{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GOCAXDHPYVDQX4URP3TBP65HYK","short_pith_number":"pith:GOCAXDHP","canonical_record":{"source":{"id":"2607.04751","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T07:43:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3aaa223c2d512bd14abee6b04ad6ca2f42d4f00d641a1f865d063738f49bc412","abstract_canon_sha256":"952f7cd1e2e983847c1a5a0d2b704141042c29a6768530ebc3f4d83300fd12c4"},"schema_version":"1.0"},"canonical_sha256":"33840b8cefc5470bf2917ee617fba7c2a1c69d5431be21f3689e6279fa053b3a","source":{"kind":"arxiv","id":"2607.04751","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04751","created_at":"2026-07-07T02:20:01Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04751v1","created_at":"2026-07-07T02:20:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04751","created_at":"2026-07-07T02:20:01Z"},{"alias_kind":"pith_short_12","alias_value":"GOCAXDHPYVDQ","created_at":"2026-07-07T02:20:01Z"},{"alias_kind":"pith_short_16","alias_value":"GOCAXDHPYVDQX4UR","created_at":"2026-07-07T02:20:01Z"},{"alias_kind":"pith_short_8","alias_value":"GOCAXDHP","created_at":"2026-07-07T02:20:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GOCAXDHPYVDQX4URP3TBP65HYK","target":"record","payload":{"canonical_record":{"source":{"id":"2607.04751","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T07:43:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3aaa223c2d512bd14abee6b04ad6ca2f42d4f00d641a1f865d063738f49bc412","abstract_canon_sha256":"952f7cd1e2e983847c1a5a0d2b704141042c29a6768530ebc3f4d83300fd12c4"},"schema_version":"1.0"},"canonical_sha256":"33840b8cefc5470bf2917ee617fba7c2a1c69d5431be21f3689e6279fa053b3a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:20:01.528606Z","signature_b64":"Z2fJHtRduyEpSXKip/0PkjhAbQpF+uUYsNRD0ject4DxjF+CbAna8qjIgq3PuGFMHvMKW4cfPol3yNGAXIMzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33840b8cefc5470bf2917ee617fba7c2a1c69d5431be21f3689e6279fa053b3a","last_reissued_at":"2026-07-07T02:20:01.527830Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:20:01.527830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.04751","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":"2026-07-07T02:20:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"skKxGt7RUEg+hA0bqpl267RDNrIhGY7nMo+hbY080aEvWtmyIzOAKgbu6ff6YHCr9dcLiMormS9AlTMhVfhUAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:50:39.467303Z"},"content_sha256":"325be203279e017cd6f72faedd436d6d5364fe89459c75414988e02e3c51a7e0","schema_version":"1.0","event_id":"sha256:325be203279e017cd6f72faedd436d6d5364fe89459c75414988e02e3c51a7e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GOCAXDHPYVDQX4URP3TBP65HYK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Trust Region Policy Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Li Lyna Zhang, Mao Yang, Zeke Xie, Zhengpeng Xie","submitted_at":"2026-07-06T07:43:36Z","abstract_excerpt":"Big goals are hard to achieve all at once; breaking them into small steps is wiser. We present Trust Region Policy Distillation (TOP-D), which transforms the notoriously unstable, high-variance On-Policy Distillation (OPD) into a stable training paradigm by dynamically constructing a proximal teacher. Theoretically, we establish a rigorous framework demonstrating that TOP-D inherently controls gradient variance. By providing a formal global convergence analysis alongside a monotonic improvement bound, we mathematically formalize the reliability and stability of the overall training dynamics. E"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04751","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/2607.04751/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":"2026-07-07T02:20:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+I1I9VU3SyoM88bpCpSjOcTjqQVwJElT6w/qUE/3g3DjEykyHFHxsfCQefPLfBymP0rIE+ikB57Imid2/mfJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:50:39.467653Z"},"content_sha256":"d691adfe743b72aa98b730d2c8644d8e7bcb1cb15b9806994e499f3986860857","schema_version":"1.0","event_id":"sha256:d691adfe743b72aa98b730d2c8644d8e7bcb1cb15b9806994e499f3986860857"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GOCAXDHPYVDQX4URP3TBP65HYK/bundle.json","state_url":"https://pith.science/pith/GOCAXDHPYVDQX4URP3TBP65HYK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GOCAXDHPYVDQX4URP3TBP65HYK/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":"2026-08-05T13:50:39Z","links":{"resolver":"https://pith.science/pith/GOCAXDHPYVDQX4URP3TBP65HYK","bundle":"https://pith.science/pith/GOCAXDHPYVDQX4URP3TBP65HYK/bundle.json","state":"https://pith.science/pith/GOCAXDHPYVDQX4URP3TBP65HYK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GOCAXDHPYVDQX4URP3TBP65HYK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GOCAXDHPYVDQX4URP3TBP65HYK","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":"952f7cd1e2e983847c1a5a0d2b704141042c29a6768530ebc3f4d83300fd12c4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T07:43:36Z","title_canon_sha256":"3aaa223c2d512bd14abee6b04ad6ca2f42d4f00d641a1f865d063738f49bc412"},"schema_version":"1.0","source":{"id":"2607.04751","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04751","created_at":"2026-07-07T02:20:01Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04751v1","created_at":"2026-07-07T02:20:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04751","created_at":"2026-07-07T02:20:01Z"},{"alias_kind":"pith_short_12","alias_value":"GOCAXDHPYVDQ","created_at":"2026-07-07T02:20:01Z"},{"alias_kind":"pith_short_16","alias_value":"GOCAXDHPYVDQX4UR","created_at":"2026-07-07T02:20:01Z"},{"alias_kind":"pith_short_8","alias_value":"GOCAXDHP","created_at":"2026-07-07T02:20:01Z"}],"graph_snapshots":[{"event_id":"sha256:d691adfe743b72aa98b730d2c8644d8e7bcb1cb15b9806994e499f3986860857","target":"graph","created_at":"2026-07-07T02:20:01Z","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/2607.04751/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Big goals are hard to achieve all at once; breaking them into small steps is wiser. We present Trust Region Policy Distillation (TOP-D), which transforms the notoriously unstable, high-variance On-Policy Distillation (OPD) into a stable training paradigm by dynamically constructing a proximal teacher. Theoretically, we establish a rigorous framework demonstrating that TOP-D inherently controls gradient variance. By providing a formal global convergence analysis alongside a monotonic improvement bound, we mathematically formalize the reliability and stability of the overall training dynamics. E","authors_text":"Li Lyna Zhang, Mao Yang, Zeke Xie, Zhengpeng Xie","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T07:43:36Z","title":"Trust Region Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04751","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":"sha256:325be203279e017cd6f72faedd436d6d5364fe89459c75414988e02e3c51a7e0","target":"record","created_at":"2026-07-07T02:20:01Z","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":"952f7cd1e2e983847c1a5a0d2b704141042c29a6768530ebc3f4d83300fd12c4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T07:43:36Z","title_canon_sha256":"3aaa223c2d512bd14abee6b04ad6ca2f42d4f00d641a1f865d063738f49bc412"},"schema_version":"1.0","source":{"id":"2607.04751","kind":"arxiv","version":1}},"canonical_sha256":"33840b8cefc5470bf2917ee617fba7c2a1c69d5431be21f3689e6279fa053b3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33840b8cefc5470bf2917ee617fba7c2a1c69d5431be21f3689e6279fa053b3a","first_computed_at":"2026-07-07T02:20:01.527830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:20:01.527830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z2fJHtRduyEpSXKip/0PkjhAbQpF+uUYsNRD0ject4DxjF+CbAna8qjIgq3PuGFMHvMKW4cfPol3yNGAXIMzAw==","signature_status":"signed_v1","signed_at":"2026-07-07T02:20:01.528606Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04751","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:325be203279e017cd6f72faedd436d6d5364fe89459c75414988e02e3c51a7e0","sha256:d691adfe743b72aa98b730d2c8644d8e7bcb1cb15b9806994e499f3986860857"],"state_sha256":"37d640c73cab0349ab67f9ac31d872ff696340547ce5e3c6a96c2a5612f5c015"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7gVAEawlFsJV11q9KbiQCV3FlcUKMNPLpsbhwITeMjN79AN7qm2AYk7aLiy4FIXcyChtM1rphAPaHMIaSWrOCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:50:39.471149Z","bundle_sha256":"40ec5903d5d7e427a59801349b313b8a2f93d51be9c49282a4b4793cba223958"}}