{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LBLJVDPU5KFHDNEQVHWTFGO3WW","short_pith_number":"pith:LBLJVDPU","schema_version":"1.0","canonical_sha256":"58569a8df4ea8a71b490a9ed3299dbb5a4b6fc9140b4a0cd3ec1f90fbaa95985","source":{"kind":"arxiv","id":"1901.08128","version":2},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1901.08128","created_at":"2026-05-17T23:47:26.468709+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08128v2","created_at":"2026-05-17T23:47:26.468709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08128","created_at":"2026-05-17T23:47:26.468709+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBLJVDPU5KFH","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBLJVDPU5KFHDNEQ","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBLJVDPU","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2407.15134","citing_title":"Proximal Policy Distillation","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13733","citing_title":"Jump-Start Reinforcement Learning with Vision-Language-Action Regularization","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LBLJVDPU5KFHDNEQVHWTFGO3WW","json":"https://pith.science/pith/LBLJVDPU5KFHDNEQVHWTFGO3WW.json","graph_json":"https://pith.science/api/pith-number/LBLJVDPU5KFHDNEQVHWTFGO3WW/graph.json","events_json":"https://pith.science/api/pith-number/LBLJVDPU5KFHDNEQVHWTFGO3WW/events.json","paper":"https://pith.science/paper/LBLJVDPU"},"agent_actions":{"view_html":"https://pith.science/pith/LBLJVDPU5KFHDNEQVHWTFGO3WW","download_json":"https://pith.science/pith/LBLJVDPU5KFHDNEQVHWTFGO3WW.json","view_paper":"https://pith.science/paper/LBLJVDPU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08128&json=true","fetch_graph":"https://pith.science/api/pith-number/LBLJVDPU5KFHDNEQVHWTFGO3WW/graph.json","fetch_events":"https://pith.science/api/pith-number/LBLJVDPU5KFHDNEQVHWTFGO3WW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBLJVDPU5KFHDNEQVHWTFGO3WW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBLJVDPU5KFHDNEQVHWTFGO3WW/action/storage_attestation","attest_author":"https://pith.science/pith/LBLJVDPU5KFHDNEQVHWTFGO3WW/action/author_attestation","sign_citation":"https://pith.science/pith/LBLJVDPU5KFHDNEQVHWTFGO3WW/action/citation_signature","submit_replication":"https://pith.science/pith/LBLJVDPU5KFHDNEQVHWTFGO3WW/action/replication_record"}},"created_at":"2026-05-17T23:47:26.468709+00:00","updated_at":"2026-05-17T23:47:26.468709+00:00"}