{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SHPR3HLIK3CIFWRZS6KEWY7JW4","short_pith_number":"pith:SHPR3HLI","schema_version":"1.0","canonical_sha256":"91df1d9d6856c482da3997944b63e9b71e05280ac09597276f4788fc6289e7ec","source":{"kind":"arxiv","id":"2606.08432","version":1},"attestation_state":"computed","paper":{"title":"Trajectory-Refined Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Amy Zhang, Haoran Xu, Li Jiang, Yichuan Ding","submitted_at":"2026-06-07T03:17:25Z","abstract_excerpt":"On-policy distillation (OPD) has become a central post-training tool for large language models (LLMs), providing dense per-token teacher supervision along the student's own rollouts. In this work, we identify a common structural cause underlying OPD, which we call prefix failure. Under prefix failure, dense per-token supervision induces a bimodal teacher mixture and fragmented gradients that token-level loss truncation or reweighting fail to address. This observation motivates us to move beyond token-level loss interventions toward trajectory-level output corrections. We thus propose Trajector"},"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":"2606.08432","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-07T03:17:25Z","cross_cats_sorted":[],"title_canon_sha256":"56a9f53bacf710e13144e7f81c45c3c44d5b9e472ec20464ff3d3cf758e218d4","abstract_canon_sha256":"86f4b76ea64d6a4117cfe85a91fefeb4e6658b1608da4433fefd19e335edba8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:36.441804Z","signature_b64":"k5nOX9SMm7b5z/5tAuYcb2SLmj0fY86CFytid8M/WIBXPsXFBqvCNbu2gY2v+PAN/hwdjJGM3ySP5EcVOINbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91df1d9d6856c482da3997944b63e9b71e05280ac09597276f4788fc6289e7ec","last_reissued_at":"2026-06-09T01:05:36.441404Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:36.441404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trajectory-Refined Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Amy Zhang, Haoran Xu, Li Jiang, Yichuan Ding","submitted_at":"2026-06-07T03:17:25Z","abstract_excerpt":"On-policy distillation (OPD) has become a central post-training tool for large language models (LLMs), providing dense per-token teacher supervision along the student's own rollouts. In this work, we identify a common structural cause underlying OPD, which we call prefix failure. Under prefix failure, dense per-token supervision induces a bimodal teacher mixture and fragmented gradients that token-level loss truncation or reweighting fail to address. This observation motivates us to move beyond token-level loss interventions toward trajectory-level output corrections. We thus propose Trajector"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08432","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/2606.08432/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":"2606.08432","created_at":"2026-06-09T01:05:36.441472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08432v1","created_at":"2026-06-09T01:05:36.441472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08432","created_at":"2026-06-09T01:05:36.441472+00:00"},{"alias_kind":"pith_short_12","alias_value":"SHPR3HLIK3CI","created_at":"2026-06-09T01:05:36.441472+00:00"},{"alias_kind":"pith_short_16","alias_value":"SHPR3HLIK3CIFWRZ","created_at":"2026-06-09T01:05:36.441472+00:00"},{"alias_kind":"pith_short_8","alias_value":"SHPR3HLI","created_at":"2026-06-09T01:05:36.441472+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/SHPR3HLIK3CIFWRZS6KEWY7JW4","json":"https://pith.science/pith/SHPR3HLIK3CIFWRZS6KEWY7JW4.json","graph_json":"https://pith.science/api/pith-number/SHPR3HLIK3CIFWRZS6KEWY7JW4/graph.json","events_json":"https://pith.science/api/pith-number/SHPR3HLIK3CIFWRZS6KEWY7JW4/events.json","paper":"https://pith.science/paper/SHPR3HLI"},"agent_actions":{"view_html":"https://pith.science/pith/SHPR3HLIK3CIFWRZS6KEWY7JW4","download_json":"https://pith.science/pith/SHPR3HLIK3CIFWRZS6KEWY7JW4.json","view_paper":"https://pith.science/paper/SHPR3HLI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08432&json=true","fetch_graph":"https://pith.science/api/pith-number/SHPR3HLIK3CIFWRZS6KEWY7JW4/graph.json","fetch_events":"https://pith.science/api/pith-number/SHPR3HLIK3CIFWRZS6KEWY7JW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SHPR3HLIK3CIFWRZS6KEWY7JW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SHPR3HLIK3CIFWRZS6KEWY7JW4/action/storage_attestation","attest_author":"https://pith.science/pith/SHPR3HLIK3CIFWRZS6KEWY7JW4/action/author_attestation","sign_citation":"https://pith.science/pith/SHPR3HLIK3CIFWRZS6KEWY7JW4/action/citation_signature","submit_replication":"https://pith.science/pith/SHPR3HLIK3CIFWRZS6KEWY7JW4/action/replication_record"}},"created_at":"2026-06-09T01:05:36.441472+00:00","updated_at":"2026-06-09T01:05:36.441472+00:00"}