{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NHGF75XPPOQ7TQMRDRWH3E5KED","short_pith_number":"pith:NHGF75XP","canonical_record":{"source":{"id":"2501.10598","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-17T23:10:50Z","cross_cats_sorted":[],"title_canon_sha256":"d458e51a2f597be865a64c5aa8e381f65cb169bf785e54c38b5d5a63b3254d84","abstract_canon_sha256":"5d3683d8381e9483437f9a1586c47f534cf458b81377a05e09ad66d135ef9690"},"schema_version":"1.0"},"canonical_sha256":"69cc5ff6ef7ba1f9c1911c6c7d93aa20ce30f2163dd43f7723985f1ab5e9d24e","source":{"kind":"arxiv","id":"2501.10598","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.10598","created_at":"2026-05-18T02:45:14Z"},{"alias_kind":"arxiv_version","alias_value":"2501.10598v3","created_at":"2026-05-18T02:45:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10598","created_at":"2026-05-18T02:45:14Z"},{"alias_kind":"pith_short_12","alias_value":"NHGF75XPPOQ7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"NHGF75XPPOQ7TQMR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"NHGF75XP","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NHGF75XPPOQ7TQMRDRWH3E5KED","target":"record","payload":{"canonical_record":{"source":{"id":"2501.10598","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-17T23:10:50Z","cross_cats_sorted":[],"title_canon_sha256":"d458e51a2f597be865a64c5aa8e381f65cb169bf785e54c38b5d5a63b3254d84","abstract_canon_sha256":"5d3683d8381e9483437f9a1586c47f534cf458b81377a05e09ad66d135ef9690"},"schema_version":"1.0"},"canonical_sha256":"69cc5ff6ef7ba1f9c1911c6c7d93aa20ce30f2163dd43f7723985f1ab5e9d24e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:45:14.605308Z","signature_b64":"ZSYLcIVfaS0hw3FPiqKI9uj+r1fC4qC8lUu8M3Q+7uOGJCs5Djy2PmY/eLoJW4I1qaizND+sclx2zWaY6YAbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69cc5ff6ef7ba1f9c1911c6c7d93aa20ce30f2163dd43f7723985f1ab5e9d24e","last_reissued_at":"2026-05-18T02:45:14.604653Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:45:14.604653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.10598","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":"2026-05-18T02:45:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SniEkPiHDJA9ggUSxGmKkePQUa8cdf9L5scQrRlZs6Oh3qvzt+UQYojIyFpVpN5heZSQiw/mwzS9OzKB/p+AAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T12:23:16.819307Z"},"content_sha256":"b97f9d0be67767d8fb2100a298fad612d51380d96e129c66c3e7860000b7d8d8","schema_version":"1.0","event_id":"sha256:b97f9d0be67767d8fb2100a298fad612d51380d96e129c66c3e7860000b7d8d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NHGF75XPPOQ7TQMRDRWH3E5KED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Addressing Finite-Horizon MDPs via Low-Rank Tensor Value Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antonio G. Marques, Jose Luis Orejuela, Sergio Rozada","submitted_at":"2025-01-17T23:10:50Z","abstract_excerpt":"We study the problem of learning optimal policies in finite-horizon Markov Decision Processes (MDPs) using low-rank reinforcement learning (RL) methods. In finite-horizon MDPs, the policies, and therefore the value functions (VFs) are not stationary. This aggravates the challenges of high-dimensional MDPs, as they suffer from the curse of dimensionality and high sample complexity. To address these issues, we propose modeling the VFs of finite-horizon MDPs as low-rank tensors, enabling a scalable representation that renders the problem of learning optimal policies tractable. Our approach focuse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10598","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":""},"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":"2026-05-18T02:45:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1EKyHxCfYqnkNlu6Q1IPD4ZewtP3JMZRpDLZwV0yoI0IkN85gPgSgrdssMTaV4g0Jh9nNhEcMvWrLBiP5+jBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T12:23:16.819995Z"},"content_sha256":"f6e8a722164e4cbaddc0704efb46a8e96d865263dcb594c12cb996ffcfd8f07f","schema_version":"1.0","event_id":"sha256:f6e8a722164e4cbaddc0704efb46a8e96d865263dcb594c12cb996ffcfd8f07f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NHGF75XPPOQ7TQMRDRWH3E5KED/bundle.json","state_url":"https://pith.science/pith/NHGF75XPPOQ7TQMRDRWH3E5KED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NHGF75XPPOQ7TQMRDRWH3E5KED/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":"2026-05-23T12:23:16Z","links":{"resolver":"https://pith.science/pith/NHGF75XPPOQ7TQMRDRWH3E5KED","bundle":"https://pith.science/pith/NHGF75XPPOQ7TQMRDRWH3E5KED/bundle.json","state":"https://pith.science/pith/NHGF75XPPOQ7TQMRDRWH3E5KED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NHGF75XPPOQ7TQMRDRWH3E5KED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NHGF75XPPOQ7TQMRDRWH3E5KED","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":"5d3683d8381e9483437f9a1586c47f534cf458b81377a05e09ad66d135ef9690","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-17T23:10:50Z","title_canon_sha256":"d458e51a2f597be865a64c5aa8e381f65cb169bf785e54c38b5d5a63b3254d84"},"schema_version":"1.0","source":{"id":"2501.10598","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.10598","created_at":"2026-05-18T02:45:14Z"},{"alias_kind":"arxiv_version","alias_value":"2501.10598v3","created_at":"2026-05-18T02:45:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10598","created_at":"2026-05-18T02:45:14Z"},{"alias_kind":"pith_short_12","alias_value":"NHGF75XPPOQ7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"NHGF75XPPOQ7TQMR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"NHGF75XP","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:f6e8a722164e4cbaddc0704efb46a8e96d865263dcb594c12cb996ffcfd8f07f","target":"graph","created_at":"2026-05-18T02:45:14Z","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":"We study the problem of learning optimal policies in finite-horizon Markov Decision Processes (MDPs) using low-rank reinforcement learning (RL) methods. In finite-horizon MDPs, the policies, and therefore the value functions (VFs) are not stationary. This aggravates the challenges of high-dimensional MDPs, as they suffer from the curse of dimensionality and high sample complexity. To address these issues, we propose modeling the VFs of finite-horizon MDPs as low-rank tensors, enabling a scalable representation that renders the problem of learning optimal policies tractable. Our approach focuse","authors_text":"Antonio G. Marques, Jose Luis Orejuela, Sergio Rozada","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-17T23:10:50Z","title":"Addressing Finite-Horizon MDPs via Low-Rank Tensor Value Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10598","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:b97f9d0be67767d8fb2100a298fad612d51380d96e129c66c3e7860000b7d8d8","target":"record","created_at":"2026-05-18T02:45:14Z","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":"5d3683d8381e9483437f9a1586c47f534cf458b81377a05e09ad66d135ef9690","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-17T23:10:50Z","title_canon_sha256":"d458e51a2f597be865a64c5aa8e381f65cb169bf785e54c38b5d5a63b3254d84"},"schema_version":"1.0","source":{"id":"2501.10598","kind":"arxiv","version":3}},"canonical_sha256":"69cc5ff6ef7ba1f9c1911c6c7d93aa20ce30f2163dd43f7723985f1ab5e9d24e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69cc5ff6ef7ba1f9c1911c6c7d93aa20ce30f2163dd43f7723985f1ab5e9d24e","first_computed_at":"2026-05-18T02:45:14.604653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:45:14.604653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZSYLcIVfaS0hw3FPiqKI9uj+r1fC4qC8lUu8M3Q+7uOGJCs5Djy2PmY/eLoJW4I1qaizND+sclx2zWaY6YAbBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:45:14.605308Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.10598","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b97f9d0be67767d8fb2100a298fad612d51380d96e129c66c3e7860000b7d8d8","sha256:f6e8a722164e4cbaddc0704efb46a8e96d865263dcb594c12cb996ffcfd8f07f"],"state_sha256":"f272e187c11f2f1bdc81686bdec8a8e24978e82b851806943d6f284bebdcfaaf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gDlY43Gb+4g31QAYi2FG7wkVdR9S0wmJEIDOGoCm1aFd7kecT0I2i6jI4vCbxUUPbjiUbCfh2xwuSKvcSETuBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T12:23:16.823571Z","bundle_sha256":"0fd9886a6bfe1ce3f5ec900b2329ef0bbbbfd1e5664eff3908b3bb029d1b7bd3"}}