{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:K4XTAVJCGISFTCMHET53YPQ6MQ","short_pith_number":"pith:K4XTAVJC","canonical_record":{"source":{"id":"1801.03138","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-09T20:52:33Z","cross_cats_sorted":[],"title_canon_sha256":"66cbd9db7104f00df1d5552c38d5c1c389552d62579c72ba153d0ad513ffc5e1","abstract_canon_sha256":"ea9018b533bc89a5f13be493f12f846fa7413305820a3598c27a01c7fcfb46ac"},"schema_version":"1.0"},"canonical_sha256":"572f305522322459898724fbbc3e1e641e1de7bd0322235c703afebd7662077a","source":{"kind":"arxiv","id":"1801.03138","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.03138","created_at":"2026-05-18T00:26:18Z"},{"alias_kind":"arxiv_version","alias_value":"1801.03138v1","created_at":"2026-05-18T00:26:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.03138","created_at":"2026-05-18T00:26:18Z"},{"alias_kind":"pith_short_12","alias_value":"K4XTAVJCGISF","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"K4XTAVJCGISFTCMH","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"K4XTAVJC","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:K4XTAVJCGISFTCMHET53YPQ6MQ","target":"record","payload":{"canonical_record":{"source":{"id":"1801.03138","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-09T20:52:33Z","cross_cats_sorted":[],"title_canon_sha256":"66cbd9db7104f00df1d5552c38d5c1c389552d62579c72ba153d0ad513ffc5e1","abstract_canon_sha256":"ea9018b533bc89a5f13be493f12f846fa7413305820a3598c27a01c7fcfb46ac"},"schema_version":"1.0"},"canonical_sha256":"572f305522322459898724fbbc3e1e641e1de7bd0322235c703afebd7662077a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:18.920396Z","signature_b64":"tIjNZbKSzpkNFqnhIROBfcPYUjhkQAjYwwCzs1jKZL4IIlzhwFh4AFRajL/psUj1PJiLtAwC2KTNbZztbez9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"572f305522322459898724fbbc3e1e641e1de7bd0322235c703afebd7662077a","last_reissued_at":"2026-05-18T00:26:18.919391Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:18.919391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.03138","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":"2026-05-18T00:26:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YfzMCHmwugYuInxAl4E++58kWiAIJUUPB74ZCaTr8mgT6mSc8SOs6gonq4uSuoqZKURMXJlrWQVrb2dNR1syBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T03:59:21.342494Z"},"content_sha256":"275d448a63dc3b1cde75900ae9a48e12c41177509364de035254311c331f5cba","schema_version":"1.0","event_id":"sha256:275d448a63dc3b1cde75900ae9a48e12c41177509364de035254311c331f5cba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:K4XTAVJCGISFTCMHET53YPQ6MQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep In-GPU Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ben Parr","submitted_at":"2018-01-09T20:52:33Z","abstract_excerpt":"Experience replay allows a reinforcement learning agent to train on samples from a large amount of the most recent experiences. A simple in-RAM experience replay stores these most recent experiences in a list in RAM, and then copies sampled batches to the GPU for training. I moved this list to the GPU, thus creating an in-GPU experience replay, and a training step that no longer has inputs copied from the CPU. I trained an agent to play Super Smash Bros. Melee, using internal game memory values as inputs and outputting controller button presses. A single state in Melee contains 27 floats, so t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.03138","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":"2026-05-18T00:26:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8DxN7NcNaPuatMZCMVeYajft7yiUZ+WqMhNnL75RmPmTGlW8m1cgEJt19BR16kJTPZqkkRtZwW51rNFX4TGhCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T03:59:21.343167Z"},"content_sha256":"ec2799ef61026193b63810bf5c122f68af6b2f1c1ad5a231c5ba9e432af51abf","schema_version":"1.0","event_id":"sha256:ec2799ef61026193b63810bf5c122f68af6b2f1c1ad5a231c5ba9e432af51abf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K4XTAVJCGISFTCMHET53YPQ6MQ/bundle.json","state_url":"https://pith.science/pith/K4XTAVJCGISFTCMHET53YPQ6MQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K4XTAVJCGISFTCMHET53YPQ6MQ/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":"2026-06-12T03:59:21Z","links":{"resolver":"https://pith.science/pith/K4XTAVJCGISFTCMHET53YPQ6MQ","bundle":"https://pith.science/pith/K4XTAVJCGISFTCMHET53YPQ6MQ/bundle.json","state":"https://pith.science/pith/K4XTAVJCGISFTCMHET53YPQ6MQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K4XTAVJCGISFTCMHET53YPQ6MQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:K4XTAVJCGISFTCMHET53YPQ6MQ","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":"ea9018b533bc89a5f13be493f12f846fa7413305820a3598c27a01c7fcfb46ac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-09T20:52:33Z","title_canon_sha256":"66cbd9db7104f00df1d5552c38d5c1c389552d62579c72ba153d0ad513ffc5e1"},"schema_version":"1.0","source":{"id":"1801.03138","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.03138","created_at":"2026-05-18T00:26:18Z"},{"alias_kind":"arxiv_version","alias_value":"1801.03138v1","created_at":"2026-05-18T00:26:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.03138","created_at":"2026-05-18T00:26:18Z"},{"alias_kind":"pith_short_12","alias_value":"K4XTAVJCGISF","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"K4XTAVJCGISFTCMH","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"K4XTAVJC","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:ec2799ef61026193b63810bf5c122f68af6b2f1c1ad5a231c5ba9e432af51abf","target":"graph","created_at":"2026-05-18T00:26:18Z","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":"Experience replay allows a reinforcement learning agent to train on samples from a large amount of the most recent experiences. A simple in-RAM experience replay stores these most recent experiences in a list in RAM, and then copies sampled batches to the GPU for training. I moved this list to the GPU, thus creating an in-GPU experience replay, and a training step that no longer has inputs copied from the CPU. I trained an agent to play Super Smash Bros. Melee, using internal game memory values as inputs and outputting controller button presses. A single state in Melee contains 27 floats, so t","authors_text":"Ben Parr","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-09T20:52:33Z","title":"Deep In-GPU Experience Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.03138","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":"sha256:275d448a63dc3b1cde75900ae9a48e12c41177509364de035254311c331f5cba","target":"record","created_at":"2026-05-18T00:26:18Z","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":"ea9018b533bc89a5f13be493f12f846fa7413305820a3598c27a01c7fcfb46ac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-09T20:52:33Z","title_canon_sha256":"66cbd9db7104f00df1d5552c38d5c1c389552d62579c72ba153d0ad513ffc5e1"},"schema_version":"1.0","source":{"id":"1801.03138","kind":"arxiv","version":1}},"canonical_sha256":"572f305522322459898724fbbc3e1e641e1de7bd0322235c703afebd7662077a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"572f305522322459898724fbbc3e1e641e1de7bd0322235c703afebd7662077a","first_computed_at":"2026-05-18T00:26:18.919391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:26:18.919391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tIjNZbKSzpkNFqnhIROBfcPYUjhkQAjYwwCzs1jKZL4IIlzhwFh4AFRajL/psUj1PJiLtAwC2KTNbZztbez9Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T00:26:18.920396Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.03138","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:275d448a63dc3b1cde75900ae9a48e12c41177509364de035254311c331f5cba","sha256:ec2799ef61026193b63810bf5c122f68af6b2f1c1ad5a231c5ba9e432af51abf"],"state_sha256":"c7d7ea343d96d32d8c74bcbc693295806f55d0ca258ea236b084764524c6dc9d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8DmRjcDC0p0ZHvnBtln/GzNNkD7HNVQlPKuVmk9AUYLVu/GTypp6H8mqzBfmp80zPXL+jNn5H4rrxH6JOsK2CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T03:59:21.347336Z","bundle_sha256":"2505233e9b0ff2af545df62af677545cd26d04d64d1f476b5db60c43a6cce0e9"}}