{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:73KA2Z6SNV2IYLDF2OWRTP3RSB","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":"d71d76c74843e484b253ea41ba4c94509e590de371b34fe4becc6bbea3e632f4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T05:07:22Z","title_canon_sha256":"cf55aaf860ef34e9341229cb5f7700fad8c44d3b498f2fc055ebd0894901e546"},"schema_version":"1.0","source":{"id":"2607.19395","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19395","created_at":"2026-07-23T00:23:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19395v1","created_at":"2026-07-23T00:23:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19395","created_at":"2026-07-23T00:23:47Z"},{"alias_kind":"pith_short_12","alias_value":"73KA2Z6SNV2I","created_at":"2026-07-23T00:23:47Z"},{"alias_kind":"pith_short_16","alias_value":"73KA2Z6SNV2IYLDF","created_at":"2026-07-23T00:23:47Z"},{"alias_kind":"pith_short_8","alias_value":"73KA2Z6S","created_at":"2026-07-23T00:23:47Z"}],"graph_snapshots":[{"event_id":"sha256:8f7fddbfa97da4992ad8adde406fcdd57bc5b3a68ef4b73ec998a8a66d57d518","target":"graph","created_at":"2026-07-23T00:23:47Z","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/2607.19395/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Small language models are attractive backbones for interactive agents, but direct distillation from strong teacher trajectories often turns rich multi-turn behavior into one-shot imitation targets. This is inefficient in long-horizon environments, where early decisions shape later states and rewards. We propose Prefix-GRPO, a reinforcement learning framework that decomposes teacher trajectories into replay-aligned prefix queries and online continuations. Each prefix is replayed in the environment to recover a valid intermediate state, after which the student continues online interaction and re","authors_text":"Haoran Sun, Hongke Zhao, Jiale Huang, Likang Wu, Yihan Wang, Zhong Guan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T05:07:22Z","title":"From Trajectories to Prefixes: Reusing Teacher Trajectories via Replayed Prefixes and Online Continuation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19395","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:aa7971b4cd01735b1cbdd8d6f7ffec6d71c3670dde72552e28245417ca4a5fd2","target":"record","created_at":"2026-07-23T00:23:47Z","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":"d71d76c74843e484b253ea41ba4c94509e590de371b34fe4becc6bbea3e632f4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T05:07:22Z","title_canon_sha256":"cf55aaf860ef34e9341229cb5f7700fad8c44d3b498f2fc055ebd0894901e546"},"schema_version":"1.0","source":{"id":"2607.19395","kind":"arxiv","version":1}},"canonical_sha256":"fed40d67d26d748c2c65d3ad19bf71905ef2de62188b5f0afae15dfc969a7093","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fed40d67d26d748c2c65d3ad19bf71905ef2de62188b5f0afae15dfc969a7093","first_computed_at":"2026-07-23T00:23:47.888866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T00:23:47.888866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pBdwo9BXNXkDwhyEG8JYz+OpW7LeOZjPXbuLSMkKfh/fD4qbe/uODWf6946x/BBPHxOM5VQ9dCLzOsATsIzwAA==","signature_status":"signed_v1","signed_at":"2026-07-23T00:23:47.889701Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19395","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa7971b4cd01735b1cbdd8d6f7ffec6d71c3670dde72552e28245417ca4a5fd2","sha256:8f7fddbfa97da4992ad8adde406fcdd57bc5b3a68ef4b73ec998a8a66d57d518"],"state_sha256":"ee431468d43173345ecb02c3a87b5f0b6cc98fac75fdc9919737d191d9743856"}