{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:NVVW6T56EHE5N35KYFCWV6EPP5","short_pith_number":"pith:NVVW6T56","canonical_record":{"source":{"id":"1611.01224","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-03T23:21:32Z","cross_cats_sorted":[],"title_canon_sha256":"ca86845ee927407972dabed2e1c87170159b278f44e47823546311482b728fc6","abstract_canon_sha256":"018d747ef51633e94c6124f86a1aa11e6eb4cb9f33e5ee5b6967fcb8ed97eec1"},"schema_version":"1.0"},"canonical_sha256":"6d6b6f4fbe21c9d6efaac1456af88f7f50b1ca7f52bb39e9997221faf1e4c389","source":{"kind":"arxiv","id":"1611.01224","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01224","created_at":"2026-05-18T00:40:40Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01224v2","created_at":"2026-05-18T00:40:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01224","created_at":"2026-05-18T00:40:40Z"},{"alias_kind":"pith_short_12","alias_value":"NVVW6T56EHE5","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"NVVW6T56EHE5N35K","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"NVVW6T56","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:NVVW6T56EHE5N35KYFCWV6EPP5","target":"record","payload":{"canonical_record":{"source":{"id":"1611.01224","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-03T23:21:32Z","cross_cats_sorted":[],"title_canon_sha256":"ca86845ee927407972dabed2e1c87170159b278f44e47823546311482b728fc6","abstract_canon_sha256":"018d747ef51633e94c6124f86a1aa11e6eb4cb9f33e5ee5b6967fcb8ed97eec1"},"schema_version":"1.0"},"canonical_sha256":"6d6b6f4fbe21c9d6efaac1456af88f7f50b1ca7f52bb39e9997221faf1e4c389","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:40.902714Z","signature_b64":"IdvSoebttrE2MLP2hdeMWSrJPv/Oc1TPkXzn+OGyk1hH4H/hxUSft42CrIgoti6IJD2vhGDC6ZicAY1b+/vCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d6b6f4fbe21c9d6efaac1456af88f7f50b1ca7f52bb39e9997221faf1e4c389","last_reissued_at":"2026-05-18T00:40:40.901919Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:40.901919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.01224","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":"2026-05-18T00:40:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sfC7MOyaAV1zz4w68PPIOcPq8Rd8/EqV5vD+R748ewlfxZ1ZjW+9jW8k6mVpIGNtB0UZclXx2G8iD9OdsvkZDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T02:01:20.906799Z"},"content_sha256":"d9ebbba64df8ddfc5ff408edbf37113a8e0ba7dbb95b018d5e3ec1881f7d6e99","schema_version":"1.0","event_id":"sha256:d9ebbba64df8ddfc5ff408edbf37113a8e0ba7dbb95b018d5e3ec1881f7d6e99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:NVVW6T56EHE5N35KYFCWV6EPP5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample Efficient Actor-Critic with Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Koray Kavukcuoglu, Nando de Freitas, Nicolas Heess, Remi Munos, Victor Bapst, Volodymyr Mnih, Ziyu Wang","submitted_at":"2016-11-03T23:21:32Z","abstract_excerpt":"This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the discrete 57-game Atari domain and several continuous control problems. To achieve this, the paper introduces several innovations, including truncated importance sampling with bias correction, stochastic dueling network architectures, and a new trust region policy optimization method."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01224","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":"2026-05-18T00:40:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mouVFPG45grTBKWemawUcfADJZx/RvS69PNPgBdVW5MfBJr2vzrm2G9z04TnmtL7fMtK3Yyhk4mQkVSteXaiBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T02:01:20.907524Z"},"content_sha256":"7a898d3fba5904c3e9deda86e2ec218c29665b03667e5cf55fdfcb4b1b261dbb","schema_version":"1.0","event_id":"sha256:7a898d3fba5904c3e9deda86e2ec218c29665b03667e5cf55fdfcb4b1b261dbb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NVVW6T56EHE5N35KYFCWV6EPP5/bundle.json","state_url":"https://pith.science/pith/NVVW6T56EHE5N35KYFCWV6EPP5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NVVW6T56EHE5N35KYFCWV6EPP5/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":"2026-06-07T02:01:20Z","links":{"resolver":"https://pith.science/pith/NVVW6T56EHE5N35KYFCWV6EPP5","bundle":"https://pith.science/pith/NVVW6T56EHE5N35KYFCWV6EPP5/bundle.json","state":"https://pith.science/pith/NVVW6T56EHE5N35KYFCWV6EPP5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NVVW6T56EHE5N35KYFCWV6EPP5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:NVVW6T56EHE5N35KYFCWV6EPP5","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":"018d747ef51633e94c6124f86a1aa11e6eb4cb9f33e5ee5b6967fcb8ed97eec1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-03T23:21:32Z","title_canon_sha256":"ca86845ee927407972dabed2e1c87170159b278f44e47823546311482b728fc6"},"schema_version":"1.0","source":{"id":"1611.01224","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01224","created_at":"2026-05-18T00:40:40Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01224v2","created_at":"2026-05-18T00:40:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01224","created_at":"2026-05-18T00:40:40Z"},{"alias_kind":"pith_short_12","alias_value":"NVVW6T56EHE5","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"NVVW6T56EHE5N35K","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"NVVW6T56","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:7a898d3fba5904c3e9deda86e2ec218c29665b03667e5cf55fdfcb4b1b261dbb","target":"graph","created_at":"2026-05-18T00:40:40Z","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":"This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the discrete 57-game Atari domain and several continuous control problems. To achieve this, the paper introduces several innovations, including truncated importance sampling with bias correction, stochastic dueling network architectures, and a new trust region policy optimization method.","authors_text":"Koray Kavukcuoglu, Nando de Freitas, Nicolas Heess, Remi Munos, Victor Bapst, Volodymyr Mnih, Ziyu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-03T23:21:32Z","title":"Sample Efficient Actor-Critic with Experience Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01224","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:d9ebbba64df8ddfc5ff408edbf37113a8e0ba7dbb95b018d5e3ec1881f7d6e99","target":"record","created_at":"2026-05-18T00:40:40Z","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":"018d747ef51633e94c6124f86a1aa11e6eb4cb9f33e5ee5b6967fcb8ed97eec1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-03T23:21:32Z","title_canon_sha256":"ca86845ee927407972dabed2e1c87170159b278f44e47823546311482b728fc6"},"schema_version":"1.0","source":{"id":"1611.01224","kind":"arxiv","version":2}},"canonical_sha256":"6d6b6f4fbe21c9d6efaac1456af88f7f50b1ca7f52bb39e9997221faf1e4c389","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d6b6f4fbe21c9d6efaac1456af88f7f50b1ca7f52bb39e9997221faf1e4c389","first_computed_at":"2026-05-18T00:40:40.901919Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:40.901919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IdvSoebttrE2MLP2hdeMWSrJPv/Oc1TPkXzn+OGyk1hH4H/hxUSft42CrIgoti6IJD2vhGDC6ZicAY1b+/vCAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:40.902714Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.01224","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9ebbba64df8ddfc5ff408edbf37113a8e0ba7dbb95b018d5e3ec1881f7d6e99","sha256:7a898d3fba5904c3e9deda86e2ec218c29665b03667e5cf55fdfcb4b1b261dbb"],"state_sha256":"9dbb04d08b67607929abdd486978099af763644f7d86bc352e52d52eddbf1453"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ChTESz4tbSiMyXnuxDGM6mh5zT7+zVXNvGibZpnIYLkqH5f0eE5deBH7EF6yXX0x/lkdKoFTu1WwTUiJriSPCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T02:01:20.910539Z","bundle_sha256":"19638de6caed2e90bf03660c1657c503c7853c6f665254ab1439a67d27e0a388"}}