{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZKQY6N227AHLZ6GOAPJTWYUA3W","short_pith_number":"pith:ZKQY6N22","canonical_record":{"source":{"id":"2312.01203","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-02T18:55:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c09f43c78c06deeddf52ffa479456f307e4121951ac65cba21dcf7242ff35b0a","abstract_canon_sha256":"9395c2411ac98f030f4a1b6b6474ca738d18b171f78fae6ec387f98a2e2632a0"},"schema_version":"1.0"},"canonical_sha256":"caa18f375af80ebcf8ce03d33b6280dd9bc821903085747b1fa10de207c90bc6","source":{"kind":"arxiv","id":"2312.01203","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01203","created_at":"2026-07-05T08:43:24Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01203v3","created_at":"2026-07-05T08:43:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01203","created_at":"2026-07-05T08:43:24Z"},{"alias_kind":"pith_short_12","alias_value":"ZKQY6N227AHL","created_at":"2026-07-05T08:43:24Z"},{"alias_kind":"pith_short_16","alias_value":"ZKQY6N227AHLZ6GO","created_at":"2026-07-05T08:43:24Z"},{"alias_kind":"pith_short_8","alias_value":"ZKQY6N22","created_at":"2026-07-05T08:43:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZKQY6N227AHLZ6GOAPJTWYUA3W","target":"record","payload":{"canonical_record":{"source":{"id":"2312.01203","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-02T18:55:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c09f43c78c06deeddf52ffa479456f307e4121951ac65cba21dcf7242ff35b0a","abstract_canon_sha256":"9395c2411ac98f030f4a1b6b6474ca738d18b171f78fae6ec387f98a2e2632a0"},"schema_version":"1.0"},"canonical_sha256":"caa18f375af80ebcf8ce03d33b6280dd9bc821903085747b1fa10de207c90bc6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:24.602030Z","signature_b64":"No13yYkX6bU8xyEfe8FR3NM43CzKoxVf1uuUB/V3aWLJP6i3pJrMY7utaYBA8z8/t3ZdBarzgpPyniLohJ9SDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caa18f375af80ebcf8ce03d33b6280dd9bc821903085747b1fa10de207c90bc6","last_reissued_at":"2026-07-05T08:43:24.601564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:24.601564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.01203","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:43:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FZF0vHitU2lIOqdrqzHkkfD3I9chHo6YlmNCYw9dqy3l8imsRVogLWLHeuUDHQteJGH+hODE8uwNGAm71zAoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T21:52:18.494276Z"},"content_sha256":"543cb87608486335b6cc96a4ecc4b808a302ae8c32fc470b872cbc140a4693a1","schema_version":"1.0","event_id":"sha256:543cb87608486335b6cc96a4ecc4b808a302ae8c32fc470b872cbc140a4693a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZKQY6N227AHLZ6GOAPJTWYUA3W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Harnessing Discrete Representations For Continual Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam White, Edan Meyer, Marlos C. Machado","submitted_at":"2023-12-02T18:55:26Z","abstract_excerpt":"Reinforcement learning (RL) agents make decisions using nothing but observations from the environment, and consequently, heavily rely on the representations of those observations. Though some recent breakthroughs have used vector-based categorical representations of observations, often referred to as discrete representations, there is little work explicitly assessing the significance of such a choice. In this work, we provide a thorough empirical investigation of the advantages of representing observations as vectors of categorical values within the context of reinforcement learning. We perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01203","kind":"arxiv","version":3},"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/2312.01203/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":"2026-07-05T08:43:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h1TOO80LFJSlycO0kZGrnJVJm6s5cGOKAcn38LUZCJOd5Kq0PdTXScqr7waTtfE1E8wN/iYr5Hqv24FaJqfZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T21:52:18.494970Z"},"content_sha256":"973ffd412f120f1b185cb8055a1b0f5ece4075487e051b5cfef252eb02a88a34","schema_version":"1.0","event_id":"sha256:973ffd412f120f1b185cb8055a1b0f5ece4075487e051b5cfef252eb02a88a34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZKQY6N227AHLZ6GOAPJTWYUA3W/bundle.json","state_url":"https://pith.science/pith/ZKQY6N227AHLZ6GOAPJTWYUA3W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZKQY6N227AHLZ6GOAPJTWYUA3W/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":"2026-08-23T21:52:18Z","links":{"resolver":"https://pith.science/pith/ZKQY6N227AHLZ6GOAPJTWYUA3W","bundle":"https://pith.science/pith/ZKQY6N227AHLZ6GOAPJTWYUA3W/bundle.json","state":"https://pith.science/pith/ZKQY6N227AHLZ6GOAPJTWYUA3W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZKQY6N227AHLZ6GOAPJTWYUA3W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZKQY6N227AHLZ6GOAPJTWYUA3W","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":"9395c2411ac98f030f4a1b6b6474ca738d18b171f78fae6ec387f98a2e2632a0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-02T18:55:26Z","title_canon_sha256":"c09f43c78c06deeddf52ffa479456f307e4121951ac65cba21dcf7242ff35b0a"},"schema_version":"1.0","source":{"id":"2312.01203","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01203","created_at":"2026-07-05T08:43:24Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01203v3","created_at":"2026-07-05T08:43:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01203","created_at":"2026-07-05T08:43:24Z"},{"alias_kind":"pith_short_12","alias_value":"ZKQY6N227AHL","created_at":"2026-07-05T08:43:24Z"},{"alias_kind":"pith_short_16","alias_value":"ZKQY6N227AHLZ6GO","created_at":"2026-07-05T08:43:24Z"},{"alias_kind":"pith_short_8","alias_value":"ZKQY6N22","created_at":"2026-07-05T08:43:24Z"}],"graph_snapshots":[{"event_id":"sha256:973ffd412f120f1b185cb8055a1b0f5ece4075487e051b5cfef252eb02a88a34","target":"graph","created_at":"2026-07-05T08:43:24Z","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/2312.01203/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) agents make decisions using nothing but observations from the environment, and consequently, heavily rely on the representations of those observations. Though some recent breakthroughs have used vector-based categorical representations of observations, often referred to as discrete representations, there is little work explicitly assessing the significance of such a choice. In this work, we provide a thorough empirical investigation of the advantages of representing observations as vectors of categorical values within the context of reinforcement learning. We perfor","authors_text":"Adam White, Edan Meyer, Marlos C. Machado","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-02T18:55:26Z","title":"Harnessing Discrete Representations For Continual Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01203","kind":"arxiv","version":3},"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":"sha256:543cb87608486335b6cc96a4ecc4b808a302ae8c32fc470b872cbc140a4693a1","target":"record","created_at":"2026-07-05T08:43:24Z","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":"9395c2411ac98f030f4a1b6b6474ca738d18b171f78fae6ec387f98a2e2632a0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-02T18:55:26Z","title_canon_sha256":"c09f43c78c06deeddf52ffa479456f307e4121951ac65cba21dcf7242ff35b0a"},"schema_version":"1.0","source":{"id":"2312.01203","kind":"arxiv","version":3}},"canonical_sha256":"caa18f375af80ebcf8ce03d33b6280dd9bc821903085747b1fa10de207c90bc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"caa18f375af80ebcf8ce03d33b6280dd9bc821903085747b1fa10de207c90bc6","first_computed_at":"2026-07-05T08:43:24.601564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:24.601564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"No13yYkX6bU8xyEfe8FR3NM43CzKoxVf1uuUB/V3aWLJP6i3pJrMY7utaYBA8z8/t3ZdBarzgpPyniLohJ9SDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:24.602030Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.01203","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:543cb87608486335b6cc96a4ecc4b808a302ae8c32fc470b872cbc140a4693a1","sha256:973ffd412f120f1b185cb8055a1b0f5ece4075487e051b5cfef252eb02a88a34"],"state_sha256":"b4426084683c63b45f6c6e8401b6798015af73dcf77dd3397fa479d123ef696b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uxmK//QHC6gQ+MPYWy7XDrNlG0PbAEFlrIfzOyWb0yBBw+vKvQ9VRXrhCNumHg/q4nmgDILe8tKMu+kKTA7rBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T21:52:18.501048Z","bundle_sha256":"8b73c4e5b3e30d5b8edb9512249d22b5bf668b59064c20a5c2d4e3c8142cf031"}}