{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G6HRKA62M5R4Y3A52VHASLE3NG","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":"725591e0e916f054842a5131fd6ac8a5dc17c7d3cc1e44128a2f651e98ae9dfd","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T03:56:35Z","title_canon_sha256":"5dc28a5424b13203a5788ef2777d8a1a49f5b181240caed81582d0c8f50ca98b"},"schema_version":"1.0","source":{"id":"2607.05804","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05804","created_at":"2026-07-08T01:18:46Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05804v1","created_at":"2026-07-08T01:18:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05804","created_at":"2026-07-08T01:18:46Z"},{"alias_kind":"pith_short_12","alias_value":"G6HRKA62M5R4","created_at":"2026-07-08T01:18:46Z"},{"alias_kind":"pith_short_16","alias_value":"G6HRKA62M5R4Y3A5","created_at":"2026-07-08T01:18:46Z"},{"alias_kind":"pith_short_8","alias_value":"G6HRKA62","created_at":"2026-07-08T01:18:46Z"}],"graph_snapshots":[{"event_id":"sha256:9989544515391a5da91139bfb592540276f1542221779abb964f96c051a03978","target":"graph","created_at":"2026-07-08T01:18:46Z","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/2607.05804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD) trains a student policy by matching a stronger teacher on the student's own trajectories, offering a promising framework for language agent training. However, its application to long-horizon agentic tasks remains insufficiently explored. We identify two key inefficiencies in vanilla agent OPD: (1) full-horizon rollouts often waste wall-clock resources on tail turns that provide weak and noisy KL supervision, and (2) trajectory-level KL objectives concentrate most of the loss on shallow tokens, leaving deeper decision turns under-trained once initial behaviors are a","authors_text":"Can Xu, Dengyun Peng, Haoling Li, Jingjing Chen, Kai Zheng, Yuhang Zhou","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T03:56:35Z","title":"TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05804","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":"sha256:94c446bf980f3e0aec54ba927d773712a33bc683fc3352d1fc3f9038c787e51a","target":"record","created_at":"2026-07-08T01:18:46Z","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":"725591e0e916f054842a5131fd6ac8a5dc17c7d3cc1e44128a2f651e98ae9dfd","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T03:56:35Z","title_canon_sha256":"5dc28a5424b13203a5788ef2777d8a1a49f5b181240caed81582d0c8f50ca98b"},"schema_version":"1.0","source":{"id":"2607.05804","kind":"arxiv","version":1}},"canonical_sha256":"378f1503da6763cc6c1dd54e092c9b6993ceada2547f964f39f21dc32651cab3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"378f1503da6763cc6c1dd54e092c9b6993ceada2547f964f39f21dc32651cab3","first_computed_at":"2026-07-08T01:18:46.616908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:18:46.616908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KmKiKNzVNTx8OniwomE4S/5he+r+t/DlVwaWy2FN2uS9nh5xXP959uSDpTd2HqipgP57yo99otXFENOnmlWYBw==","signature_status":"signed_v1","signed_at":"2026-07-08T01:18:46.617353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.05804","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94c446bf980f3e0aec54ba927d773712a33bc683fc3352d1fc3f9038c787e51a","sha256:9989544515391a5da91139bfb592540276f1542221779abb964f96c051a03978"],"state_sha256":"4e4da2f4198e2bd1bd42f833fd48e0a2dadbc422a8bbdf7d5e9c795b6019fbf6"}