{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:LC4QMJWGK5V76W5E5VU6QVNIDE","short_pith_number":"pith:LC4QMJWG","canonical_record":{"source":{"id":"1707.06887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-21T13:21:54Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"168818ce2861f8fec60caf76b63e37c483c4f8fb37d637d01eee4254d35cdffb","abstract_canon_sha256":"37caa04b6e21e14aaf3f437f1f0faf6e239e5c4691a7fc77f62d9886905dd6d3"},"schema_version":"1.0"},"canonical_sha256":"58b90626c6576bff5ba4ed69e855a81929fdc8906a8441fcec0951873ce8ceaf","source":{"kind":"arxiv","id":"1707.06887","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06887","created_at":"2026-05-18T00:39:51Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06887v1","created_at":"2026-05-18T00:39:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06887","created_at":"2026-05-18T00:39:51Z"},{"alias_kind":"pith_short_12","alias_value":"LC4QMJWGK5V7","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LC4QMJWGK5V76W5E","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LC4QMJWG","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:LC4QMJWGK5V76W5E5VU6QVNIDE","target":"record","payload":{"canonical_record":{"source":{"id":"1707.06887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-21T13:21:54Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"168818ce2861f8fec60caf76b63e37c483c4f8fb37d637d01eee4254d35cdffb","abstract_canon_sha256":"37caa04b6e21e14aaf3f437f1f0faf6e239e5c4691a7fc77f62d9886905dd6d3"},"schema_version":"1.0"},"canonical_sha256":"58b90626c6576bff5ba4ed69e855a81929fdc8906a8441fcec0951873ce8ceaf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:51.261884Z","signature_b64":"4yx7/YmxxvLsA5IFod3orAjrJiKeKNupM8h/9iLxDxb0LBGn3fywRw5HeZsmWvqAThmnplPCEJeF/M/xzx5XAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58b90626c6576bff5ba4ed69e855a81929fdc8906a8441fcec0951873ce8ceaf","last_reissued_at":"2026-05-18T00:39:51.261105Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:51.261105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.06887","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":"2026-05-18T00:39:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EQ/FlPROaS8oEro2Y2AU2ZaZ0sixB/SSWKUaZvnzLj80bJ7FQA9MCgyT3sDNMCAiLJYIVTFKK+UOiCHIMBxgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T10:23:12.089095Z"},"content_sha256":"73045921e7ad7089e909c39189975643c9febc199a679f9446f16dfc26758efe","schema_version":"1.0","event_id":"sha256:73045921e7ad7089e909c39189975643c9febc199a679f9446f16dfc26758efe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:LC4QMJWGK5V76W5E5VU6QVNIDE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Distributional Perspective on Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Marc G. Bellemare, R\\'emi Munos, Will Dabney","submitted_at":"2017-07-21T13:21:54Z","abstract_excerpt":"In this paper we argue for the fundamental importance of the value distribution: the distribution of the random return received by a reinforcement learning agent. This is in contrast to the common approach to reinforcement learning which models the expectation of this return, or value. Although there is an established body of literature studying the value distribution, thus far it has always been used for a specific purpose such as implementing risk-aware behaviour. We begin with theoretical results in both the policy evaluation and control settings, exposing a significant distributional insta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06887","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":"2026-05-18T00:39:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y+1Vh/G0QNhtHbjKGuqylfw1ZlsDvNdbv949CFNi+QKTCCTaxJhwdjWwAKjQX41vrjIFghceKO1bHKN9XcRJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T10:23:12.089454Z"},"content_sha256":"6163e4c033214e28eebdd71ead6971a337aef5e0b91bb58a6a111e1b53d5c137","schema_version":"1.0","event_id":"sha256:6163e4c033214e28eebdd71ead6971a337aef5e0b91bb58a6a111e1b53d5c137"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LC4QMJWGK5V76W5E5VU6QVNIDE/bundle.json","state_url":"https://pith.science/pith/LC4QMJWGK5V76W5E5VU6QVNIDE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LC4QMJWGK5V76W5E5VU6QVNIDE/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":"2026-06-11T10:23:12Z","links":{"resolver":"https://pith.science/pith/LC4QMJWGK5V76W5E5VU6QVNIDE","bundle":"https://pith.science/pith/LC4QMJWGK5V76W5E5VU6QVNIDE/bundle.json","state":"https://pith.science/pith/LC4QMJWGK5V76W5E5VU6QVNIDE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LC4QMJWGK5V76W5E5VU6QVNIDE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LC4QMJWGK5V76W5E5VU6QVNIDE","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":"37caa04b6e21e14aaf3f437f1f0faf6e239e5c4691a7fc77f62d9886905dd6d3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-21T13:21:54Z","title_canon_sha256":"168818ce2861f8fec60caf76b63e37c483c4f8fb37d637d01eee4254d35cdffb"},"schema_version":"1.0","source":{"id":"1707.06887","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06887","created_at":"2026-05-18T00:39:51Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06887v1","created_at":"2026-05-18T00:39:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06887","created_at":"2026-05-18T00:39:51Z"},{"alias_kind":"pith_short_12","alias_value":"LC4QMJWGK5V7","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LC4QMJWGK5V76W5E","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LC4QMJWG","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:6163e4c033214e28eebdd71ead6971a337aef5e0b91bb58a6a111e1b53d5c137","target":"graph","created_at":"2026-05-18T00:39:51Z","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":"In this paper we argue for the fundamental importance of the value distribution: the distribution of the random return received by a reinforcement learning agent. This is in contrast to the common approach to reinforcement learning which models the expectation of this return, or value. Although there is an established body of literature studying the value distribution, thus far it has always been used for a specific purpose such as implementing risk-aware behaviour. We begin with theoretical results in both the policy evaluation and control settings, exposing a significant distributional insta","authors_text":"Marc G. Bellemare, R\\'emi Munos, Will Dabney","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-21T13:21:54Z","title":"A Distributional Perspective on Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06887","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":"sha256:73045921e7ad7089e909c39189975643c9febc199a679f9446f16dfc26758efe","target":"record","created_at":"2026-05-18T00:39:51Z","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":"37caa04b6e21e14aaf3f437f1f0faf6e239e5c4691a7fc77f62d9886905dd6d3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-21T13:21:54Z","title_canon_sha256":"168818ce2861f8fec60caf76b63e37c483c4f8fb37d637d01eee4254d35cdffb"},"schema_version":"1.0","source":{"id":"1707.06887","kind":"arxiv","version":1}},"canonical_sha256":"58b90626c6576bff5ba4ed69e855a81929fdc8906a8441fcec0951873ce8ceaf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58b90626c6576bff5ba4ed69e855a81929fdc8906a8441fcec0951873ce8ceaf","first_computed_at":"2026-05-18T00:39:51.261105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:51.261105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4yx7/YmxxvLsA5IFod3orAjrJiKeKNupM8h/9iLxDxb0LBGn3fywRw5HeZsmWvqAThmnplPCEJeF/M/xzx5XAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:51.261884Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.06887","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73045921e7ad7089e909c39189975643c9febc199a679f9446f16dfc26758efe","sha256:6163e4c033214e28eebdd71ead6971a337aef5e0b91bb58a6a111e1b53d5c137"],"state_sha256":"f9257ca162c91bf49e2e166407ce3183bcf378d6f1fe0b71379ae00624bba13b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JVlva1ibFvanBrPOn/QGp58z9MEhEo3CHBw7eAPXVuAJ65rEdUxQwZpS69TLBMGKz7EKFeB6QfcZ4aaNJhAnAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T10:23:12.091395Z","bundle_sha256":"ed066c167fb8f3f3691c1c94fdd11c1dfb26884b1a2a2492b375ffd1f8675bfd"}}