{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:F34T2FZ77TYBDUGIY2I4OLNNHF","short_pith_number":"pith:F34T2FZ7","canonical_record":{"source":{"id":"1902.02186","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-06T14:01:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b4a0aab9dde30477f83de5594af9e2100a49b858fa6c44965a429f86dff3198b","abstract_canon_sha256":"be977552585ee0b0b17beb9815cc8f2ad1df36d95df1e492baab341453eae0fc"},"schema_version":"1.0"},"canonical_sha256":"2ef93d173ffcf011d0c8c691c72dad3961b88cf7d32486f6fe9313b1246fb186","source":{"kind":"arxiv","id":"1902.02186","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.02186","created_at":"2026-05-17T23:54:37Z"},{"alias_kind":"arxiv_version","alias_value":"1902.02186v1","created_at":"2026-05-17T23:54:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02186","created_at":"2026-05-17T23:54:37Z"},{"alias_kind":"pith_short_12","alias_value":"F34T2FZ77TYB","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"F34T2FZ77TYBDUGI","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"F34T2FZ7","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:F34T2FZ77TYBDUGIY2I4OLNNHF","target":"record","payload":{"canonical_record":{"source":{"id":"1902.02186","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-06T14:01:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b4a0aab9dde30477f83de5594af9e2100a49b858fa6c44965a429f86dff3198b","abstract_canon_sha256":"be977552585ee0b0b17beb9815cc8f2ad1df36d95df1e492baab341453eae0fc"},"schema_version":"1.0"},"canonical_sha256":"2ef93d173ffcf011d0c8c691c72dad3961b88cf7d32486f6fe9313b1246fb186","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:37.682283Z","signature_b64":"ZyivJrF0oTirquX9GtavzXGzwyObZ1tq+EOSsjFnlyHFLcRlStVThCFSS9SlrBAodjOMWL0I4gezYEU2OXXhDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ef93d173ffcf011d0c8c691c72dad3961b88cf7d32486f6fe9313b1246fb186","last_reissued_at":"2026-05-17T23:54:37.681535Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:37.681535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.02186","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":"2026-05-17T23:54:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A/fG+i0dfU7aUhYv/ntJ8jkjWeDTvDkgzp4rrBAuA2z7BOKAaAPLoiwBrCZs79kyN5L9tcq54fOFmn1tuXeICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:38:10.299348Z"},"content_sha256":"f0c0a31e8a8369cb6ebd2206783eb18c56ddfc1d191a19518fac89956351bd6c","schema_version":"1.0","event_id":"sha256:f0c0a31e8a8369cb6ebd2206783eb18c56ddfc1d191a19518fac89956351bd6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:F34T2FZ77TYBDUGIY2I4OLNNHF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distilling Policy Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Grzegorz Swirszcz, Max Jaderberg, Razvan Pascanu, Siddhant M. Jayakumar, Simon Osindero, Wojciech Marian Czarnecki","submitted_at":"2019-02-06T14:01:34Z","abstract_excerpt":"The transfer of knowledge from one policy to another is an important tool in Deep Reinforcement Learning. This process, referred to as distillation, has been used to great success, for example, by enhancing the optimisation of agents, leading to stronger performance faster, on harder domains [26, 32, 5, 8]. Despite the widespread use and conceptual simplicity of distillation, many different formulations are used in practice, and the subtle variations between them can often drastically change the performance and the resulting objective that is being optimised. In this work, we rigorously explor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02186","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":""},"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":"2026-05-17T23:54:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/l5lXeFyq/x7T6kOAF5ixM03dNjVEwepVZr28cn29I22Ic/hQPAg49mtBWikYPSA3fpsX1uzzNtIuVcKkqIbCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:38:10.300037Z"},"content_sha256":"a82f7a6ed4ffa992113fb1cac0b8c58fd173f0f743a836cce5209f0f319a283f","schema_version":"1.0","event_id":"sha256:a82f7a6ed4ffa992113fb1cac0b8c58fd173f0f743a836cce5209f0f319a283f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F34T2FZ77TYBDUGIY2I4OLNNHF/bundle.json","state_url":"https://pith.science/pith/F34T2FZ77TYBDUGIY2I4OLNNHF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F34T2FZ77TYBDUGIY2I4OLNNHF/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":"2026-05-25T17:38:10Z","links":{"resolver":"https://pith.science/pith/F34T2FZ77TYBDUGIY2I4OLNNHF","bundle":"https://pith.science/pith/F34T2FZ77TYBDUGIY2I4OLNNHF/bundle.json","state":"https://pith.science/pith/F34T2FZ77TYBDUGIY2I4OLNNHF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F34T2FZ77TYBDUGIY2I4OLNNHF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:F34T2FZ77TYBDUGIY2I4OLNNHF","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":"be977552585ee0b0b17beb9815cc8f2ad1df36d95df1e492baab341453eae0fc","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-06T14:01:34Z","title_canon_sha256":"b4a0aab9dde30477f83de5594af9e2100a49b858fa6c44965a429f86dff3198b"},"schema_version":"1.0","source":{"id":"1902.02186","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.02186","created_at":"2026-05-17T23:54:37Z"},{"alias_kind":"arxiv_version","alias_value":"1902.02186v1","created_at":"2026-05-17T23:54:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02186","created_at":"2026-05-17T23:54:37Z"},{"alias_kind":"pith_short_12","alias_value":"F34T2FZ77TYB","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"F34T2FZ77TYBDUGI","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"F34T2FZ7","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:a82f7a6ed4ffa992113fb1cac0b8c58fd173f0f743a836cce5209f0f319a283f","target":"graph","created_at":"2026-05-17T23:54:37Z","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"},"paper":{"abstract_excerpt":"The transfer of knowledge from one policy to another is an important tool in Deep Reinforcement Learning. This process, referred to as distillation, has been used to great success, for example, by enhancing the optimisation of agents, leading to stronger performance faster, on harder domains [26, 32, 5, 8]. Despite the widespread use and conceptual simplicity of distillation, many different formulations are used in practice, and the subtle variations between them can often drastically change the performance and the resulting objective that is being optimised. In this work, we rigorously explor","authors_text":"Grzegorz Swirszcz, Max Jaderberg, Razvan Pascanu, Siddhant M. Jayakumar, Simon Osindero, Wojciech Marian Czarnecki","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-06T14:01:34Z","title":"Distilling Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02186","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:f0c0a31e8a8369cb6ebd2206783eb18c56ddfc1d191a19518fac89956351bd6c","target":"record","created_at":"2026-05-17T23:54:37Z","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":"be977552585ee0b0b17beb9815cc8f2ad1df36d95df1e492baab341453eae0fc","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-06T14:01:34Z","title_canon_sha256":"b4a0aab9dde30477f83de5594af9e2100a49b858fa6c44965a429f86dff3198b"},"schema_version":"1.0","source":{"id":"1902.02186","kind":"arxiv","version":1}},"canonical_sha256":"2ef93d173ffcf011d0c8c691c72dad3961b88cf7d32486f6fe9313b1246fb186","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ef93d173ffcf011d0c8c691c72dad3961b88cf7d32486f6fe9313b1246fb186","first_computed_at":"2026-05-17T23:54:37.681535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:37.681535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZyivJrF0oTirquX9GtavzXGzwyObZ1tq+EOSsjFnlyHFLcRlStVThCFSS9SlrBAodjOMWL0I4gezYEU2OXXhDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:37.682283Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.02186","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0c0a31e8a8369cb6ebd2206783eb18c56ddfc1d191a19518fac89956351bd6c","sha256:a82f7a6ed4ffa992113fb1cac0b8c58fd173f0f743a836cce5209f0f319a283f"],"state_sha256":"a6973f0f2f53723ad4396465c0b7f3a89c2decd85e4206aa34e33782009f3473"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5gnVZ/zcAIsEqy0bwaXb7B1vmbnsFUORz7JA8FLX1o20kxweUV7UHkCMlEE54BR/Ln5Sa3oHn3uESc9w0EbwCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:38:10.303712Z","bundle_sha256":"61226faf9d5b63cbcabcfa6c9282f03decc627073b04d4afcd5422be2b827741"}}