{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ER4JWYZLATMXZ7UNKGWOIBKTJD","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":"5b814859f03014f4963e34640af9f1c1bdc76771284ded1b833ea43954e151f7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T14:20:47Z","title_canon_sha256":"7b8c7e37dec0cef32fd7d61f07b7324b35a623dc395c87beb9d2de24f1c394a3"},"schema_version":"1.0","source":{"id":"2606.30345","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30345","created_at":"2026-06-30T02:18:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30345v1","created_at":"2026-06-30T02:18:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30345","created_at":"2026-06-30T02:18:11Z"},{"alias_kind":"pith_short_12","alias_value":"ER4JWYZLATMX","created_at":"2026-06-30T02:18:11Z"},{"alias_kind":"pith_short_16","alias_value":"ER4JWYZLATMXZ7UN","created_at":"2026-06-30T02:18:11Z"},{"alias_kind":"pith_short_8","alias_value":"ER4JWYZL","created_at":"2026-06-30T02:18:11Z"}],"graph_snapshots":[{"event_id":"sha256:419b3cc7cd164b33731c3829156dbab3c02fe433fb4b67fc717fc44325d0e564","target":"graph","created_at":"2026-06-30T02:18:11Z","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/2606.30345/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Enabling large language models to achieve stable self-improvement without external expert supervision remains a central challenge in complex reasoning tasks. Existing self-distillation and reinforcement learning methods lack explicit mechanisms for tracking problem-level learning progress and adapting optimization strategies accordingly. Consequently, training may over-optimize easy problems, receive weak supervision from hard problems, and fail to sufficiently explore borderline cases. To resolve these issues, we propose DRIFT, an online self-evolution policy optimization framework for large ","authors_text":"Baoyan Guo, Bolan Yang, Chengwei Liu, Dan Liu, Haisen Luo, Haoning Wang, Haotian Wang, Jiong Chen, Junxi Yin, Lei Zhang, Ming Cui, Shuaiting Chen, Xiaoyu Tian, Xiongfei Yan, Yiwei Liu, Yuansheng Song","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T14:20:47Z","title":"DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30345","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:d124943283dde3c69addc7442df0443c2c23e951c76459ff733f06ca76622522","target":"record","created_at":"2026-06-30T02:18:11Z","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":"5b814859f03014f4963e34640af9f1c1bdc76771284ded1b833ea43954e151f7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T14:20:47Z","title_canon_sha256":"7b8c7e37dec0cef32fd7d61f07b7324b35a623dc395c87beb9d2de24f1c394a3"},"schema_version":"1.0","source":{"id":"2606.30345","kind":"arxiv","version":1}},"canonical_sha256":"24789b632b04d97cfe8d51ace4055348dd87235585362e813c4a78aba4cb2636","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24789b632b04d97cfe8d51ace4055348dd87235585362e813c4a78aba4cb2636","first_computed_at":"2026-06-30T02:18:11.267658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:18:11.267658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LtvwChso6A0NcVt+aayIxBaIblSVz/+RI+OLvyxwb1KIUSba11t7MKU3WUU2gRH6pm7OvoPLV5pnH+WnAS2wDA==","signature_status":"signed_v1","signed_at":"2026-06-30T02:18:11.268452Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30345","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d124943283dde3c69addc7442df0443c2c23e951c76459ff733f06ca76622522","sha256:419b3cc7cd164b33731c3829156dbab3c02fe433fb4b67fc717fc44325d0e564"],"state_sha256":"5c8af1581d8b808092ddc3c85e406b01a62dba2d00dc61f642e6a33f7cb09565"}