{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:R3KVYEFYTS4G3F7FCUZUZYVFSQ","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":"04f3db6172d0e548aa491f65d78e3b1a74cfe1904a28f59ee8a1f024d6abe27f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T01:02:30Z","title_canon_sha256":"51145b420cd400d5da64c1f976a1fc20d67e7549ffd5b5ffdd8951de68af83b9"},"schema_version":"1.0","source":{"id":"2607.04574","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04574","created_at":"2026-07-07T02:19:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04574v1","created_at":"2026-07-07T02:19:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04574","created_at":"2026-07-07T02:19:25Z"},{"alias_kind":"pith_short_12","alias_value":"R3KVYEFYTS4G","created_at":"2026-07-07T02:19:25Z"},{"alias_kind":"pith_short_16","alias_value":"R3KVYEFYTS4G3F7F","created_at":"2026-07-07T02:19:25Z"},{"alias_kind":"pith_short_8","alias_value":"R3KVYEFY","created_at":"2026-07-07T02:19:25Z"}],"graph_snapshots":[{"event_id":"sha256:eacbd0c96ef297f10f62d4361bb7e382d148362d136051d03b264025200b67df","target":"graph","created_at":"2026-07-07T02:19:25Z","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/2607.04574/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For LLM agents, supervised fine-tuning is not only about teacher labels' quality, but also about which interaction contexts those labels condition on. Pure behavioral cloning uses full teacher demonstrations, creating a mismatch between teacher-induced contexts seen in training and student-induced contexts encountered at test time. Recent work addresses this mismatch by querying a teacher at contexts reached by the student, often with increasingly elaborate filtering of the teacher's continuations. We instead frame on-policy data construction as a budget-allocation problem: under matched super","authors_text":"Jiayi Cheng, Jose Blanchet, Junze Ye, Miao Lu, Michal Mankowski, Mohsen Bayati","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T01:02:30Z","title":"A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04574","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":"sha256:3bca6d77cef74f745604ea92627bf0804f8e56d14d0e0337c1d6871548d6fb73","target":"record","created_at":"2026-07-07T02:19:25Z","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":"04f3db6172d0e548aa491f65d78e3b1a74cfe1904a28f59ee8a1f024d6abe27f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T01:02:30Z","title_canon_sha256":"51145b420cd400d5da64c1f976a1fc20d67e7549ffd5b5ffdd8951de68af83b9"},"schema_version":"1.0","source":{"id":"2607.04574","kind":"arxiv","version":1}},"canonical_sha256":"8ed55c10b89cb86d97e515334ce2a5943cf48da0cc33761a0e756b918fcab1f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ed55c10b89cb86d97e515334ce2a5943cf48da0cc33761a0e756b918fcab1f5","first_computed_at":"2026-07-07T02:19:25.511466Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:25.511466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S48CGYtWy+MW9kbj5ulC4LZ6TRQSqzxsrqr/8bd2Mjhc6pJPe+CfjtOfdzzT+hbWyJYSOHVvce3dDmhf40l4DA==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:25.512428Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04574","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3bca6d77cef74f745604ea92627bf0804f8e56d14d0e0337c1d6871548d6fb73","sha256:eacbd0c96ef297f10f62d4361bb7e382d148362d136051d03b264025200b67df"],"state_sha256":"4cdb345502e041eeac79f5f92350391f6effb8089063398e390585ca85a5d7be"}