{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:LBLJVDPU5KFHDNEQVHWTFGO3WW","short_pith_number":"pith:LBLJVDPU","canonical_record":{"source":{"id":"1901.08128","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-23T21:00:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9cd6aa75dccae32e7d84484e3d8ff44efc06952bfee2b9f2673dfb8df071ec34","abstract_canon_sha256":"959ee2bb9bc4afaaced5bc3d00ac66141f8e6c291ac5e15d96f81389d5175f30"},"schema_version":"1.0"},"canonical_sha256":"58569a8df4ea8a71b490a9ed3299dbb5a4b6fc9140b4a0cd3ec1f90fbaa95985","source":{"kind":"arxiv","id":"1901.08128","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08128","created_at":"2026-05-17T23:47:26Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08128v2","created_at":"2026-05-17T23:47:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08128","created_at":"2026-05-17T23:47:26Z"},{"alias_kind":"pith_short_12","alias_value":"LBLJVDPU5KFH","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LBLJVDPU5KFHDNEQ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LBLJVDPU","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:LBLJVDPU5KFHDNEQVHWTFGO3WW","target":"record","payload":{"canonical_record":{"source":{"id":"1901.08128","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-23T21:00:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9cd6aa75dccae32e7d84484e3d8ff44efc06952bfee2b9f2673dfb8df071ec34","abstract_canon_sha256":"959ee2bb9bc4afaaced5bc3d00ac66141f8e6c291ac5e15d96f81389d5175f30"},"schema_version":"1.0"},"canonical_sha256":"58569a8df4ea8a71b490a9ed3299dbb5a4b6fc9140b4a0cd3ec1f90fbaa95985","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:26.469249Z","signature_b64":"SWssjGiM393lY3Drd0u9M2IosDq8/BLB4WgkE9vCMGA0FxDe0NHABIpsvdaJKmGytkTe5xDxcZS+umnxBz2LBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58569a8df4ea8a71b490a9ed3299dbb5a4b6fc9140b4a0cd3ec1f90fbaa95985","last_reissued_at":"2026-05-17T23:47:26.468605Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:26.468605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.08128","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ix7oDSkqOW8wP9pAx5wSD6mM54m0QV3ytOiU+7uZmuiUSRr+t3Vva6rYR4fSo0NyJH1KF4VG/P+Jc4szrvdlBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T03:56:04.354845Z"},"content_sha256":"6f0ad0bc6f9d93d5d1c5ebf2436d541904cbd068ed10bd359327c02d62e95181","schema_version":"1.0","event_id":"sha256:6f0ad0bc6f9d93d5d1c5ebf2436d541904cbd068ed10bd359327c02d62e95181"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:LBLJVDPU5KFHDNEQVHWTFGO3WW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distillation Strategies for Proximal Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"\\c{C}etin Kaya Ko\\c{c}, Craig M. Vineyard, Sam Green","submitted_at":"2019-01-23T21:00:33Z","abstract_excerpt":"Vision-based deep reinforcement learning (RL) typically obtains performance benefit by using high capacity and relatively large convolutional neural networks (CNN). However, a large network leads to higher inference costs (power, latency, silicon area, MAC count). Many inference optimizations have been developed for CNNs. Some optimization techniques offer theoretical efficiency, such as sparsity, but designing actual hardware to support them is difficult. On the other hand, distillation is a simple general-purpose optimization technique which is broadly applicable for transferring knowledge f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08128","kind":"arxiv","version":2},"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":"2026-05-17T23:47:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4xW8OMpnShMu0jlMZIk+eNwGxjAYItEK4BvSnaky2nzVTS+glUhG6cTxrLs5JlxOExbiFU3dwHKYd6VMiq/eAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T03:56:04.355601Z"},"content_sha256":"a70399e68d435892fb9903bb08c6788756ef10d5dfa2e4b6fc9a707dc23575cc","schema_version":"1.0","event_id":"sha256:a70399e68d435892fb9903bb08c6788756ef10d5dfa2e4b6fc9a707dc23575cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LBLJVDPU5KFHDNEQVHWTFGO3WW/bundle.json","state_url":"https://pith.science/pith/LBLJVDPU5KFHDNEQVHWTFGO3WW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LBLJVDPU5KFHDNEQVHWTFGO3WW/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":"2026-06-06T03:56:04Z","links":{"resolver":"https://pith.science/pith/LBLJVDPU5KFHDNEQVHWTFGO3WW","bundle":"https://pith.science/pith/LBLJVDPU5KFHDNEQVHWTFGO3WW/bundle.json","state":"https://pith.science/pith/LBLJVDPU5KFHDNEQVHWTFGO3WW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LBLJVDPU5KFHDNEQVHWTFGO3WW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:LBLJVDPU5KFHDNEQVHWTFGO3WW","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":"959ee2bb9bc4afaaced5bc3d00ac66141f8e6c291ac5e15d96f81389d5175f30","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-23T21:00:33Z","title_canon_sha256":"9cd6aa75dccae32e7d84484e3d8ff44efc06952bfee2b9f2673dfb8df071ec34"},"schema_version":"1.0","source":{"id":"1901.08128","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08128","created_at":"2026-05-17T23:47:26Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08128v2","created_at":"2026-05-17T23:47:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08128","created_at":"2026-05-17T23:47:26Z"},{"alias_kind":"pith_short_12","alias_value":"LBLJVDPU5KFH","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LBLJVDPU5KFHDNEQ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LBLJVDPU","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:a70399e68d435892fb9903bb08c6788756ef10d5dfa2e4b6fc9a707dc23575cc","target":"graph","created_at":"2026-05-17T23:47:26Z","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":"Vision-based deep reinforcement learning (RL) typically obtains performance benefit by using high capacity and relatively large convolutional neural networks (CNN). However, a large network leads to higher inference costs (power, latency, silicon area, MAC count). Many inference optimizations have been developed for CNNs. Some optimization techniques offer theoretical efficiency, such as sparsity, but designing actual hardware to support them is difficult. On the other hand, distillation is a simple general-purpose optimization technique which is broadly applicable for transferring knowledge f","authors_text":"\\c{C}etin Kaya Ko\\c{c}, Craig M. Vineyard, Sam Green","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-23T21:00:33Z","title":"Distillation Strategies for Proximal Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08128","kind":"arxiv","version":2},"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":"sha256:6f0ad0bc6f9d93d5d1c5ebf2436d541904cbd068ed10bd359327c02d62e95181","target":"record","created_at":"2026-05-17T23:47:26Z","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":"959ee2bb9bc4afaaced5bc3d00ac66141f8e6c291ac5e15d96f81389d5175f30","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-23T21:00:33Z","title_canon_sha256":"9cd6aa75dccae32e7d84484e3d8ff44efc06952bfee2b9f2673dfb8df071ec34"},"schema_version":"1.0","source":{"id":"1901.08128","kind":"arxiv","version":2}},"canonical_sha256":"58569a8df4ea8a71b490a9ed3299dbb5a4b6fc9140b4a0cd3ec1f90fbaa95985","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58569a8df4ea8a71b490a9ed3299dbb5a4b6fc9140b4a0cd3ec1f90fbaa95985","first_computed_at":"2026-05-17T23:47:26.468605Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:26.468605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SWssjGiM393lY3Drd0u9M2IosDq8/BLB4WgkE9vCMGA0FxDe0NHABIpsvdaJKmGytkTe5xDxcZS+umnxBz2LBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:26.469249Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.08128","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f0ad0bc6f9d93d5d1c5ebf2436d541904cbd068ed10bd359327c02d62e95181","sha256:a70399e68d435892fb9903bb08c6788756ef10d5dfa2e4b6fc9a707dc23575cc"],"state_sha256":"9868dd84775cbbe0cffc8bb2524192ac3b2220efbebfe1329cd8805464ad7ac9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/UkHBdg6P9XXQfIuyHjwqB8lH6s8VAhrXfGQg1H8Us+Ib2exUjTy7EO9KkNBMHw1bm1nrGo1gIz7vMF+ScEiAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T03:56:04.359599Z","bundle_sha256":"4a50802cb8ef8015874fdb2568ff9d3b561ecc381d447558038bc11392d6ac05"}}