{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Q3QDWVBT236FY7GTTLBT5J47FQ","short_pith_number":"pith:Q3QDWVBT","canonical_record":{"source":{"id":"2605.17862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T05:14:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f38cf2d5d45deddf8a77b5e5b0c3fe1f488afabd632e383ef2b6abe13e81c901","abstract_canon_sha256":"a2975045e4161cd725eb758351787fb88d4053bc469f948ee30f46c97fa87fa4"},"schema_version":"1.0"},"canonical_sha256":"86e03b5433d6fc5c7cd39ac33ea79f2c2bb673527d44129d23610bd52aea2bce","source":{"kind":"arxiv","id":"2605.17862","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17862","created_at":"2026-05-20T00:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17862v1","created_at":"2026-05-20T00:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17862","created_at":"2026-05-20T00:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"Q3QDWVBT236F","created_at":"2026-05-20T00:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"Q3QDWVBT236FY7GT","created_at":"2026-05-20T00:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"Q3QDWVBT","created_at":"2026-05-20T00:05:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Q3QDWVBT236FY7GTTLBT5J47FQ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.17862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T05:14:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f38cf2d5d45deddf8a77b5e5b0c3fe1f488afabd632e383ef2b6abe13e81c901","abstract_canon_sha256":"a2975045e4161cd725eb758351787fb88d4053bc469f948ee30f46c97fa87fa4"},"schema_version":"1.0"},"canonical_sha256":"86e03b5433d6fc5c7cd39ac33ea79f2c2bb673527d44129d23610bd52aea2bce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:02.398363Z","signature_b64":"hg44Q1Oh1PIw82NZahqyDxI+Uq9u540oskvSMxG54F5JcTJY3YmPVO2zr6D0xFVRv/5eZgJEX297nDcL0d5CDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86e03b5433d6fc5c7cd39ac33ea79f2c2bb673527d44129d23610bd52aea2bce","last_reissued_at":"2026-05-20T00:05:02.397379Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:02.397379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.17862","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4pMmTp73xY/TaHnsgP5k/TplgdBW382MuSpBRFuPsw+5b31P6XXo3K6VVzbsZhwy1N86yOsPXnYSGpWRATG4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T14:47:35.516660Z"},"content_sha256":"4b91d7b9cea3c0a2163c9d4b9f6315b92def6e1e272d82299752593c41881ab9","schema_version":"1.0","event_id":"sha256:4b91d7b9cea3c0a2163c9d4b9f6315b92def6e1e272d82299752593c41881ab9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Q3QDWVBT236FY7GTTLBT5J47FQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"$\\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jibin Wu, Shimin Zhang, Xianwei Chen","submitted_at":"2026-05-18T05:14:18Z","abstract_excerpt":"Scaling on-policy distillation (OPD) for large language models (LLMs) confronts a fundamental tension: asynchronous execution is necessary for system efficiency, but structurally deviates from the ideal on-policy objective. To address this challenge, we theoretically decompose the objective discrepancy into rollout drift and supervision drift, capturing staleness in student rollout and teacher context, respectively. Building on this, we introduce a sample-level freshness score that quantifies the reliability of a buffered sample with respect to the on-policy objective. Guided by this signal, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17862","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/2605.17862/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rvEAsTpSHyzbMLCT98cpcCQzpJU0vEtqPg2ahsozZUR7KPmNvMoVgRaZqZ92nDKfM1FlUGcM7iG8xraiTTN1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T14:47:35.517036Z"},"content_sha256":"c51d898514b1c9917a7058cddfa70076b9d14b2d3d98da39ace6538d17578f1b","schema_version":"1.0","event_id":"sha256:c51d898514b1c9917a7058cddfa70076b9d14b2d3d98da39ace6538d17578f1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q3QDWVBT236FY7GTTLBT5J47FQ/bundle.json","state_url":"https://pith.science/pith/Q3QDWVBT236FY7GTTLBT5J47FQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q3QDWVBT236FY7GTTLBT5J47FQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T14:47:35Z","links":{"resolver":"https://pith.science/pith/Q3QDWVBT236FY7GTTLBT5J47FQ","bundle":"https://pith.science/pith/Q3QDWVBT236FY7GTTLBT5J47FQ/bundle.json","state":"https://pith.science/pith/Q3QDWVBT236FY7GTTLBT5J47FQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q3QDWVBT236FY7GTTLBT5J47FQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q3QDWVBT236FY7GTTLBT5J47FQ","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":"a2975045e4161cd725eb758351787fb88d4053bc469f948ee30f46c97fa87fa4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T05:14:18Z","title_canon_sha256":"f38cf2d5d45deddf8a77b5e5b0c3fe1f488afabd632e383ef2b6abe13e81c901"},"schema_version":"1.0","source":{"id":"2605.17862","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17862","created_at":"2026-05-20T00:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17862v1","created_at":"2026-05-20T00:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17862","created_at":"2026-05-20T00:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"Q3QDWVBT236F","created_at":"2026-05-20T00:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"Q3QDWVBT236FY7GT","created_at":"2026-05-20T00:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"Q3QDWVBT","created_at":"2026-05-20T00:05:02Z"}],"graph_snapshots":[{"event_id":"sha256:c51d898514b1c9917a7058cddfa70076b9d14b2d3d98da39ace6538d17578f1b","target":"graph","created_at":"2026-05-20T00:05:02Z","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/2605.17862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling on-policy distillation (OPD) for large language models (LLMs) confronts a fundamental tension: asynchronous execution is necessary for system efficiency, but structurally deviates from the ideal on-policy objective. To address this challenge, we theoretically decompose the objective discrepancy into rollout drift and supervision drift, capturing staleness in student rollout and teacher context, respectively. Building on this, we introduce a sample-level freshness score that quantifies the reliability of a buffered sample with respect to the on-policy objective. Guided by this signal, w","authors_text":"Jibin Wu, Shimin Zhang, Xianwei Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T05:14:18Z","title":"$\\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17862","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":"sha256:4b91d7b9cea3c0a2163c9d4b9f6315b92def6e1e272d82299752593c41881ab9","target":"record","created_at":"2026-05-20T00:05:02Z","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":"a2975045e4161cd725eb758351787fb88d4053bc469f948ee30f46c97fa87fa4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T05:14:18Z","title_canon_sha256":"f38cf2d5d45deddf8a77b5e5b0c3fe1f488afabd632e383ef2b6abe13e81c901"},"schema_version":"1.0","source":{"id":"2605.17862","kind":"arxiv","version":1}},"canonical_sha256":"86e03b5433d6fc5c7cd39ac33ea79f2c2bb673527d44129d23610bd52aea2bce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86e03b5433d6fc5c7cd39ac33ea79f2c2bb673527d44129d23610bd52aea2bce","first_computed_at":"2026-05-20T00:05:02.397379Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:02.397379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hg44Q1Oh1PIw82NZahqyDxI+Uq9u540oskvSMxG54F5JcTJY3YmPVO2zr6D0xFVRv/5eZgJEX297nDcL0d5CDA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:02.398363Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17862","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b91d7b9cea3c0a2163c9d4b9f6315b92def6e1e272d82299752593c41881ab9","sha256:c51d898514b1c9917a7058cddfa70076b9d14b2d3d98da39ace6538d17578f1b"],"state_sha256":"1f332b6a38cc2d2c50208850b94da8da7d2ca0c7c92a94940b3e1e46c8c9564c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UXKxmldFNSJh2i7c5Ar1ezAqLM8iB+ZhTM8dmFlGsdfets2E773e5y7XVYEPvJVBXGBl2sCqnbdv04By5VgjCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T14:47:35.519139Z","bundle_sha256":"68b84c548eb313045a949f07324a1203a83205bf285e9cbe7bafdef5f0273f15"}}