{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:ZPFLSRA2247YNJSS4YDTUWSXME","short_pith_number":"pith:ZPFLSRA2","canonical_record":{"source":{"id":"1606.02396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-08T04:48:49Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"269b0fb478a391bcf7345c4e9359e42c3d4ff8f11e5af0cf74a499e2e7757ea3","abstract_canon_sha256":"3bd9f1b0faf0fef375ee534ee22a0b41c7dbc13d9f594ec0db3d41fb3abe434a"},"schema_version":"1.0"},"canonical_sha256":"cbcab9441ad73f86a652e6073a5a57610382de5bfdcb098b909e4a291f2013ed","source":{"kind":"arxiv","id":"1606.02396","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.02396","created_at":"2026-05-18T01:12:41Z"},{"alias_kind":"arxiv_version","alias_value":"1606.02396v1","created_at":"2026-05-18T01:12:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.02396","created_at":"2026-05-18T01:12:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZPFLSRA2247Y","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZPFLSRA2247YNJSS","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZPFLSRA2","created_at":"2026-05-18T12:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:ZPFLSRA2247YNJSS4YDTUWSXME","target":"record","payload":{"canonical_record":{"source":{"id":"1606.02396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-08T04:48:49Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"269b0fb478a391bcf7345c4e9359e42c3d4ff8f11e5af0cf74a499e2e7757ea3","abstract_canon_sha256":"3bd9f1b0faf0fef375ee534ee22a0b41c7dbc13d9f594ec0db3d41fb3abe434a"},"schema_version":"1.0"},"canonical_sha256":"cbcab9441ad73f86a652e6073a5a57610382de5bfdcb098b909e4a291f2013ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:41.451900Z","signature_b64":"JF+YdcykHY4VNbClk5pcCA54lUjkUBFQVMSnYnubNQjzxA0yj4AkkBUCogfPhn7rZPXMQhXgCVdfjLhXpNEnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbcab9441ad73f86a652e6073a5a57610382de5bfdcb098b909e4a291f2013ed","last_reissued_at":"2026-05-18T01:12:41.451550Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:41.451550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.02396","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":"2026-05-18T01:12:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GzxXgW0M37MxSIbO0zM5Qx1iQAXe2xyo+0b9UfHtymKg09+3ecLyOQxIm3JMXtSqlFTND1azhbFVj7n3g9CcDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:23:11.633760Z"},"content_sha256":"51c4182fd700502f3d758e479447d256f8c940c09296912ed98c1f8030cb2534","schema_version":"1.0","event_id":"sha256:51c4182fd700502f3d758e479447d256f8c940c09296912ed98c1f8030cb2534"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:ZPFLSRA2247YNJSS4YDTUWSXME","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Successor Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Ardavan Saeedi, Samuel J. Gershman, Simanta Gautam, Tejas D. Kulkarni","submitted_at":"2016-06-08T04:48:49Z","abstract_excerpt":"Learning robust value functions given raw observations and rewards is now possible with model-free and model-based deep reinforcement learning algorithms. There is a third alternative, called Successor Representations (SR), which decomposes the value function into two components -- a reward predictor and a successor map. The successor map represents the expected future state occupancy from any given state and the reward predictor maps states to scalar rewards. The value function of a state can be computed as the inner product between the successor map and the reward weights. In this paper, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.02396","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":"2026-05-18T01:12:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gXzOSvXeZeNQpxhtNug2PNu/07Nw+V0/RTnGrPmRHLdHA9RJ8nV0Fa2IHx5hod1yoH1nIOErNVmTX2+ZaKLGDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:23:11.634121Z"},"content_sha256":"4b215f1b7581a9c7d89a55c31215150dd062e5e0a18e015845920acd55954f73","schema_version":"1.0","event_id":"sha256:4b215f1b7581a9c7d89a55c31215150dd062e5e0a18e015845920acd55954f73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZPFLSRA2247YNJSS4YDTUWSXME/bundle.json","state_url":"https://pith.science/pith/ZPFLSRA2247YNJSS4YDTUWSXME/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZPFLSRA2247YNJSS4YDTUWSXME/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":"2026-05-30T08:23:11Z","links":{"resolver":"https://pith.science/pith/ZPFLSRA2247YNJSS4YDTUWSXME","bundle":"https://pith.science/pith/ZPFLSRA2247YNJSS4YDTUWSXME/bundle.json","state":"https://pith.science/pith/ZPFLSRA2247YNJSS4YDTUWSXME/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZPFLSRA2247YNJSS4YDTUWSXME/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:ZPFLSRA2247YNJSS4YDTUWSXME","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":"3bd9f1b0faf0fef375ee534ee22a0b41c7dbc13d9f594ec0db3d41fb3abe434a","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-08T04:48:49Z","title_canon_sha256":"269b0fb478a391bcf7345c4e9359e42c3d4ff8f11e5af0cf74a499e2e7757ea3"},"schema_version":"1.0","source":{"id":"1606.02396","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.02396","created_at":"2026-05-18T01:12:41Z"},{"alias_kind":"arxiv_version","alias_value":"1606.02396v1","created_at":"2026-05-18T01:12:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.02396","created_at":"2026-05-18T01:12:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZPFLSRA2247Y","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZPFLSRA2247YNJSS","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZPFLSRA2","created_at":"2026-05-18T12:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:4b215f1b7581a9c7d89a55c31215150dd062e5e0a18e015845920acd55954f73","target":"graph","created_at":"2026-05-18T01:12:41Z","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":"Learning robust value functions given raw observations and rewards is now possible with model-free and model-based deep reinforcement learning algorithms. There is a third alternative, called Successor Representations (SR), which decomposes the value function into two components -- a reward predictor and a successor map. The successor map represents the expected future state occupancy from any given state and the reward predictor maps states to scalar rewards. The value function of a state can be computed as the inner product between the successor map and the reward weights. In this paper, we ","authors_text":"Ardavan Saeedi, Samuel J. Gershman, Simanta Gautam, Tejas D. Kulkarni","cross_cats":["cs.AI","cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-08T04:48:49Z","title":"Deep Successor Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.02396","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":"sha256:51c4182fd700502f3d758e479447d256f8c940c09296912ed98c1f8030cb2534","target":"record","created_at":"2026-05-18T01:12:41Z","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":"3bd9f1b0faf0fef375ee534ee22a0b41c7dbc13d9f594ec0db3d41fb3abe434a","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-08T04:48:49Z","title_canon_sha256":"269b0fb478a391bcf7345c4e9359e42c3d4ff8f11e5af0cf74a499e2e7757ea3"},"schema_version":"1.0","source":{"id":"1606.02396","kind":"arxiv","version":1}},"canonical_sha256":"cbcab9441ad73f86a652e6073a5a57610382de5bfdcb098b909e4a291f2013ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbcab9441ad73f86a652e6073a5a57610382de5bfdcb098b909e4a291f2013ed","first_computed_at":"2026-05-18T01:12:41.451550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:41.451550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JF+YdcykHY4VNbClk5pcCA54lUjkUBFQVMSnYnubNQjzxA0yj4AkkBUCogfPhn7rZPXMQhXgCVdfjLhXpNEnAg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:41.451900Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.02396","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51c4182fd700502f3d758e479447d256f8c940c09296912ed98c1f8030cb2534","sha256:4b215f1b7581a9c7d89a55c31215150dd062e5e0a18e015845920acd55954f73"],"state_sha256":"073cc97579f76b603e791b38f6a45384d34927f225f70fe211d9855fd8bb8b99"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UgnvrE74GihJD1+r7b5/wuhL2r2un/ubXumNY7tbm3ugEzq1bYqFk0SEOrXZlZemrrMorWeACRP2AEWdnAebCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T08:23:11.636424Z","bundle_sha256":"d2a4e99b5156b184c988c64130999d6976194b22863aa054916035248e8ae12d"}}