{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XRESD7G4DHBAVVMHTXPKGKTFMI","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":"de0c151991be2f144eb4fd175b04d73a52ea2a8c994642f84c42f321ad7c4e21","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T19:32:07Z","title_canon_sha256":"3160e291b23efca6e605922406e898c644f9aeb94f9f10a8af11fc9c683c27c8"},"schema_version":"1.0","source":{"id":"2606.00305","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00305","created_at":"2026-06-02T01:03:51Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00305v1","created_at":"2026-06-02T01:03:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00305","created_at":"2026-06-02T01:03:51Z"},{"alias_kind":"pith_short_12","alias_value":"XRESD7G4DHBA","created_at":"2026-06-02T01:03:51Z"},{"alias_kind":"pith_short_16","alias_value":"XRESD7G4DHBAVVMH","created_at":"2026-06-02T01:03:51Z"},{"alias_kind":"pith_short_8","alias_value":"XRESD7G4","created_at":"2026-06-02T01:03:51Z"}],"graph_snapshots":[{"event_id":"sha256:500ea0ccb59e306ffa6e18739c6cff7c089314abbb6b37edbab32daae5ae3390","target":"graph","created_at":"2026-06-02T01:03:51Z","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/2606.00305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-Policy Distillation (OPD) improves large language model reasoning by training a student model on trajectories sampled from its own policy under teacher supervision. Although OPD operates on trajectories, its learning signal remains token-level: it identifies deviations through high-loss tokens and repairs them through local reverse-KL correction. We show that this \"trajectory-sampled but token-learned\" mechanism cannot reliably bridge student trajectories toward teacher trajectories. About 30% of high-loss tokens fall into the low-divergence regime, indicating that many are surface-form mis","authors_text":"Francis Ferraro, Yuxuan Jiang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T19:32:07Z","title":"Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00305","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":"sha256:62f7f521c5a7bea6e256c91db6bd78f5f325b7492dfda3126cc911389c251579","target":"record","created_at":"2026-06-02T01:03:51Z","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":"de0c151991be2f144eb4fd175b04d73a52ea2a8c994642f84c42f321ad7c4e21","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T19:32:07Z","title_canon_sha256":"3160e291b23efca6e605922406e898c644f9aeb94f9f10a8af11fc9c683c27c8"},"schema_version":"1.0","source":{"id":"2606.00305","kind":"arxiv","version":1}},"canonical_sha256":"bc4921fcdc19c20ad5879ddea32a65622802a8b393fb3e412736f5334e596d75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc4921fcdc19c20ad5879ddea32a65622802a8b393fb3e412736f5334e596d75","first_computed_at":"2026-06-02T01:03:51.168104Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:51.168104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Aay2iEZqMSiTSlIvpxlfHKvVwfgFleSSiZGFMlAHz6yOOmFC0PAFRs9ZDbAl4BEpqaOScQGkdvQScZ2oRns8Bg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:51.168503Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00305","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62f7f521c5a7bea6e256c91db6bd78f5f325b7492dfda3126cc911389c251579","sha256:500ea0ccb59e306ffa6e18739c6cff7c089314abbb6b37edbab32daae5ae3390"],"state_sha256":"30b4c65e8a2669817cb26a3d4b83fdf414ba41c44de0ed4c9223b92b3822844d"}