{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:7PVMLWXQSER2B23AV57BCQ7AEH","short_pith_number":"pith:7PVMLWXQ","canonical_record":{"source":{"id":"1406.3270","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-01-16T05:02:28Z","cross_cats_sorted":[],"title_canon_sha256":"9bb7985bb3dcf30a7b9b9d3d2277f5776d8eab31a4709f55d8a2cef5bc51542d","abstract_canon_sha256":"9aafc683377c932963ffd882dabd6a36ae9994ae95a7e773a26a90d7ab223f85"},"schema_version":"1.0"},"canonical_sha256":"fbeac5daf09123a0eb60af7e1143e021e6213b91d0bb5ee1f86253fb8b7107c3","source":{"kind":"arxiv","id":"1406.3270","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.3270","created_at":"2026-05-18T02:49:52Z"},{"alias_kind":"arxiv_version","alias_value":"1406.3270v1","created_at":"2026-05-18T02:49:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.3270","created_at":"2026-05-18T02:49:52Z"},{"alias_kind":"pith_short_12","alias_value":"7PVMLWXQSER2","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"7PVMLWXQSER2B23A","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"7PVMLWXQ","created_at":"2026-05-18T12:28:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:7PVMLWXQSER2B23AV57BCQ7AEH","target":"record","payload":{"canonical_record":{"source":{"id":"1406.3270","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-01-16T05:02:28Z","cross_cats_sorted":[],"title_canon_sha256":"9bb7985bb3dcf30a7b9b9d3d2277f5776d8eab31a4709f55d8a2cef5bc51542d","abstract_canon_sha256":"9aafc683377c932963ffd882dabd6a36ae9994ae95a7e773a26a90d7ab223f85"},"schema_version":"1.0"},"canonical_sha256":"fbeac5daf09123a0eb60af7e1143e021e6213b91d0bb5ee1f86253fb8b7107c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:49:52.706403Z","signature_b64":"dtuKIb4AlJqhIplOxMvtu/f+GSpVkUV9LEZLQ/u2lnv6R+Zlr7rofkZ82AfnUP80Rm9JcsTAIqCQw5WQNbcUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbeac5daf09123a0eb60af7e1143e021e6213b91d0bb5ee1f86253fb8b7107c3","last_reissued_at":"2026-05-18T02:49:52.705942Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:49:52.705942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1406.3270","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":"2026-05-18T02:49:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rB8ZmsPc/9xWUqiAoIJX87ga2aLNky0vmryaMMvhh0uGP2u7+Et6BLg44hFinJOcpnEnN098/bhqE46rg3auAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T02:34:50.271412Z"},"content_sha256":"6b2390a2db74bfbc0cfbe1816c601e8a205cfc164c8931964845d567cd49330f","schema_version":"1.0","event_id":"sha256:6b2390a2db74bfbc0cfbe1816c601e8a205cfc164c8931964845d567cd49330f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:7PVMLWXQSER2B23AV57BCQ7AEH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Kalman Temporal Differences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Matthieu Geist, Olivier Pietquin","submitted_at":"2014-01-16T05:02:28Z","abstract_excerpt":"Because reinforcement learning suffers from a lack of scalability, online value (and Q-) function approximation has received increasing interest this last decade. This contribution introduces a novel approximation scheme, namely the Kalman Temporal Differences (KTD) framework, that exhibits the following features: sample-efficiency, non-linear approximation, non-stationarity handling and uncertainty management. A first KTD-based algorithm is provided for deterministic Markov Decision Processes (MDP) which produces biased estimates in the case of stochastic transitions. Than the eXtended KTD fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.3270","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":"2026-05-18T02:49:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4RMkB6WdiVLDIY/sjLjWqkQ8rRRTAeMNLXK8nxTmAUXFb5KAC9VIE+pdaoYiGJUZyV9HD9oX24S6mVrSpY19Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T02:34:50.272108Z"},"content_sha256":"e4a76a9ffbadc32785fba0402decf6cc3182ac75b3a4135f0de1e220ddb0faaf","schema_version":"1.0","event_id":"sha256:e4a76a9ffbadc32785fba0402decf6cc3182ac75b3a4135f0de1e220ddb0faaf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7PVMLWXQSER2B23AV57BCQ7AEH/bundle.json","state_url":"https://pith.science/pith/7PVMLWXQSER2B23AV57BCQ7AEH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7PVMLWXQSER2B23AV57BCQ7AEH/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":"2026-06-01T02:34:50Z","links":{"resolver":"https://pith.science/pith/7PVMLWXQSER2B23AV57BCQ7AEH","bundle":"https://pith.science/pith/7PVMLWXQSER2B23AV57BCQ7AEH/bundle.json","state":"https://pith.science/pith/7PVMLWXQSER2B23AV57BCQ7AEH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7PVMLWXQSER2B23AV57BCQ7AEH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:7PVMLWXQSER2B23AV57BCQ7AEH","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":"9aafc683377c932963ffd882dabd6a36ae9994ae95a7e773a26a90d7ab223f85","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-01-16T05:02:28Z","title_canon_sha256":"9bb7985bb3dcf30a7b9b9d3d2277f5776d8eab31a4709f55d8a2cef5bc51542d"},"schema_version":"1.0","source":{"id":"1406.3270","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.3270","created_at":"2026-05-18T02:49:52Z"},{"alias_kind":"arxiv_version","alias_value":"1406.3270v1","created_at":"2026-05-18T02:49:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.3270","created_at":"2026-05-18T02:49:52Z"},{"alias_kind":"pith_short_12","alias_value":"7PVMLWXQSER2","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"7PVMLWXQSER2B23A","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"7PVMLWXQ","created_at":"2026-05-18T12:28:19Z"}],"graph_snapshots":[{"event_id":"sha256:e4a76a9ffbadc32785fba0402decf6cc3182ac75b3a4135f0de1e220ddb0faaf","target":"graph","created_at":"2026-05-18T02:49:52Z","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":"Because reinforcement learning suffers from a lack of scalability, online value (and Q-) function approximation has received increasing interest this last decade. This contribution introduces a novel approximation scheme, namely the Kalman Temporal Differences (KTD) framework, that exhibits the following features: sample-efficiency, non-linear approximation, non-stationarity handling and uncertainty management. A first KTD-based algorithm is provided for deterministic Markov Decision Processes (MDP) which produces biased estimates in the case of stochastic transitions. Than the eXtended KTD fr","authors_text":"Matthieu Geist, Olivier Pietquin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-01-16T05:02:28Z","title":"Kalman Temporal Differences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.3270","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":"sha256:6b2390a2db74bfbc0cfbe1816c601e8a205cfc164c8931964845d567cd49330f","target":"record","created_at":"2026-05-18T02:49:52Z","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":"9aafc683377c932963ffd882dabd6a36ae9994ae95a7e773a26a90d7ab223f85","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-01-16T05:02:28Z","title_canon_sha256":"9bb7985bb3dcf30a7b9b9d3d2277f5776d8eab31a4709f55d8a2cef5bc51542d"},"schema_version":"1.0","source":{"id":"1406.3270","kind":"arxiv","version":1}},"canonical_sha256":"fbeac5daf09123a0eb60af7e1143e021e6213b91d0bb5ee1f86253fb8b7107c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbeac5daf09123a0eb60af7e1143e021e6213b91d0bb5ee1f86253fb8b7107c3","first_computed_at":"2026-05-18T02:49:52.705942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:49:52.705942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dtuKIb4AlJqhIplOxMvtu/f+GSpVkUV9LEZLQ/u2lnv6R+Zlr7rofkZ82AfnUP80Rm9JcsTAIqCQw5WQNbcUDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:49:52.706403Z","signed_message":"canonical_sha256_bytes"},"source_id":"1406.3270","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b2390a2db74bfbc0cfbe1816c601e8a205cfc164c8931964845d567cd49330f","sha256:e4a76a9ffbadc32785fba0402decf6cc3182ac75b3a4135f0de1e220ddb0faaf"],"state_sha256":"913447e260297fdf123852af35fc0f76f15d6a03dd4a1098b121c12503c4cc2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"74+eRDxEYLuViUA7VtQmT+hi45tKu0RbGTUzahmYPZvrPLrLLWUQBIAfuFFGMCz2eLFNvpcmtsR06ym4ExerCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T02:34:50.275613Z","bundle_sha256":"53f17f04db7ea7baf8f84288558fb01034fa6867aa847172e35b5248d844730c"}}