{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7P72UKZVCK6EIGQWNW7XSG4467","short_pith_number":"pith:7P72UKZV","canonical_record":{"source":{"id":"1909.01575","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-04T06:58:32Z","cross_cats_sorted":["cs.AI","cs.NE","cs.RO","stat.ML"],"title_canon_sha256":"199b45f7e35f12df860e2bef7f6e7eb8bff629d94b482a02769c69d4abe1a855","abstract_canon_sha256":"96a0c1aaac16d3ed2c451bf966590a42445d26f5c0cef724569e263708861eb9"},"schema_version":"1.0"},"canonical_sha256":"fbffaa2b3512bc441a166dbf791b9cf7e5f0fca329b5c795258e893ebc42a8a5","source":{"kind":"arxiv","id":"1909.01575","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01575","created_at":"2026-07-05T00:02:17Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01575v1","created_at":"2026-07-05T00:02:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01575","created_at":"2026-07-05T00:02:17Z"},{"alias_kind":"pith_short_12","alias_value":"7P72UKZVCK6E","created_at":"2026-07-05T00:02:17Z"},{"alias_kind":"pith_short_16","alias_value":"7P72UKZVCK6EIGQW","created_at":"2026-07-05T00:02:17Z"},{"alias_kind":"pith_short_8","alias_value":"7P72UKZV","created_at":"2026-07-05T00:02:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7P72UKZVCK6EIGQWNW7XSG4467","target":"record","payload":{"canonical_record":{"source":{"id":"1909.01575","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-04T06:58:32Z","cross_cats_sorted":["cs.AI","cs.NE","cs.RO","stat.ML"],"title_canon_sha256":"199b45f7e35f12df860e2bef7f6e7eb8bff629d94b482a02769c69d4abe1a855","abstract_canon_sha256":"96a0c1aaac16d3ed2c451bf966590a42445d26f5c0cef724569e263708861eb9"},"schema_version":"1.0"},"canonical_sha256":"fbffaa2b3512bc441a166dbf791b9cf7e5f0fca329b5c795258e893ebc42a8a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:17.620187Z","signature_b64":"eS0tNPaUGEgEKsq34g4/7Y3gNtCXx7qD2/QmW5wktFJ/lA9BY17qzFUkultn/ZmWZ/7HbLlYz6q5+6v6RyJ4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbffaa2b3512bc441a166dbf791b9cf7e5f0fca329b5c795258e893ebc42a8a5","last_reissued_at":"2026-07-05T00:02:17.619724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:17.619724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.01575","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":"2026-07-05T00:02:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B1NZWlLjxZSg8+tG9D59M9LVzADruC+ccB4C47SeJP7PYURvZY8is6ZoM/jCQVpZB0H7Gx5T0BgvTAOiLcuRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T14:44:24.868000Z"},"content_sha256":"824e21e0bff845d081d45a21340d37fa8dd3f33ba439dbd507d78a5f2c9c8ba9","schema_version":"1.0","event_id":"sha256:824e21e0bff845d081d45a21340d37fa8dd3f33ba439dbd507d78a5f2c9c8ba9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7P72UKZVCK6EIGQWNW7XSG4467","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning sparse representations in reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"David C. Noelle, Jacob Rafati","submitted_at":"2019-09-04T06:58:32Z","abstract_excerpt":"Reinforcement learning (RL) algorithms allow artificial agents to improve their selection of actions to increase rewarding experiences in their environments. Temporal Difference (TD) Learning -- a model-free RL method -- is a leading account of the midbrain dopamine system and the basal ganglia in reinforcement learning. These algorithms typically learn a mapping from the agent's current sensed state to a selected action (known as a policy function) via learning a value function (expected future rewards). TD Learning methods have been very successful on a broad range of control tasks, but lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01575","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/1909.01575/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":"2026-07-05T00:02:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SXqPMvif1NKau+u4WugSP4StBYPu6kV67uo00EKfgEijQVsAlhGFtxOfq7QRfI1fIEkHoaT1zKUsXdva8A6+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T14:44:24.868358Z"},"content_sha256":"08b0491573cc8d6b53fb01ea38de547af485bbb8424364f6281456e7e305c36a","schema_version":"1.0","event_id":"sha256:08b0491573cc8d6b53fb01ea38de547af485bbb8424364f6281456e7e305c36a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7P72UKZVCK6EIGQWNW7XSG4467/bundle.json","state_url":"https://pith.science/pith/7P72UKZVCK6EIGQWNW7XSG4467/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7P72UKZVCK6EIGQWNW7XSG4467/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":"2026-08-21T14:44:24Z","links":{"resolver":"https://pith.science/pith/7P72UKZVCK6EIGQWNW7XSG4467","bundle":"https://pith.science/pith/7P72UKZVCK6EIGQWNW7XSG4467/bundle.json","state":"https://pith.science/pith/7P72UKZVCK6EIGQWNW7XSG4467/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7P72UKZVCK6EIGQWNW7XSG4467/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7P72UKZVCK6EIGQWNW7XSG4467","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":"96a0c1aaac16d3ed2c451bf966590a42445d26f5c0cef724569e263708861eb9","cross_cats_sorted":["cs.AI","cs.NE","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-04T06:58:32Z","title_canon_sha256":"199b45f7e35f12df860e2bef7f6e7eb8bff629d94b482a02769c69d4abe1a855"},"schema_version":"1.0","source":{"id":"1909.01575","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01575","created_at":"2026-07-05T00:02:17Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01575v1","created_at":"2026-07-05T00:02:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01575","created_at":"2026-07-05T00:02:17Z"},{"alias_kind":"pith_short_12","alias_value":"7P72UKZVCK6E","created_at":"2026-07-05T00:02:17Z"},{"alias_kind":"pith_short_16","alias_value":"7P72UKZVCK6EIGQW","created_at":"2026-07-05T00:02:17Z"},{"alias_kind":"pith_short_8","alias_value":"7P72UKZV","created_at":"2026-07-05T00:02:17Z"}],"graph_snapshots":[{"event_id":"sha256:08b0491573cc8d6b53fb01ea38de547af485bbb8424364f6281456e7e305c36a","target":"graph","created_at":"2026-07-05T00:02:17Z","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/1909.01575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) algorithms allow artificial agents to improve their selection of actions to increase rewarding experiences in their environments. Temporal Difference (TD) Learning -- a model-free RL method -- is a leading account of the midbrain dopamine system and the basal ganglia in reinforcement learning. These algorithms typically learn a mapping from the agent's current sensed state to a selected action (known as a policy function) via learning a value function (expected future rewards). TD Learning methods have been very successful on a broad range of control tasks, but lear","authors_text":"David C. Noelle, Jacob Rafati","cross_cats":["cs.AI","cs.NE","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-04T06:58:32Z","title":"Learning sparse representations in reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01575","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":"sha256:824e21e0bff845d081d45a21340d37fa8dd3f33ba439dbd507d78a5f2c9c8ba9","target":"record","created_at":"2026-07-05T00:02:17Z","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":"96a0c1aaac16d3ed2c451bf966590a42445d26f5c0cef724569e263708861eb9","cross_cats_sorted":["cs.AI","cs.NE","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-04T06:58:32Z","title_canon_sha256":"199b45f7e35f12df860e2bef7f6e7eb8bff629d94b482a02769c69d4abe1a855"},"schema_version":"1.0","source":{"id":"1909.01575","kind":"arxiv","version":1}},"canonical_sha256":"fbffaa2b3512bc441a166dbf791b9cf7e5f0fca329b5c795258e893ebc42a8a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbffaa2b3512bc441a166dbf791b9cf7e5f0fca329b5c795258e893ebc42a8a5","first_computed_at":"2026-07-05T00:02:17.619724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:02:17.619724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eS0tNPaUGEgEKsq34g4/7Y3gNtCXx7qD2/QmW5wktFJ/lA9BY17qzFUkultn/ZmWZ/7HbLlYz6q5+6v6RyJ4Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T00:02:17.620187Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.01575","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:824e21e0bff845d081d45a21340d37fa8dd3f33ba439dbd507d78a5f2c9c8ba9","sha256:08b0491573cc8d6b53fb01ea38de547af485bbb8424364f6281456e7e305c36a"],"state_sha256":"27c156d1c61d93922a2a6ec7d15405f0de8b54a80ac9bd31b717007e387f5309"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cFtxaw23AJY1Fjri4Aqpv50eWS3OXa7qVc0EGuvf0hgI2z1ZnMwCZ2WbN2xt/p9S3y0mGGRqRbru+4n3zG14BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T14:44:24.871595Z","bundle_sha256":"dd0f730054df4c5d902e3f584707bb66159a44082d5e11b8d809696c3b8a4c58"}}