{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZSOUND2R3EWDGJ7ZDO3PBQ2HZG","short_pith_number":"pith:ZSOUND2R","canonical_record":{"source":{"id":"1904.03367","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-06T05:42:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"72fdf922f2840e0458de1d71f583a6d210eab81687d2a6811d52d2b6e3e2b979","abstract_canon_sha256":"03a7de34b3b2a92f2b46461a8074ed00b42ea03116b25a3f3fe726c0a27ca44f"},"schema_version":"1.0"},"canonical_sha256":"cc9d468f51d92c3327f91bb6f0c347c98da83078be340dbb97935fcfffa06801","source":{"kind":"arxiv","id":"1904.03367","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03367","created_at":"2026-05-17T23:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03367v1","created_at":"2026-05-17T23:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03367","created_at":"2026-05-17T23:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"ZSOUND2R3EWD","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZSOUND2R3EWDGJ7Z","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZSOUND2R","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZSOUND2R3EWDGJ7ZDO3PBQ2HZG","target":"record","payload":{"canonical_record":{"source":{"id":"1904.03367","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-06T05:42:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"72fdf922f2840e0458de1d71f583a6d210eab81687d2a6811d52d2b6e3e2b979","abstract_canon_sha256":"03a7de34b3b2a92f2b46461a8074ed00b42ea03116b25a3f3fe726c0a27ca44f"},"schema_version":"1.0"},"canonical_sha256":"cc9d468f51d92c3327f91bb6f0c347c98da83078be340dbb97935fcfffa06801","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:13.696882Z","signature_b64":"I92mKlMVliTLYvd6B4KjN6fiMSfPydK/lkdXig2bAw3XmC1Z3UHiZOeVsQkowJUGRyFplsuiosDFfVcxBbE2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc9d468f51d92c3327f91bb6f0c347c98da83078be340dbb97935fcfffa06801","last_reissued_at":"2026-05-17T23:49:13.696345Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:13.696345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.03367","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":"2026-05-17T23:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SdntO9KW6i90F7u4NLn9z0tQmtVChUGzwJQZ9a+NTV9XB9cY3MmTKFJlplvkyJQtaq+Lxsbp+e12vlzXKmq7Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T16:59:23.988477Z"},"content_sha256":"a8653c1bfd503749961e342c63c453785822c4ddbccad763f495ea0bbeb40236","schema_version":"1.0","event_id":"sha256:a8653c1bfd503749961e342c63c453785822c4ddbccad763f495ea0bbeb40236"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZSOUND2R3EWDGJ7ZDO3PBQ2HZG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Attention that Works: A Self-Supervised Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anthony Manchin, Anton van den Hengel, Ehsan Abbasnejad","submitted_at":"2019-04-06T05:42:43Z","abstract_excerpt":"Attention models have had a significant positive impact on deep learning across a range of tasks. However previous attempts at integrating attention with reinforcement learning have failed to produce significant improvements. We propose the first combination of self attention and reinforcement learning that is capable of producing significant improvements, including new state of the art results in the Arcade Learning Environment. Unlike the selective attention models used in previous attempts, which constrain the attention via preconceived notions of importance, our implementation utilises the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03367","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":"2026-05-17T23:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w1o75wMmTwjnTtwd2s3ywWVjEnt5+5Mu7+bkfZZVc4Gqqcd4tZW6CO1VuX7Zjtm2eT5Rkcf4fqKepazem5SrDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T16:59:23.988825Z"},"content_sha256":"f5adf6baebf3fdd965003329aa54c27e0ac2994595cff4498b87af08ff9a5dbe","schema_version":"1.0","event_id":"sha256:f5adf6baebf3fdd965003329aa54c27e0ac2994595cff4498b87af08ff9a5dbe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZSOUND2R3EWDGJ7ZDO3PBQ2HZG/bundle.json","state_url":"https://pith.science/pith/ZSOUND2R3EWDGJ7ZDO3PBQ2HZG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZSOUND2R3EWDGJ7ZDO3PBQ2HZG/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":"2026-06-04T16:59:23Z","links":{"resolver":"https://pith.science/pith/ZSOUND2R3EWDGJ7ZDO3PBQ2HZG","bundle":"https://pith.science/pith/ZSOUND2R3EWDGJ7ZDO3PBQ2HZG/bundle.json","state":"https://pith.science/pith/ZSOUND2R3EWDGJ7ZDO3PBQ2HZG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZSOUND2R3EWDGJ7ZDO3PBQ2HZG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZSOUND2R3EWDGJ7ZDO3PBQ2HZG","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":"03a7de34b3b2a92f2b46461a8074ed00b42ea03116b25a3f3fe726c0a27ca44f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-06T05:42:43Z","title_canon_sha256":"72fdf922f2840e0458de1d71f583a6d210eab81687d2a6811d52d2b6e3e2b979"},"schema_version":"1.0","source":{"id":"1904.03367","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03367","created_at":"2026-05-17T23:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03367v1","created_at":"2026-05-17T23:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03367","created_at":"2026-05-17T23:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"ZSOUND2R3EWD","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZSOUND2R3EWDGJ7Z","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZSOUND2R","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:f5adf6baebf3fdd965003329aa54c27e0ac2994595cff4498b87af08ff9a5dbe","target":"graph","created_at":"2026-05-17T23:49:13Z","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":"Attention models have had a significant positive impact on deep learning across a range of tasks. However previous attempts at integrating attention with reinforcement learning have failed to produce significant improvements. We propose the first combination of self attention and reinforcement learning that is capable of producing significant improvements, including new state of the art results in the Arcade Learning Environment. Unlike the selective attention models used in previous attempts, which constrain the attention via preconceived notions of importance, our implementation utilises the","authors_text":"Anthony Manchin, Anton van den Hengel, Ehsan Abbasnejad","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-06T05:42:43Z","title":"Reinforcement Learning with Attention that Works: A Self-Supervised Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03367","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:a8653c1bfd503749961e342c63c453785822c4ddbccad763f495ea0bbeb40236","target":"record","created_at":"2026-05-17T23:49:13Z","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":"03a7de34b3b2a92f2b46461a8074ed00b42ea03116b25a3f3fe726c0a27ca44f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-06T05:42:43Z","title_canon_sha256":"72fdf922f2840e0458de1d71f583a6d210eab81687d2a6811d52d2b6e3e2b979"},"schema_version":"1.0","source":{"id":"1904.03367","kind":"arxiv","version":1}},"canonical_sha256":"cc9d468f51d92c3327f91bb6f0c347c98da83078be340dbb97935fcfffa06801","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc9d468f51d92c3327f91bb6f0c347c98da83078be340dbb97935fcfffa06801","first_computed_at":"2026-05-17T23:49:13.696345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:13.696345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I92mKlMVliTLYvd6B4KjN6fiMSfPydK/lkdXig2bAw3XmC1Z3UHiZOeVsQkowJUGRyFplsuiosDFfVcxBbE2BQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:13.696882Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.03367","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8653c1bfd503749961e342c63c453785822c4ddbccad763f495ea0bbeb40236","sha256:f5adf6baebf3fdd965003329aa54c27e0ac2994595cff4498b87af08ff9a5dbe"],"state_sha256":"afc48d9f998b252e547a89fc90fa7078d6a2e21cbc9c89c0b95bd17025bf1276"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZvjLgr+REHRz7bSHWOM8OUERv0K4FlcTqJ+4ExvJT42+fc77Fk3TyS3H1tpahFBQufyMd74eCWnrvS820/O0Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T16:59:23.990930Z","bundle_sha256":"2bebdc2b534aca08e57db7510d078a0aad2607a416ea8d00ac21cf96af3792f8"}}