{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UAGSU34P6TVCKC4PJ7S7VREWDT","short_pith_number":"pith:UAGSU34P","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"},"canonical_sha256":"a00d2a6f8ff4ea250b8f4fe5fac4961cf59013784878ec3f8ea93d02a03736a0","source":{"kind":"arxiv","id":"2607.29078","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.29078","created_at":"2026-08-03T01:19:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.29078v1","created_at":"2026-08-03T01:19:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29078","created_at":"2026-08-03T01:19:04Z"},{"alias_kind":"pith_short_12","alias_value":"UAGSU34P6TVC","created_at":"2026-08-03T01:19:04Z"},{"alias_kind":"pith_short_16","alias_value":"UAGSU34P6TVCKC4P","created_at":"2026-08-03T01:19:04Z"},{"alias_kind":"pith_short_8","alias_value":"UAGSU34P","created_at":"2026-08-03T01:19:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UAGSU34P6TVCKC4PJ7S7VREWDT","target":"record","payload":{"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"},"canonical_sha256":"a00d2a6f8ff4ea250b8f4fe5fac4961cf59013784878ec3f8ea93d02a03736a0","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"},"source_kind":"arxiv","source_id":"2607.29078","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":"2026-08-03T01:19:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Dz+QiHn3cVWECe++ROwu9oyQrU56mgQPRykmjLgGFrUazyJR91wQAiH4lNI91ihypwUKERZ/nMt2sSdFPMDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:31:31.770390Z"},"content_sha256":"bc6dc8b91765efbe9051d704bbdf55303588c66461cfc0fdee07711b27099943","schema_version":"1.0","event_id":"sha256:bc6dc8b91765efbe9051d704bbdf55303588c66461cfc0fdee07711b27099943"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UAGSU34P6TVCKC4PJ7S7VREWDT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-03T01:19:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TuaAOuNRgg6O2oV7qJU9ppCp4aO+z1ojwCh+2iiXz8Ax7Akay7EattutKgQawQKmZDBBIzDfQodwk89ZfHlrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:31:31.770916Z"},"content_sha256":"9355a1edbd26b4d92a66580872b119c53375bf468abd96da8cad79c53d640d3e","schema_version":"1.0","event_id":"sha256:9355a1edbd26b4d92a66580872b119c53375bf468abd96da8cad79c53d640d3e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UAGSU34P6TVCKC4PJ7S7VREWDT/bundle.json","state_url":"https://pith.science/pith/UAGSU34P6TVCKC4PJ7S7VREWDT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UAGSU34P6TVCKC4PJ7S7VREWDT/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":"2026-08-04T17:31:31Z","links":{"resolver":"https://pith.science/pith/UAGSU34P6TVCKC4PJ7S7VREWDT","bundle":"https://pith.science/pith/UAGSU34P6TVCKC4PJ7S7VREWDT/bundle.json","state":"https://pith.science/pith/UAGSU34P6TVCKC4PJ7S7VREWDT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UAGSU34P6TVCKC4PJ7S7VREWDT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UAGSU34P6TVCKC4PJ7S7VREWDT","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":"d6a920ab362cc56963edb94798481bc8f4c6d25f4b4af8c1a15c13bcdb9540ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T06:57:17Z","title_canon_sha256":"805b9a6e811256f34018a4e73e0f27d8635013f7415d1e75a642a717d799da99"},"schema_version":"1.0","source":{"id":"2607.29078","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.29078","created_at":"2026-08-03T01:19:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.29078v1","created_at":"2026-08-03T01:19:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29078","created_at":"2026-08-03T01:19:04Z"},{"alias_kind":"pith_short_12","alias_value":"UAGSU34P6TVC","created_at":"2026-08-03T01:19:04Z"},{"alias_kind":"pith_short_16","alias_value":"UAGSU34P6TVCKC4P","created_at":"2026-08-03T01:19:04Z"},{"alias_kind":"pith_short_8","alias_value":"UAGSU34P","created_at":"2026-08-03T01:19:04Z"}],"graph_snapshots":[{"event_id":"sha256:9355a1edbd26b4d92a66580872b119c53375bf468abd96da8cad79c53d640d3e","target":"graph","created_at":"2026-08-03T01:19:04Z","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/2607.29078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chao Song, Junlong Wu, Qianguo Sun, Yiyan Qi, Yuchen Xia, Yunjian Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T06:57:17Z","title":"DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29078","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:bc6dc8b91765efbe9051d704bbdf55303588c66461cfc0fdee07711b27099943","target":"record","created_at":"2026-08-03T01:19:04Z","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":"d6a920ab362cc56963edb94798481bc8f4c6d25f4b4af8c1a15c13bcdb9540ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T06:57:17Z","title_canon_sha256":"805b9a6e811256f34018a4e73e0f27d8635013f7415d1e75a642a717d799da99"},"schema_version":"1.0","source":{"id":"2607.29078","kind":"arxiv","version":1}},"canonical_sha256":"a00d2a6f8ff4ea250b8f4fe5fac4961cf59013784878ec3f8ea93d02a03736a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a00d2a6f8ff4ea250b8f4fe5fac4961cf59013784878ec3f8ea93d02a03736a0","first_computed_at":"2026-08-03T01:19:04.968913Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:19:04.968913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8CrD27dJXZmjGxPofFKllhhrKqMT0+PbpqC3XTz+KvfRa3lbD3bulD6Ht4OKRW2ICE+YN/ncDamBWJW/Us63Cg==","signature_status":"signed_v1","signed_at":"2026-08-03T01:19:04.970446Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.29078","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc6dc8b91765efbe9051d704bbdf55303588c66461cfc0fdee07711b27099943","sha256:9355a1edbd26b4d92a66580872b119c53375bf468abd96da8cad79c53d640d3e"],"state_sha256":"fd03f46e71b33f237d5678e6e7175f401131236f2ac05c9597ad98edb10c64dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2OsPK5Itrd/YbrIPgmcmIuF0t9a6lXeo0H5VcBmBeT5JynJwhgqowjIpm/J/FwQlUcjmhirIcUpV4jug4WmJDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:31:31.775579Z","bundle_sha256":"a004c9b019cab12ed933ae98fb8b97524933a516bd9744cfcedd03e64533247e"}}