{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UAGSU34P6TVCKC4PJ7S7VREWDT","short_pith_number":"pith:UAGSU34P","schema_version":"1.0","canonical_sha256":"a00d2a6f8ff4ea250b8f4fe5fac4961cf59013784878ec3f8ea93d02a03736a0","source":{"kind":"arxiv","id":"2607.29078","version":1},"attestation_state":"computed","paper":{"title":"DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Song, Junlong Wu, Qianguo Sun, Yiyan Qi, Yuchen Xia, Yunjian Xu","submitted_at":"2026-07-31T06:57:17Z","abstract_excerpt":"On-policy distillation (OPD) trains student models on their own rollouts to reduce exposure bias. However, in multi-turn agent scenarios, early student errors can lead a trajectory away from the teacher's familiar domain. Existing curriculum learning methods regulate how much teacher support is used according to training progress, but cannot determine when it is needed. In light of this, we propose DASH-OPD, Discrepancy-Aware Switching with Hysteresis for OPD, a new agentic OPD method that can switch executors adaptively and bidirectionally. On each turn, DASH-OPD calculates a mean log-probabi"},"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":"2607.29078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T06:57:17Z","cross_cats_sorted":[],"title_canon_sha256":"805b9a6e811256f34018a4e73e0f27d8635013f7415d1e75a642a717d799da99","abstract_canon_sha256":"d6a920ab362cc56963edb94798481bc8f4c6d25f4b4af8c1a15c13bcdb9540ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:19:04.970446Z","signature_b64":"8CrD27dJXZmjGxPofFKllhhrKqMT0+PbpqC3XTz+KvfRa3lbD3bulD6Ht4OKRW2ICE+YN/ncDamBWJW/Us63Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a00d2a6f8ff4ea250b8f4fe5fac4961cf59013784878ec3f8ea93d02a03736a0","last_reissued_at":"2026-08-03T01:19:04.968913Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:19:04.968913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Song, Junlong Wu, Qianguo Sun, Yiyan Qi, Yuchen Xia, Yunjian Xu","submitted_at":"2026-07-31T06:57:17Z","abstract_excerpt":"On-policy distillation (OPD) trains student models on their own rollouts to reduce exposure bias. However, in multi-turn agent scenarios, early student errors can lead a trajectory away from the teacher's familiar domain. Existing curriculum learning methods regulate how much teacher support is used according to training progress, but cannot determine when it is needed. In light of this, we propose DASH-OPD, Discrepancy-Aware Switching with Hysteresis for OPD, a new agentic OPD method that can switch executors adaptively and bidirectionally. On each turn, DASH-OPD calculates a mean log-probabi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29078","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/2607.29078/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":"2607.29078","created_at":"2026-08-03T01:19:04.969848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.29078v1","created_at":"2026-08-03T01:19:04.969848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29078","created_at":"2026-08-03T01:19:04.969848+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAGSU34P6TVC","created_at":"2026-08-03T01:19:04.969848+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAGSU34P6TVCKC4P","created_at":"2026-08-03T01:19:04.969848+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAGSU34P","created_at":"2026-08-03T01:19:04.969848+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/UAGSU34P6TVCKC4PJ7S7VREWDT","json":"https://pith.science/pith/UAGSU34P6TVCKC4PJ7S7VREWDT.json","graph_json":"https://pith.science/api/pith-number/UAGSU34P6TVCKC4PJ7S7VREWDT/graph.json","events_json":"https://pith.science/api/pith-number/UAGSU34P6TVCKC4PJ7S7VREWDT/events.json","paper":"https://pith.science/paper/UAGSU34P"},"agent_actions":{"view_html":"https://pith.science/pith/UAGSU34P6TVCKC4PJ7S7VREWDT","download_json":"https://pith.science/pith/UAGSU34P6TVCKC4PJ7S7VREWDT.json","view_paper":"https://pith.science/paper/UAGSU34P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.29078&json=true","fetch_graph":"https://pith.science/api/pith-number/UAGSU34P6TVCKC4PJ7S7VREWDT/graph.json","fetch_events":"https://pith.science/api/pith-number/UAGSU34P6TVCKC4PJ7S7VREWDT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAGSU34P6TVCKC4PJ7S7VREWDT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAGSU34P6TVCKC4PJ7S7VREWDT/action/storage_attestation","attest_author":"https://pith.science/pith/UAGSU34P6TVCKC4PJ7S7VREWDT/action/author_attestation","sign_citation":"https://pith.science/pith/UAGSU34P6TVCKC4PJ7S7VREWDT/action/citation_signature","submit_replication":"https://pith.science/pith/UAGSU34P6TVCKC4PJ7S7VREWDT/action/replication_record"}},"created_at":"2026-08-03T01:19:04.969848+00:00","updated_at":"2026-08-03T01:19:04.969848+00:00"}