{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:P76AIXM2DFNCXVJKZDWA4ZG5CE","short_pith_number":"pith:P76AIXM2","canonical_record":{"source":{"id":"2102.07920","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-16T02:16:54Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"1a7a4704a399803fc51804e6d0bfcac18c4ada08b18593896803650ade26f936","abstract_canon_sha256":"2c313911eb046f4163ec9fe81c67dca4e0d82dfa287d3e9213e4c6e0f0402809"},"schema_version":"1.0"},"canonical_sha256":"7ffc045d9a195a2bd52ac8ec0e64dd111d3bbd883854e1bbd180e9dbea8ae971","source":{"kind":"arxiv","id":"2102.07920","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.07920","created_at":"2026-07-05T02:15:44Z"},{"alias_kind":"arxiv_version","alias_value":"2102.07920v1","created_at":"2026-07-05T02:15:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07920","created_at":"2026-07-05T02:15:44Z"},{"alias_kind":"pith_short_12","alias_value":"P76AIXM2DFNC","created_at":"2026-07-05T02:15:44Z"},{"alias_kind":"pith_short_16","alias_value":"P76AIXM2DFNCXVJK","created_at":"2026-07-05T02:15:44Z"},{"alias_kind":"pith_short_8","alias_value":"P76AIXM2","created_at":"2026-07-05T02:15:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:P76AIXM2DFNCXVJKZDWA4ZG5CE","target":"record","payload":{"canonical_record":{"source":{"id":"2102.07920","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-16T02:16:54Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"1a7a4704a399803fc51804e6d0bfcac18c4ada08b18593896803650ade26f936","abstract_canon_sha256":"2c313911eb046f4163ec9fe81c67dca4e0d82dfa287d3e9213e4c6e0f0402809"},"schema_version":"1.0"},"canonical_sha256":"7ffc045d9a195a2bd52ac8ec0e64dd111d3bbd883854e1bbd180e9dbea8ae971","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:44.636300Z","signature_b64":"rYC7lzdgZWRHTmUO0LgitHXjeHVyv+3CxuXVTKuL3O538Wrp8o2fe25pffZyPF7F7GwiPLkttP8tcwLD4XDcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ffc045d9a195a2bd52ac8ec0e64dd111d3bbd883854e1bbd180e9dbea8ae971","last_reissued_at":"2026-07-05T02:15:44.635901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:44.635901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.07920","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":"2026-07-05T02:15:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GKtQK/lSsd0+lRiYeXs+YPPJg4W5ePIOGFSxf9vJukO7RwCoFX1lOEq2obHJ2J2Z+Eghl9z1BDUc8pDx50dNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:02:35.715399Z"},"content_sha256":"1d36fc399736bb69f7796546c8ac1aa4b74faf84f2cb9be56d4d296cc397d404","schema_version":"1.0","event_id":"sha256:1d36fc399736bb69f7796546c8ac1aa4b74faf84f2cb9be56d4d296cc397d404"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:P76AIXM2DFNCXVJKZDWA4ZG5CE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Larger Networks for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Asako Kanezaki, Devesh K. Jha, Kei Ota","submitted_at":"2021-02-16T02:16:54Z","abstract_excerpt":"The success of deep learning in the computer vision and natural language processing communities can be attributed to training of very deep neural networks with millions or billions of parameters which can then be trained with massive amounts of data. However, similar trend has largely eluded training of deep reinforcement learning (RL) algorithms where larger networks do not lead to performance improvement. Previous work has shown that this is mostly due to instability during training of deep RL agents when using larger networks. In this paper, we make an attempt to understand and address trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07920","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2102.07920/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:15:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r+oj1as5nIu6vxsvfsygEeQUNiP/9ynoYf7xXpZVgk1q0Fg4LOqPtnAvalptg79tM+1ZIcrNbBMhaaBpTs+VBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:02:35.715904Z"},"content_sha256":"56db81d8446112dedfadf9e76cc46154d7e66075223bb685d504a87b6baa9f2e","schema_version":"1.0","event_id":"sha256:56db81d8446112dedfadf9e76cc46154d7e66075223bb685d504a87b6baa9f2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P76AIXM2DFNCXVJKZDWA4ZG5CE/bundle.json","state_url":"https://pith.science/pith/P76AIXM2DFNCXVJKZDWA4ZG5CE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P76AIXM2DFNCXVJKZDWA4ZG5CE/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":"2026-08-04T23:02:35Z","links":{"resolver":"https://pith.science/pith/P76AIXM2DFNCXVJKZDWA4ZG5CE","bundle":"https://pith.science/pith/P76AIXM2DFNCXVJKZDWA4ZG5CE/bundle.json","state":"https://pith.science/pith/P76AIXM2DFNCXVJKZDWA4ZG5CE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P76AIXM2DFNCXVJKZDWA4ZG5CE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:P76AIXM2DFNCXVJKZDWA4ZG5CE","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":"2c313911eb046f4163ec9fe81c67dca4e0d82dfa287d3e9213e4c6e0f0402809","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-16T02:16:54Z","title_canon_sha256":"1a7a4704a399803fc51804e6d0bfcac18c4ada08b18593896803650ade26f936"},"schema_version":"1.0","source":{"id":"2102.07920","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.07920","created_at":"2026-07-05T02:15:44Z"},{"alias_kind":"arxiv_version","alias_value":"2102.07920v1","created_at":"2026-07-05T02:15:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07920","created_at":"2026-07-05T02:15:44Z"},{"alias_kind":"pith_short_12","alias_value":"P76AIXM2DFNC","created_at":"2026-07-05T02:15:44Z"},{"alias_kind":"pith_short_16","alias_value":"P76AIXM2DFNCXVJK","created_at":"2026-07-05T02:15:44Z"},{"alias_kind":"pith_short_8","alias_value":"P76AIXM2","created_at":"2026-07-05T02:15:44Z"}],"graph_snapshots":[{"event_id":"sha256:56db81d8446112dedfadf9e76cc46154d7e66075223bb685d504a87b6baa9f2e","target":"graph","created_at":"2026-07-05T02:15:44Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2102.07920/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of deep learning in the computer vision and natural language processing communities can be attributed to training of very deep neural networks with millions or billions of parameters which can then be trained with massive amounts of data. However, similar trend has largely eluded training of deep reinforcement learning (RL) algorithms where larger networks do not lead to performance improvement. Previous work has shown that this is mostly due to instability during training of deep RL agents when using larger networks. In this paper, we make an attempt to understand and address trai","authors_text":"Asako Kanezaki, Devesh K. Jha, Kei Ota","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-16T02:16:54Z","title":"Training Larger Networks for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07920","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":"sha256:1d36fc399736bb69f7796546c8ac1aa4b74faf84f2cb9be56d4d296cc397d404","target":"record","created_at":"2026-07-05T02:15:44Z","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":"2c313911eb046f4163ec9fe81c67dca4e0d82dfa287d3e9213e4c6e0f0402809","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-16T02:16:54Z","title_canon_sha256":"1a7a4704a399803fc51804e6d0bfcac18c4ada08b18593896803650ade26f936"},"schema_version":"1.0","source":{"id":"2102.07920","kind":"arxiv","version":1}},"canonical_sha256":"7ffc045d9a195a2bd52ac8ec0e64dd111d3bbd883854e1bbd180e9dbea8ae971","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ffc045d9a195a2bd52ac8ec0e64dd111d3bbd883854e1bbd180e9dbea8ae971","first_computed_at":"2026-07-05T02:15:44.635901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:15:44.635901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rYC7lzdgZWRHTmUO0LgitHXjeHVyv+3CxuXVTKuL3O538Wrp8o2fe25pffZyPF7F7GwiPLkttP8tcwLD4XDcAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:15:44.636300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.07920","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d36fc399736bb69f7796546c8ac1aa4b74faf84f2cb9be56d4d296cc397d404","sha256:56db81d8446112dedfadf9e76cc46154d7e66075223bb685d504a87b6baa9f2e"],"state_sha256":"73665cc2e3d2192dccb22b854b5e261daae8265e5f3f3d2a256d733b89153d22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GWpFui+8C3m0hLiU2AXIGh3JM9Fw5mI5sbb+ShjVrxiheqTvJzlOItFPGKPmQCovaJBulgCHsrZwHy2DOSFSAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:02:35.721504Z","bundle_sha256":"bb037c6f627a3dfe29ac65d225ddd3371a80faede699d94d3d6a3b91564aea46"}}