"},"canonical_sha256":"2f4cc5b79a70016f6575b2c45c8d61651f50351f1d4c3243d31837c4363a0977","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:31.219206Z","signature_b64":"JZz+g6JJ0vrXggWUHX/OXjZ1VPo/PpdR43XkuBc/rixF1EhuThYGORWBjSvzqwrqTEbngwj2YxIy9/ZLjT3HDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f4cc5b79a70016f6575b2c45c8d61651f50351f1d4c3243d31837c4363a0977","last_reissued_at":"2026-07-05T11:06:31.218704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:31.218704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.21277","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:06:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zrqf5IF84yFsxw2mzpN4pxiO4rIcYhSI99y9rBEZzD3A86V0rDqSNlABr3t567lpd38T9QzmoUIXG7zE+jPVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T12:26:49.454454Z"},"content_sha256":"17d30857f63fd5e34d0c2bdd583c918a72679068933f63e9b6859dfc0744cb14","schema_version":"1.0","event_id":"sha256:17d30857f63fd5e34d0c2bdd583c918a72679068933f63e9b6859dfc0744cb14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:F5GMLN42OAAW6ZLVWLCFZDLBMU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cen Chen, Guanghao Zhou, Jian Xu, Jie Wang, Minghui Qiu, Panjia Qiu, Zheming Yang","submitted_at":"2025-04-30T03:14:28Z","abstract_excerpt":"The application of reinforcement learning (RL) to enhance the reasoning capabilities of Multimodal Large Language Models (MLLMs) constitutes a rapidly advancing research area. While MLLMs extend Large Language Models (LLMs) to handle diverse modalities such as vision, audio, and video, enabling robust reasoning across multimodal inputs remains challenging. This paper provides a systematic review of recent advances in RL-based reasoning for MLLMs, covering key algorithmic designs, reward mechanism innovations, and practical applications. We highlight two main RL paradigms, value-model-free and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21277","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/2504.21277/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:06:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jVbFTIavIbjhHEfTXsk2RfUQzcyVjQGPzvKB2I5JJsErQM1DmXj6L2Qkgf0It78QYtcO2QUmGn5enzqRVLmYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T12:26:49.454951Z"},"content_sha256":"b9b90b9d622d9cf9647c8429d409bb0d683839e47a04f35a6bd242785d04f540","schema_version":"1.0","event_id":"sha256:b9b90b9d622d9cf9647c8429d409bb0d683839e47a04f35a6bd242785d04f540"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5GMLN42OAAW6ZLVWLCFZDLBMU/bundle.json","state_url":"https://pith.science/pith/F5GMLN42OAAW6ZLVWLCFZDLBMU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5GMLN42OAAW6ZLVWLCFZDLBMU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-01T12:26:49Z","links":{"resolver":"https://pith.science/pith/F5GMLN42OAAW6ZLVWLCFZDLBMU","bundle":"https://pith.science/pith/F5GMLN42OAAW6ZLVWLCFZDLBMU/bundle.json","state":"https://pith.science/pith/F5GMLN42OAAW6ZLVWLCFZDLBMU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5GMLN42OAAW6ZLVWLCFZDLBMU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F5GMLN42OAAW6ZLVWLCFZDLBMU","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":"4575f098458dba8306ad39506e15d0296667e8f8dd5c2078ac1f8887301a7526","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-30T03:14:28Z","title_canon_sha256":"1195d9b47d92859b8be5b965a478e076f01123c836a052a18d884d38822964c5"},"schema_version":"1.0","source":{"id":"2504.21277","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21277","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21277v2","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21277","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"F5GMLN42OAAW","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"F5GMLN42OAAW6ZLV","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"F5GMLN42","created_at":"2026-07-05T11:06:31Z"}],"graph_snapshots":[{"event_id":"sha256:b9b90b9d622d9cf9647c8429d409bb0d683839e47a04f35a6bd242785d04f540","target":"graph","created_at":"2026-07-05T11:06:31Z","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/2504.21277/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The application of reinforcement learning (RL) to enhance the reasoning capabilities of Multimodal Large Language Models (MLLMs) constitutes a rapidly advancing research area. While MLLMs extend Large Language Models (LLMs) to handle diverse modalities such as vision, audio, and video, enabling robust reasoning across multimodal inputs remains challenging. This paper provides a systematic review of recent advances in RL-based reasoning for MLLMs, covering key algorithmic designs, reward mechanism innovations, and practical applications. We highlight two main RL paradigms, value-model-free and ","authors_text":"Cen Chen, Guanghao Zhou, Jian Xu, Jie Wang, Minghui Qiu, Panjia Qiu, Zheming Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-30T03:14:28Z","title":"Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21277","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":"sha256:17d30857f63fd5e34d0c2bdd583c918a72679068933f63e9b6859dfc0744cb14","target":"record","created_at":"2026-07-05T11:06:31Z","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":"4575f098458dba8306ad39506e15d0296667e8f8dd5c2078ac1f8887301a7526","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-30T03:14:28Z","title_canon_sha256":"1195d9b47d92859b8be5b965a478e076f01123c836a052a18d884d38822964c5"},"schema_version":"1.0","source":{"id":"2504.21277","kind":"arxiv","version":2}},"canonical_sha256":"2f4cc5b79a70016f6575b2c45c8d61651f50351f1d4c3243d31837c4363a0977","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f4cc5b79a70016f6575b2c45c8d61651f50351f1d4c3243d31837c4363a0977","first_computed_at":"2026-07-05T11:06:31.218704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:31.218704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JZz+g6JJ0vrXggWUHX/OXjZ1VPo/PpdR43XkuBc/rixF1EhuThYGORWBjSvzqwrqTEbngwj2YxIy9/ZLjT3HDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:31.219206Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.21277","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17d30857f63fd5e34d0c2bdd583c918a72679068933f63e9b6859dfc0744cb14","sha256:b9b90b9d622d9cf9647c8429d409bb0d683839e47a04f35a6bd242785d04f540"],"state_sha256":"700005400e5980d4dfc7f21107b05ab066de994d735bcdc9e3409da6f2d09cae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FKIc2n5hPFVwG+QkzEOD1BmOQsaM3LpX4c9Y/GfZmYKctXPMH+32INbGtw39Vvm7f/uAkUz6GspdTu9/5j2lDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T12:26:49.458858Z","bundle_sha256":"67b1ac90c41b5c018e39af7875f69e992df09f13c4d5e013f9d2bece2a62951b"}}