{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KUYP77MXQFGSCQ3YXUVKNVFOT6","short_pith_number":"pith:KUYP77MX","canonical_record":{"source":{"id":"2405.17628","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T19:52:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0be217eaa67d85ee2080e370dfa1fa46ea32e420592d21c6cccc1b7cf9520a02","abstract_canon_sha256":"1ae93fe320eb962625fd891203ed090f801310f33f0a7d4345bb21a67bfbe18c"},"schema_version":"1.0"},"canonical_sha256":"5530fffd97814d214378bd2aa6d4ae9f8079dc53a4d5c277539bb2580fa61bad","source":{"kind":"arxiv","id":"2405.17628","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17628","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17628v1","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17628","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_12","alias_value":"KUYP77MXQFGS","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_16","alias_value":"KUYP77MXQFGSCQ3Y","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_8","alias_value":"KUYP77MX","created_at":"2026-07-05T08:24:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KUYP77MXQFGSCQ3YXUVKNVFOT6","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17628","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T19:52:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0be217eaa67d85ee2080e370dfa1fa46ea32e420592d21c6cccc1b7cf9520a02","abstract_canon_sha256":"1ae93fe320eb962625fd891203ed090f801310f33f0a7d4345bb21a67bfbe18c"},"schema_version":"1.0"},"canonical_sha256":"5530fffd97814d214378bd2aa6d4ae9f8079dc53a4d5c277539bb2580fa61bad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:09.128796Z","signature_b64":"M6CDE90SPPvJ9KRleRW947kOizY0gVgip1Gmu7AvTlCikbQyYiBkArpCIqtqEpY7zeWmi2bC8NGs4wZHsIzVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5530fffd97814d214378bd2aa6d4ae9f8079dc53a4d5c277539bb2580fa61bad","last_reissued_at":"2026-07-05T08:24:09.128296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:09.128296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17628","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":"2026-07-05T08:24:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VIzfwqM7usO2WtPt5XbeuyqDz9PA9HbI42E+5q27hCyJutRSlrH/DjNM0SPbrlA4cOJeWSoQn/bgKi8QUMr1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:37:34.433902Z"},"content_sha256":"c4811dbdd79c4f76525276bacce7784e329336a33fd554bdf1c00d7c06666c05","schema_version":"1.0","event_id":"sha256:c4811dbdd79c4f76525276bacce7784e329336a33fd554bdf1c00d7c06666c05"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KUYP77MXQFGSCQ3YXUVKNVFOT6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tensor Low-rank Approximation of Finite-horizon Value Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Antonio G. Marques, Sergio Rozada","submitted_at":"2024-05-27T19:52:00Z","abstract_excerpt":"The goal of reinforcement learning is estimating a policy that maps states to actions and maximizes the cumulative reward of a Markov Decision Process (MDP). This is oftentimes achieved by estimating first the optimal (reward) value function (VF) associated with each state-action pair. When the MDP has an infinite horizon, the optimal VFs and policies are stationary under mild conditions. However, in finite-horizon MDPs, the VFs (hence, the policies) vary with time. This poses a challenge since the number of VFs to estimate grows not only with the size of the state-action space but also with t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17628","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/2405.17628/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":"2026-07-05T08:24:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LxDOKylTh94Xd93wTfEBbsM6qFEnluKJFC4rDMKi/K08ZOMyYzZEpE4jAkdOovrWE6hXxRr+oDMhOqoGqfyVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:37:34.434825Z"},"content_sha256":"8c2d8b3766537b0490acd8e6eb398b6b9c8ffa493d7b35047d1e9995db86646c","schema_version":"1.0","event_id":"sha256:8c2d8b3766537b0490acd8e6eb398b6b9c8ffa493d7b35047d1e9995db86646c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KUYP77MXQFGSCQ3YXUVKNVFOT6/bundle.json","state_url":"https://pith.science/pith/KUYP77MXQFGSCQ3YXUVKNVFOT6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KUYP77MXQFGSCQ3YXUVKNVFOT6/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":"2026-08-03T22:37:34Z","links":{"resolver":"https://pith.science/pith/KUYP77MXQFGSCQ3YXUVKNVFOT6","bundle":"https://pith.science/pith/KUYP77MXQFGSCQ3YXUVKNVFOT6/bundle.json","state":"https://pith.science/pith/KUYP77MXQFGSCQ3YXUVKNVFOT6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KUYP77MXQFGSCQ3YXUVKNVFOT6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KUYP77MXQFGSCQ3YXUVKNVFOT6","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":"1ae93fe320eb962625fd891203ed090f801310f33f0a7d4345bb21a67bfbe18c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T19:52:00Z","title_canon_sha256":"0be217eaa67d85ee2080e370dfa1fa46ea32e420592d21c6cccc1b7cf9520a02"},"schema_version":"1.0","source":{"id":"2405.17628","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17628","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17628v1","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17628","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_12","alias_value":"KUYP77MXQFGS","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_16","alias_value":"KUYP77MXQFGSCQ3Y","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_8","alias_value":"KUYP77MX","created_at":"2026-07-05T08:24:09Z"}],"graph_snapshots":[{"event_id":"sha256:8c2d8b3766537b0490acd8e6eb398b6b9c8ffa493d7b35047d1e9995db86646c","target":"graph","created_at":"2026-07-05T08:24:09Z","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/2405.17628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of reinforcement learning is estimating a policy that maps states to actions and maximizes the cumulative reward of a Markov Decision Process (MDP). This is oftentimes achieved by estimating first the optimal (reward) value function (VF) associated with each state-action pair. When the MDP has an infinite horizon, the optimal VFs and policies are stationary under mild conditions. However, in finite-horizon MDPs, the VFs (hence, the policies) vary with time. This poses a challenge since the number of VFs to estimate grows not only with the size of the state-action space but also with t","authors_text":"Antonio G. Marques, Sergio Rozada","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T19:52:00Z","title":"Tensor Low-rank Approximation of Finite-horizon Value Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17628","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:c4811dbdd79c4f76525276bacce7784e329336a33fd554bdf1c00d7c06666c05","target":"record","created_at":"2026-07-05T08:24:09Z","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":"1ae93fe320eb962625fd891203ed090f801310f33f0a7d4345bb21a67bfbe18c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T19:52:00Z","title_canon_sha256":"0be217eaa67d85ee2080e370dfa1fa46ea32e420592d21c6cccc1b7cf9520a02"},"schema_version":"1.0","source":{"id":"2405.17628","kind":"arxiv","version":1}},"canonical_sha256":"5530fffd97814d214378bd2aa6d4ae9f8079dc53a4d5c277539bb2580fa61bad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5530fffd97814d214378bd2aa6d4ae9f8079dc53a4d5c277539bb2580fa61bad","first_computed_at":"2026-07-05T08:24:09.128296Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:09.128296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M6CDE90SPPvJ9KRleRW947kOizY0gVgip1Gmu7AvTlCikbQyYiBkArpCIqtqEpY7zeWmi2bC8NGs4wZHsIzVCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:09.128796Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17628","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4811dbdd79c4f76525276bacce7784e329336a33fd554bdf1c00d7c06666c05","sha256:8c2d8b3766537b0490acd8e6eb398b6b9c8ffa493d7b35047d1e9995db86646c"],"state_sha256":"45f19ca60276503605fdcaccc776e2df0faac10216f65d05f55472824cb8cba7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CMXP3loPYU5lhf9a+zKhL5Raouuhw7295gvAo4vF107FgqbWiAB8BfOxxJyeIqNUclTyNFeQUeE+PqquifCJCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:37:34.440497Z","bundle_sha256":"5c666192c88b1c9ac50962033a6a0cd7060f48d45eb23a0548d47369fb7ecf7e"}}