{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PVONKTCVPSZRVYNGPNARAU7I6P","short_pith_number":"pith:PVONKTCV","schema_version":"1.0","canonical_sha256":"7d5cd54c557cb31ae1a67b411053e8f3d061915c643595eeea1a2d930ab5efab","source":{"kind":"arxiv","id":"2602.12643","version":2},"attestation_state":"computed","paper":{"title":"Unifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Balaraman Ravindran, Jashaswimalya Acharjee","submitted_at":"2026-02-13T06:06:56Z","abstract_excerpt":"We present Unified Latent Dynamics (ULD), a novel reinforcement learning algorithm that unifies the efficiency of model-free methods with the representational strengths of model-based approaches, without incurring planning overhead. By embedding state-action pairs into a latent space in which the true value function is approximately linear, our method supports a single set of hyperparameters across diverse domains -- from continuous control with low-dimensional and pixel inputs to high-dimensional Atari games. We prove that, under mild conditions, the fixed point of our embedding-based tempora"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.12643","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-13T06:06:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"dbf44698cfb8c1b132f07de05d78349a5c04ab9aea66added050b75258b2b0ac","abstract_canon_sha256":"26842ef52853b09a91456761c974d6b9f0dd9b2588f3d95e388e4119ebc1250a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T00:06:43.439611Z","signature_b64":"5ZznffShD/SebVfLXFd6cQ0oo4ebKiIgNaJ+DUEC4ugQFcN08SdzOWUKA6/S+d90NkwkbksS1pzEhjj+lVJHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d5cd54c557cb31ae1a67b411053e8f3d061915c643595eeea1a2d930ab5efab","last_reissued_at":"2026-06-04T00:06:43.439044Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T00:06:43.439044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Balaraman Ravindran, Jashaswimalya Acharjee","submitted_at":"2026-02-13T06:06:56Z","abstract_excerpt":"We present Unified Latent Dynamics (ULD), a novel reinforcement learning algorithm that unifies the efficiency of model-free methods with the representational strengths of model-based approaches, without incurring planning overhead. By embedding state-action pairs into a latent space in which the true value function is approximately linear, our method supports a single set of hyperparameters across diverse domains -- from continuous control with low-dimensional and pixel inputs to high-dimensional Atari games. We prove that, under mild conditions, the fixed point of our embedding-based tempora"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.12643","kind":"arxiv","version":2},"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/2602.12643/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.12643","created_at":"2026-06-04T00:06:43.439117+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.12643v2","created_at":"2026-06-04T00:06:43.439117+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12643","created_at":"2026-06-04T00:06:43.439117+00:00"},{"alias_kind":"pith_short_12","alias_value":"PVONKTCVPSZR","created_at":"2026-06-04T00:06:43.439117+00:00"},{"alias_kind":"pith_short_16","alias_value":"PVONKTCVPSZRVYNG","created_at":"2026-06-04T00:06:43.439117+00:00"},{"alias_kind":"pith_short_8","alias_value":"PVONKTCV","created_at":"2026-06-04T00:06:43.439117+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PVONKTCVPSZRVYNGPNARAU7I6P","json":"https://pith.science/pith/PVONKTCVPSZRVYNGPNARAU7I6P.json","graph_json":"https://pith.science/api/pith-number/PVONKTCVPSZRVYNGPNARAU7I6P/graph.json","events_json":"https://pith.science/api/pith-number/PVONKTCVPSZRVYNGPNARAU7I6P/events.json","paper":"https://pith.science/paper/PVONKTCV"},"agent_actions":{"view_html":"https://pith.science/pith/PVONKTCVPSZRVYNGPNARAU7I6P","download_json":"https://pith.science/pith/PVONKTCVPSZRVYNGPNARAU7I6P.json","view_paper":"https://pith.science/paper/PVONKTCV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.12643&json=true","fetch_graph":"https://pith.science/api/pith-number/PVONKTCVPSZRVYNGPNARAU7I6P/graph.json","fetch_events":"https://pith.science/api/pith-number/PVONKTCVPSZRVYNGPNARAU7I6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PVONKTCVPSZRVYNGPNARAU7I6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PVONKTCVPSZRVYNGPNARAU7I6P/action/storage_attestation","attest_author":"https://pith.science/pith/PVONKTCVPSZRVYNGPNARAU7I6P/action/author_attestation","sign_citation":"https://pith.science/pith/PVONKTCVPSZRVYNGPNARAU7I6P/action/citation_signature","submit_replication":"https://pith.science/pith/PVONKTCVPSZRVYNGPNARAU7I6P/action/replication_record"}},"created_at":"2026-06-04T00:06:43.439117+00:00","updated_at":"2026-06-04T00:06:43.439117+00:00"}