{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PFXWRAG4CUZGU7A47XBJBR2HE3","short_pith_number":"pith:PFXWRAG4","canonical_record":{"source":{"id":"2306.07124","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T13:59:48Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"65743b502a1f9bfc66ac04aea28ee3febfc7f03ec03018941237d42e8b7cfa91","abstract_canon_sha256":"db61199ba6257021eb89c7f5097359f151b04e7d219a66169a9ecf4c7832be58"},"schema_version":"1.0"},"canonical_sha256":"796f6880dc15326a7c1cfdc290c74726d52d19bc092f58f36711c4cc76d064f3","source":{"kind":"arxiv","id":"2306.07124","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07124","created_at":"2026-07-05T10:31:21Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07124v2","created_at":"2026-07-05T10:31:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07124","created_at":"2026-07-05T10:31:21Z"},{"alias_kind":"pith_short_12","alias_value":"PFXWRAG4CUZG","created_at":"2026-07-05T10:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"PFXWRAG4CUZGU7A4","created_at":"2026-07-05T10:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"PFXWRAG4","created_at":"2026-07-05T10:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PFXWRAG4CUZGU7A47XBJBR2HE3","target":"record","payload":{"canonical_record":{"source":{"id":"2306.07124","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T13:59:48Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"65743b502a1f9bfc66ac04aea28ee3febfc7f03ec03018941237d42e8b7cfa91","abstract_canon_sha256":"db61199ba6257021eb89c7f5097359f151b04e7d219a66169a9ecf4c7832be58"},"schema_version":"1.0"},"canonical_sha256":"796f6880dc15326a7c1cfdc290c74726d52d19bc092f58f36711c4cc76d064f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:21.673281Z","signature_b64":"sSdHE9ByxsHQA5Lai6CeGhWH5+VrQvBtcIyNlYCQi8sKOCeNlbIdm+fctLjvndWLLFQmMhq2ncDmx6/NM0QGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"796f6880dc15326a7c1cfdc290c74726d52d19bc092f58f36711c4cc76d064f3","last_reissued_at":"2026-07-05T10:31:21.672660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:21.672660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.07124","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":"2026-07-05T10:31:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KDlmYrPAFEd08TvzSDzcOVCf0VTJDKvQarS3g6h7uePV4GFll5dXCvmRAFl43IyDMh3vS4UOASQONEdwLt8wDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:33:06.149785Z"},"content_sha256":"df3333f28e276f875b150248a6f6a060eb41ecaaab5100d5bcf6b4eab245383c","schema_version":"1.0","event_id":"sha256:df3333f28e276f875b150248a6f6a060eb41ecaaab5100d5bcf6b4eab245383c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PFXWRAG4CUZGU7A47XBJBR2HE3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diverse Projection Ensembles for Distributional Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthijs T. J. Spaan, Moritz A. Zanger, Wendelin B\\\"ohmer","submitted_at":"2023-06-12T13:59:48Z","abstract_excerpt":"In contrast to classical reinforcement learning (RL), distributional RL algorithms aim to learn the distribution of returns rather than their expected value. Since the nature of the return distribution is generally unknown a priori or arbitrarily complex, a common approach finds approximations within a set of representable, parametric distributions. Typically, this involves a projection of the unconstrained distribution onto the set of simplified distributions. We argue that this projection step entails a strong inductive bias when coupled with neural networks and gradient descent, thereby pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07124","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.07124/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":"2026-07-05T10:31:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fGBoVFp8fkVj0tIkMQxJbCEixMG/b8tKBK3cuO86SU93n8ZJVPgk8p44Hi5hmUzpnybzQrEnhld+k6sEPPioAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:33:06.150161Z"},"content_sha256":"6aaa04ce7e0e50293ba954a8295cd0f94a60ab9fe8be07da6b71b046065a744a","schema_version":"1.0","event_id":"sha256:6aaa04ce7e0e50293ba954a8295cd0f94a60ab9fe8be07da6b71b046065a744a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PFXWRAG4CUZGU7A47XBJBR2HE3/bundle.json","state_url":"https://pith.science/pith/PFXWRAG4CUZGU7A47XBJBR2HE3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PFXWRAG4CUZGU7A47XBJBR2HE3/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":"2026-07-06T19:33:06Z","links":{"resolver":"https://pith.science/pith/PFXWRAG4CUZGU7A47XBJBR2HE3","bundle":"https://pith.science/pith/PFXWRAG4CUZGU7A47XBJBR2HE3/bundle.json","state":"https://pith.science/pith/PFXWRAG4CUZGU7A47XBJBR2HE3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PFXWRAG4CUZGU7A47XBJBR2HE3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PFXWRAG4CUZGU7A47XBJBR2HE3","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":"db61199ba6257021eb89c7f5097359f151b04e7d219a66169a9ecf4c7832be58","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T13:59:48Z","title_canon_sha256":"65743b502a1f9bfc66ac04aea28ee3febfc7f03ec03018941237d42e8b7cfa91"},"schema_version":"1.0","source":{"id":"2306.07124","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07124","created_at":"2026-07-05T10:31:21Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07124v2","created_at":"2026-07-05T10:31:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07124","created_at":"2026-07-05T10:31:21Z"},{"alias_kind":"pith_short_12","alias_value":"PFXWRAG4CUZG","created_at":"2026-07-05T10:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"PFXWRAG4CUZGU7A4","created_at":"2026-07-05T10:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"PFXWRAG4","created_at":"2026-07-05T10:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:6aaa04ce7e0e50293ba954a8295cd0f94a60ab9fe8be07da6b71b046065a744a","target":"graph","created_at":"2026-07-05T10:31:21Z","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/2306.07124/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In contrast to classical reinforcement learning (RL), distributional RL algorithms aim to learn the distribution of returns rather than their expected value. Since the nature of the return distribution is generally unknown a priori or arbitrarily complex, a common approach finds approximations within a set of representable, parametric distributions. Typically, this involves a projection of the unconstrained distribution onto the set of simplified distributions. We argue that this projection step entails a strong inductive bias when coupled with neural networks and gradient descent, thereby pro","authors_text":"Matthijs T. J. Spaan, Moritz A. Zanger, Wendelin B\\\"ohmer","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T13:59:48Z","title":"Diverse Projection Ensembles for Distributional Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07124","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:df3333f28e276f875b150248a6f6a060eb41ecaaab5100d5bcf6b4eab245383c","target":"record","created_at":"2026-07-05T10:31:21Z","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":"db61199ba6257021eb89c7f5097359f151b04e7d219a66169a9ecf4c7832be58","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T13:59:48Z","title_canon_sha256":"65743b502a1f9bfc66ac04aea28ee3febfc7f03ec03018941237d42e8b7cfa91"},"schema_version":"1.0","source":{"id":"2306.07124","kind":"arxiv","version":2}},"canonical_sha256":"796f6880dc15326a7c1cfdc290c74726d52d19bc092f58f36711c4cc76d064f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"796f6880dc15326a7c1cfdc290c74726d52d19bc092f58f36711c4cc76d064f3","first_computed_at":"2026-07-05T10:31:21.672660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:21.672660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sSdHE9ByxsHQA5Lai6CeGhWH5+VrQvBtcIyNlYCQi8sKOCeNlbIdm+fctLjvndWLLFQmMhq2ncDmx6/NM0QGDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:21.673281Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07124","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df3333f28e276f875b150248a6f6a060eb41ecaaab5100d5bcf6b4eab245383c","sha256:6aaa04ce7e0e50293ba954a8295cd0f94a60ab9fe8be07da6b71b046065a744a"],"state_sha256":"f46843bc0c8404b7f00458f9ccd19dacb1749fdc221334f48713e206f39c203b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gn7u4wYwjkAoBTIgBjsenOIst8gloqPtpu/vo6ZlvEG4yt+mNdvHaU65bByIFt5jUatNwdNx+H4CPDYeLVK6CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:33:06.152112Z","bundle_sha256":"24d1556fb330762e6fea2e8760554c23f7c0f8fc44b8e6f0bf1789fd13aff945"}}