{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VB2IORJG3RNLIAR6M5FSV7TRDA","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":"b544a6117da0f8087a8a0eec6ffa11c298ef0448639aaa49d93d17656a6433fd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T17:48:19Z","title_canon_sha256":"286fbb23b4c888f81f5c86051e864f486483eedd812ed67a4ea6b0741516d075"},"schema_version":"1.0","source":{"id":"2508.21113","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21113","created_at":"2026-07-05T12:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21113v2","created_at":"2026-07-05T12:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21113","created_at":"2026-07-05T12:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"VB2IORJG3RNL","created_at":"2026-07-05T12:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"VB2IORJG3RNLIAR6","created_at":"2026-07-05T12:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"VB2IORJG","created_at":"2026-07-05T12:03:32Z"}],"graph_snapshots":[{"event_id":"sha256:360d9282d2563da1b531df55c902f1db1061359eb7511e61671046a1e75b4920","target":"graph","created_at":"2026-07-05T12:03:32Z","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/2508.21113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) equipped with step-by-step thinking capabilities have demonstrated remarkable performance on complex reasoning problems. However, this thinking process is redundant for simple problems solvable without complex reasoning. To address this inefficiency, we propose R-4B, an auto-thinking MLLM, which can adaptively decide when to think based on problem complexity. The central idea of R-4B is to empower the model with both thinking and non-thinking capabilities using bi-mode annealing, and apply Bi-mode Policy Optimization (BPO) to improve the model's accurac","authors_text":"Bolin Ni, Han Hu, Houwen Peng, Jie Jiang, Qi Yang, Shiming Xiang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T17:48:19Z","title":"R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21113","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":"sha256:363bb1ce059903c73025c103250f22afa3f471e11f7591b0ac9ff8c2db226a70","target":"record","created_at":"2026-07-05T12:03:32Z","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":"b544a6117da0f8087a8a0eec6ffa11c298ef0448639aaa49d93d17656a6433fd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T17:48:19Z","title_canon_sha256":"286fbb23b4c888f81f5c86051e864f486483eedd812ed67a4ea6b0741516d075"},"schema_version":"1.0","source":{"id":"2508.21113","kind":"arxiv","version":2}},"canonical_sha256":"a874874526dc5ab4023e674b2afe71181c4397c92e741c908ce3cd20f1561dfd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a874874526dc5ab4023e674b2afe71181c4397c92e741c908ce3cd20f1561dfd","first_computed_at":"2026-07-05T12:03:32.948256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:32.948256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mru0ZbAWGdSCkySBG0z6bJLeBkLwCHekEC+egVYkI6y4Gmq0nsGgQgfeyQz9dQt5UmO5oGJg3qsCSb8gjAp2CA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:32.948766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21113","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:363bb1ce059903c73025c103250f22afa3f471e11f7591b0ac9ff8c2db226a70","sha256:360d9282d2563da1b531df55c902f1db1061359eb7511e61671046a1e75b4920"],"state_sha256":"b0f20347e2bacea2da60481e2b7463efc3977dce381c2f6eb0f092800fb4a24e"}