{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZUB5MBFDPU6PO2LBEVQAPTN6IZ","short_pith_number":"pith:ZUB5MBFD","schema_version":"1.0","canonical_sha256":"cd03d604a37d3cf76961256007cdbe466445cb13559d1b48b242b016468bc381","source":{"kind":"arxiv","id":"2506.16141","version":1},"attestation_state":"computed","paper":{"title":"GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Junhao Cheng, Rui Wang, Xihui Liu, Yi Chen, Ying Shan, Yixiao Ge, Yuying Ge","submitted_at":"2025-06-19T08:49:13Z","abstract_excerpt":"Recent reinforcement learning approaches, such as outcome-supervised GRPO, have advanced Chain-of-Thought reasoning in large language models (LLMs), yet their adaptation to multimodal LLMs (MLLMs) is unexplored. To address the lack of rigorous evaluation for MLLM post-training methods, we introduce SEED-Bench-R1, a benchmark with complex real-world videos requiring balanced perception and reasoning. It offers a large training set and evaluates generalization across three escalating challenges: in-distribution, cross-environment, and cross-environment-task scenarios. Using SEED-Bench-R1, we fin"},"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":"2506.16141","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-19T08:49:13Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"28bf2299871481a0ff95dbfd1bfc7d220c22496167e1d08cd2f1234cf4c503a2","abstract_canon_sha256":"b18b42bb2c7a0fc956d76164ba64265c4b8d8d1f5417f052ee3e964acfc0d217"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:31.228194Z","signature_b64":"YsTU4Bpz4dRAqdLy0v5uK8yOVdG2+gxkdQ1qH6BCKTqmPDixglD9hblO/lMfd+ChCYciEruRLwASxpJ9mbjSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd03d604a37d3cf76961256007cdbe466445cb13559d1b48b242b016468bc381","last_reissued_at":"2026-07-05T11:24:31.227364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:31.227364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Junhao Cheng, Rui Wang, Xihui Liu, Yi Chen, Ying Shan, Yixiao Ge, Yuying Ge","submitted_at":"2025-06-19T08:49:13Z","abstract_excerpt":"Recent reinforcement learning approaches, such as outcome-supervised GRPO, have advanced Chain-of-Thought reasoning in large language models (LLMs), yet their adaptation to multimodal LLMs (MLLMs) is unexplored. To address the lack of rigorous evaluation for MLLM post-training methods, we introduce SEED-Bench-R1, a benchmark with complex real-world videos requiring balanced perception and reasoning. It offers a large training set and evaluates generalization across three escalating challenges: in-distribution, cross-environment, and cross-environment-task scenarios. Using SEED-Bench-R1, we fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16141","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/2506.16141/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":"2506.16141","created_at":"2026-07-05T11:24:31.227444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16141v1","created_at":"2026-07-05T11:24:31.227444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16141","created_at":"2026-07-05T11:24:31.227444+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUB5MBFDPU6P","created_at":"2026-07-05T11:24:31.227444+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUB5MBFDPU6PO2LB","created_at":"2026-07-05T11:24:31.227444+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUB5MBFD","created_at":"2026-07-05T11:24:31.227444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18988","citing_title":"ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02564","citing_title":"VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30217","citing_title":"Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02564","citing_title":"VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27154","citing_title":"Touch-R1: Reinforcing Touch Reasoning in MLLMs","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26680","citing_title":"DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21801","citing_title":"Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13641","citing_title":"Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03485","citing_title":"MHPR: Multidimensional Human Perception and Reasoning Benchmark for Large Vision-Languate Models","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZUB5MBFDPU6PO2LBEVQAPTN6IZ","json":"https://pith.science/pith/ZUB5MBFDPU6PO2LBEVQAPTN6IZ.json","graph_json":"https://pith.science/api/pith-number/ZUB5MBFDPU6PO2LBEVQAPTN6IZ/graph.json","events_json":"https://pith.science/api/pith-number/ZUB5MBFDPU6PO2LBEVQAPTN6IZ/events.json","paper":"https://pith.science/paper/ZUB5MBFD"},"agent_actions":{"view_html":"https://pith.science/pith/ZUB5MBFDPU6PO2LBEVQAPTN6IZ","download_json":"https://pith.science/pith/ZUB5MBFDPU6PO2LBEVQAPTN6IZ.json","view_paper":"https://pith.science/paper/ZUB5MBFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16141&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUB5MBFDPU6PO2LBEVQAPTN6IZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUB5MBFDPU6PO2LBEVQAPTN6IZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUB5MBFDPU6PO2LBEVQAPTN6IZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUB5MBFDPU6PO2LBEVQAPTN6IZ/action/storage_attestation","attest_author":"https://pith.science/pith/ZUB5MBFDPU6PO2LBEVQAPTN6IZ/action/author_attestation","sign_citation":"https://pith.science/pith/ZUB5MBFDPU6PO2LBEVQAPTN6IZ/action/citation_signature","submit_replication":"https://pith.science/pith/ZUB5MBFDPU6PO2LBEVQAPTN6IZ/action/replication_record"}},"created_at":"2026-07-05T11:24:31.227444+00:00","updated_at":"2026-07-05T11:24:31.227444+00:00"}