{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DDSM6DIOF275RZZRUJYKXUIWWX","short_pith_number":"pith:DDSM6DIO","schema_version":"1.0","canonical_sha256":"18e4cf0d0e2ebfd8e731a270abd116b5ef595b1531bfc3a291dc46bed592b7b3","source":{"kind":"arxiv","id":"2605.30859","version":1},"attestation_state":"computed","paper":{"title":"DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Cui, Fangcheng Fu, Longzan Luo, Siwei Chen, Xinyi Liu, Xupeng Miao, Yujie Wang","submitted_at":"2026-05-29T05:31:46Z","abstract_excerpt":"Reinforcement Learning (RL) has become pivotal for improving model capabilities yet suffers from rollout efficiency bottlenecks due to the long-tail response length distribution. While existing works mitigate the impact of long tails via prompt-level tail scheduling, we focus on the root source of inefficiency: the distribution itself. Specifically, we characterize the long-tail distribution at a finer granularity, identifying intra-prompt long tails, and revealing that they frequently consist of ineffective verbosity. To address this, we propose a novel paradigm of active distribution shaping"},"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":"2605.30859","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T05:31:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d3f9e84f46f2c11c265a7a375b0a92f4a42e98959d666ebb51f0e184194c615c","abstract_canon_sha256":"c3b32d1bf6853210a597ed554e100ccf7fbccea7326442fd546dcd483e3bed31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:21.482052Z","signature_b64":"ih2Y+KrTKL0IegTnR3N5+BCuR3n58lfLPgSRb7dq9Q0NzsetbHpX+3PTZKAR0kowA1ph2/F2N1EQFHeEPVqfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18e4cf0d0e2ebfd8e731a270abd116b5ef595b1531bfc3a291dc46bed592b7b3","last_reissued_at":"2026-06-01T01:03:21.481306Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:21.481306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Cui, Fangcheng Fu, Longzan Luo, Siwei Chen, Xinyi Liu, Xupeng Miao, Yujie Wang","submitted_at":"2026-05-29T05:31:46Z","abstract_excerpt":"Reinforcement Learning (RL) has become pivotal for improving model capabilities yet suffers from rollout efficiency bottlenecks due to the long-tail response length distribution. While existing works mitigate the impact of long tails via prompt-level tail scheduling, we focus on the root source of inefficiency: the distribution itself. Specifically, we characterize the long-tail distribution at a finer granularity, identifying intra-prompt long tails, and revealing that they frequently consist of ineffective verbosity. To address this, we propose a novel paradigm of active distribution shaping"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30859","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/2605.30859/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":"2605.30859","created_at":"2026-06-01T01:03:21.481427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30859v1","created_at":"2026-06-01T01:03:21.481427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30859","created_at":"2026-06-01T01:03:21.481427+00:00"},{"alias_kind":"pith_short_12","alias_value":"DDSM6DIOF275","created_at":"2026-06-01T01:03:21.481427+00:00"},{"alias_kind":"pith_short_16","alias_value":"DDSM6DIOF275RZZR","created_at":"2026-06-01T01:03:21.481427+00:00"},{"alias_kind":"pith_short_8","alias_value":"DDSM6DIO","created_at":"2026-06-01T01:03:21.481427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DDSM6DIOF275RZZRUJYKXUIWWX","json":"https://pith.science/pith/DDSM6DIOF275RZZRUJYKXUIWWX.json","graph_json":"https://pith.science/api/pith-number/DDSM6DIOF275RZZRUJYKXUIWWX/graph.json","events_json":"https://pith.science/api/pith-number/DDSM6DIOF275RZZRUJYKXUIWWX/events.json","paper":"https://pith.science/paper/DDSM6DIO"},"agent_actions":{"view_html":"https://pith.science/pith/DDSM6DIOF275RZZRUJYKXUIWWX","download_json":"https://pith.science/pith/DDSM6DIOF275RZZRUJYKXUIWWX.json","view_paper":"https://pith.science/paper/DDSM6DIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30859&json=true","fetch_graph":"https://pith.science/api/pith-number/DDSM6DIOF275RZZRUJYKXUIWWX/graph.json","fetch_events":"https://pith.science/api/pith-number/DDSM6DIOF275RZZRUJYKXUIWWX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DDSM6DIOF275RZZRUJYKXUIWWX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DDSM6DIOF275RZZRUJYKXUIWWX/action/storage_attestation","attest_author":"https://pith.science/pith/DDSM6DIOF275RZZRUJYKXUIWWX/action/author_attestation","sign_citation":"https://pith.science/pith/DDSM6DIOF275RZZRUJYKXUIWWX/action/citation_signature","submit_replication":"https://pith.science/pith/DDSM6DIOF275RZZRUJYKXUIWWX/action/replication_record"}},"created_at":"2026-06-01T01:03:21.481427+00:00","updated_at":"2026-06-01T01:03:21.481427+00:00"}