{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZUB5MBFDPU6PO2LBEVQAPTN6IZ","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":"b18b42bb2c7a0fc956d76164ba64265c4b8d8d1f5417f052ee3e964acfc0d217","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-19T08:49:13Z","title_canon_sha256":"28bf2299871481a0ff95dbfd1bfc7d220c22496167e1d08cd2f1234cf4c503a2"},"schema_version":"1.0","source":{"id":"2506.16141","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16141","created_at":"2026-07-05T11:24:31Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16141v1","created_at":"2026-07-05T11:24:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16141","created_at":"2026-07-05T11:24:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZUB5MBFDPU6P","created_at":"2026-07-05T11:24:31Z"},{"alias_kind":"pith_short_16","alias_value":"ZUB5MBFDPU6PO2LB","created_at":"2026-07-05T11:24:31Z"},{"alias_kind":"pith_short_8","alias_value":"ZUB5MBFD","created_at":"2026-07-05T11:24:31Z"}],"graph_snapshots":[{"event_id":"sha256:f1be17b6d560946e50dcb41d5d11bb9af80aef19e89b2331f7724fa53557d23b","target":"graph","created_at":"2026-07-05T11:24:31Z","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/2506.16141/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Junhao Cheng, Rui Wang, Xihui Liu, Yi Chen, Ying Shan, Yixiao Ge, Yuying Ge","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-19T08:49:13Z","title":"GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16141","kind":"arxiv","version":1},"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":"sha256:40a79f306bbec2e03e97c73f16ff6e889b16793b4a707a4485a33e421bd659d6","target":"record","created_at":"2026-07-05T11:24:31Z","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":"b18b42bb2c7a0fc956d76164ba64265c4b8d8d1f5417f052ee3e964acfc0d217","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-19T08:49:13Z","title_canon_sha256":"28bf2299871481a0ff95dbfd1bfc7d220c22496167e1d08cd2f1234cf4c503a2"},"schema_version":"1.0","source":{"id":"2506.16141","kind":"arxiv","version":1}},"canonical_sha256":"cd03d604a37d3cf76961256007cdbe466445cb13559d1b48b242b016468bc381","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd03d604a37d3cf76961256007cdbe466445cb13559d1b48b242b016468bc381","first_computed_at":"2026-07-05T11:24:31.227364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:31.227364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YsTU4Bpz4dRAqdLy0v5uK8yOVdG2+gxkdQ1qH6BCKTqmPDixglD9hblO/lMfd+ChCYciEruRLwASxpJ9mbjSCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:31.228194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16141","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40a79f306bbec2e03e97c73f16ff6e889b16793b4a707a4485a33e421bd659d6","sha256:f1be17b6d560946e50dcb41d5d11bb9af80aef19e89b2331f7724fa53557d23b"],"state_sha256":"3cc0771fe659a0d41cd4f19882d5f2e484361a4a5d9ef76330edff56855b6639"}