{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RQICY4NVXGVLOVTZGUZWR4M3OO","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":"dc5e82b53156ae9a049e76202ac1a6f585cdbef29a0b17d73f85fbff7419e52b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-08T23:22:08Z","title_canon_sha256":"8496c541685ced74d66ac5d2c36f11ed7d1a5f972f55402c603d714fe865de26"},"schema_version":"1.0","source":{"id":"2501.04879","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04879","created_at":"2026-07-05T09:58:47Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04879v1","created_at":"2026-07-05T09:58:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04879","created_at":"2026-07-05T09:58:47Z"},{"alias_kind":"pith_short_12","alias_value":"RQICY4NVXGVL","created_at":"2026-07-05T09:58:47Z"},{"alias_kind":"pith_short_16","alias_value":"RQICY4NVXGVLOVTZ","created_at":"2026-07-05T09:58:47Z"},{"alias_kind":"pith_short_8","alias_value":"RQICY4NV","created_at":"2026-07-05T09:58:47Z"}],"graph_snapshots":[{"event_id":"sha256:59ad7ebe897351be6bf93f545666081851c6f11e15dc1d9b70e6640216af51f3","target":"graph","created_at":"2026-07-05T09:58:47Z","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/2501.04879/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) aims to estimate the action to take given a (time-varying) state, with the goal of maximizing a cumulative reward function. Predominantly, there are two families of algorithms to solve RL problems: value-based and policy-based methods, with the latter designed to learn a probabilistic parametric policy from states to actions. Most contemporary approaches implement this policy using a neural network (NN). However, NNs usually face issues related to convergence, architectural suitability, hyper-parameter selection, and underutilization of the redundancies of the state","authors_text":"Antonio G. Marques, Hoi-To Wai, Sergio Rozada","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-08T23:22:08Z","title":"Multilinear Tensor Low-Rank Approximation for Policy-Gradient Methods in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04879","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":"sha256:8391c67a144632be527d21790d8924f6f9328517a09ea115ee9879f2da79fff1","target":"record","created_at":"2026-07-05T09:58:47Z","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":"dc5e82b53156ae9a049e76202ac1a6f585cdbef29a0b17d73f85fbff7419e52b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-08T23:22:08Z","title_canon_sha256":"8496c541685ced74d66ac5d2c36f11ed7d1a5f972f55402c603d714fe865de26"},"schema_version":"1.0","source":{"id":"2501.04879","kind":"arxiv","version":1}},"canonical_sha256":"8c102c71b5b9aab75679353368f19b73a275797bd87458990a281020a8ff1f89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c102c71b5b9aab75679353368f19b73a275797bd87458990a281020a8ff1f89","first_computed_at":"2026-07-05T09:58:47.905399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:47.905399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i5YEWxlN49gPH3sfEig/okmcvnmym3eCLvXbYiMdquFHUO0Wt22eBsgXfXmUKZgEogfU+kql+7hgwDp6KrdTDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:47.905818Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04879","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8391c67a144632be527d21790d8924f6f9328517a09ea115ee9879f2da79fff1","sha256:59ad7ebe897351be6bf93f545666081851c6f11e15dc1d9b70e6640216af51f3"],"state_sha256":"151f0cba4049f00466dd41092f3738fc1c7fc258b3dd4af1099a3a02b6aa940c"}