{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WUHFW37IVBM5MZG46RHMO6EAR4","short_pith_number":"pith:WUHFW37I","canonical_record":{"source":{"id":"1904.09489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-20T19:42:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fd633d853db50d1328aaac53dd8e89d7da1abb9f3c88c0dfc7928f2df7d03d8c","abstract_canon_sha256":"dfe42a34d0c5791124e4846a3f094a1dcd637e9cba51f5b4da96df6c7de488bd"},"schema_version":"1.0"},"canonical_sha256":"b50e5b6fe8a859d664dcf44ec778808f1afc193b0333e28a4df4ac45e373db2f","source":{"kind":"arxiv","id":"1904.09489","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09489","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09489v1","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09489","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"pith_short_12","alias_value":"WUHFW37IVBM5","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WUHFW37IVBM5MZG4","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WUHFW37I","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WUHFW37IVBM5MZG46RHMO6EAR4","target":"record","payload":{"canonical_record":{"source":{"id":"1904.09489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-20T19:42:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fd633d853db50d1328aaac53dd8e89d7da1abb9f3c88c0dfc7928f2df7d03d8c","abstract_canon_sha256":"dfe42a34d0c5791124e4846a3f094a1dcd637e9cba51f5b4da96df6c7de488bd"},"schema_version":"1.0"},"canonical_sha256":"b50e5b6fe8a859d664dcf44ec778808f1afc193b0333e28a4df4ac45e373db2f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:04.069675Z","signature_b64":"GqW92GGV97FTttRjgNyy6EDT87ucichbVHqCzRXdMs0A24hF7kACDcQNTVFbj/IV1GqS/Qfg4Y6aPFYEf9ruCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b50e5b6fe8a859d664dcf44ec778808f1afc193b0333e28a4df4ac45e373db2f","last_reissued_at":"2026-05-17T23:48:04.069141Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:04.069141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.09489","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":"2026-05-17T23:48:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p8g9rHRU9Wb/p6+41g1RBTBhQri45s0SeZiVlxpXGxf9HWg5xVxYhw8n8bJuEoQanQyt384eKRg/4bMyV+VdBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T06:24:33.786237Z"},"content_sha256":"dd698b0b038548d96ee2fff5e7d4ad8ae26ffd5f2df541578f86ce96f6c3fd51","schema_version":"1.0","event_id":"sha256:dd698b0b038548d96ee2fff5e7d4ad8ae26ffd5f2df541578f86ce96f6c3fd51"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WUHFW37IVBM5MZG46RHMO6EAR4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compression and Localization in Reinforcement Learning for ATARI Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Barun Patra, Joel Ruben Antony Moniz, Sarthak Garg","submitted_at":"2019-04-20T19:42:50Z","abstract_excerpt":"Deep neural networks have become commonplace in the domain of reinforcement learning, but are often expensive in terms of the number of parameters needed. While compressing deep neural networks has of late assumed great importance to overcome this drawback, little work has been done to address this problem in the context of reinforcement learning agents. This work aims at making first steps towards model compression in an RL agent. In particular, we compress networks to drastically reduce the number of parameters in them (to sizes less than 3% of their original size), further facilitated by ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09489","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":"2026-05-17T23:48:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"56lm4j6rL3yy0scbkZmi+WzbPOOCXmSGzyPOUPLzqXK0tc5yjgo5GVmRiCzVfxC8bLK7aVTc7UUKfiacoKK0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T06:24:33.786605Z"},"content_sha256":"b4d5b8c8942d51677e147f43d5acd1d5a42b982f46893c04e18fee2b366222f2","schema_version":"1.0","event_id":"sha256:b4d5b8c8942d51677e147f43d5acd1d5a42b982f46893c04e18fee2b366222f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WUHFW37IVBM5MZG46RHMO6EAR4/bundle.json","state_url":"https://pith.science/pith/WUHFW37IVBM5MZG46RHMO6EAR4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WUHFW37IVBM5MZG46RHMO6EAR4/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":"2026-06-04T06:24:33Z","links":{"resolver":"https://pith.science/pith/WUHFW37IVBM5MZG46RHMO6EAR4","bundle":"https://pith.science/pith/WUHFW37IVBM5MZG46RHMO6EAR4/bundle.json","state":"https://pith.science/pith/WUHFW37IVBM5MZG46RHMO6EAR4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WUHFW37IVBM5MZG46RHMO6EAR4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WUHFW37IVBM5MZG46RHMO6EAR4","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":"dfe42a34d0c5791124e4846a3f094a1dcd637e9cba51f5b4da96df6c7de488bd","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-20T19:42:50Z","title_canon_sha256":"fd633d853db50d1328aaac53dd8e89d7da1abb9f3c88c0dfc7928f2df7d03d8c"},"schema_version":"1.0","source":{"id":"1904.09489","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09489","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09489v1","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09489","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"pith_short_12","alias_value":"WUHFW37IVBM5","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WUHFW37IVBM5MZG4","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WUHFW37I","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:b4d5b8c8942d51677e147f43d5acd1d5a42b982f46893c04e18fee2b366222f2","target":"graph","created_at":"2026-05-17T23:48:04Z","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"},"paper":{"abstract_excerpt":"Deep neural networks have become commonplace in the domain of reinforcement learning, but are often expensive in terms of the number of parameters needed. While compressing deep neural networks has of late assumed great importance to overcome this drawback, little work has been done to address this problem in the context of reinforcement learning agents. This work aims at making first steps towards model compression in an RL agent. In particular, we compress networks to drastically reduce the number of parameters in them (to sizes less than 3% of their original size), further facilitated by ap","authors_text":"Barun Patra, Joel Ruben Antony Moniz, Sarthak Garg","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-20T19:42:50Z","title":"Compression and Localization in Reinforcement Learning for ATARI Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09489","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:dd698b0b038548d96ee2fff5e7d4ad8ae26ffd5f2df541578f86ce96f6c3fd51","target":"record","created_at":"2026-05-17T23:48:04Z","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":"dfe42a34d0c5791124e4846a3f094a1dcd637e9cba51f5b4da96df6c7de488bd","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-20T19:42:50Z","title_canon_sha256":"fd633d853db50d1328aaac53dd8e89d7da1abb9f3c88c0dfc7928f2df7d03d8c"},"schema_version":"1.0","source":{"id":"1904.09489","kind":"arxiv","version":1}},"canonical_sha256":"b50e5b6fe8a859d664dcf44ec778808f1afc193b0333e28a4df4ac45e373db2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b50e5b6fe8a859d664dcf44ec778808f1afc193b0333e28a4df4ac45e373db2f","first_computed_at":"2026-05-17T23:48:04.069141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:04.069141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GqW92GGV97FTttRjgNyy6EDT87ucichbVHqCzRXdMs0A24hF7kACDcQNTVFbj/IV1GqS/Qfg4Y6aPFYEf9ruCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:04.069675Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.09489","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd698b0b038548d96ee2fff5e7d4ad8ae26ffd5f2df541578f86ce96f6c3fd51","sha256:b4d5b8c8942d51677e147f43d5acd1d5a42b982f46893c04e18fee2b366222f2"],"state_sha256":"85cdd8142d915d4a32d4f5f48dd30a3e9e6eda3846b21395fbef14f6f2ac0bc3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gGaFHdtGKDBZGMBOYCRTAaPRYPmX0qCodIBaBVlzoZcnvC5AH+LNvBb1qM4dFqPXHExtY4ytwLiu/RPki/OOAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T06:24:33.788810Z","bundle_sha256":"1c18eade2d20c477bb46bb02c012e7328626f77c01d610a50b2db1297a976ac9"}}