{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UJ7PIITDRF22XJ3TBY3KE4QMJ7","short_pith_number":"pith:UJ7PIITD","schema_version":"1.0","canonical_sha256":"a27ef422638975aba7730e36a2720c4fc6d47eea5ef80f620579c9ed3cb5d2f8","source":{"kind":"arxiv","id":"2602.05031","version":2},"attestation_state":"computed","paper":{"title":"Laplacian Representations for Decision-Time Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dikshant Shehmar, Marlos C. Machado, Matthew E. Taylor, Matthew Schlegel","submitted_at":"2026-02-04T20:34:50Z","abstract_excerpt":"Planning with a learned model remains a key challenge in model-based reinforcement learning (RL). In decision-time planning, state representations are critical as they must support local cost computation while preserving long-horizon structure. In this paper, we show that the Laplacian representation provides an effective latent space for planning by capturing state-space distances at multiple time scales. This representation preserves meaningful distances and naturally decomposes long-horizon problems into subgoals, also mitigating the compounding errors that arise over long prediction horizo"},"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":"2602.05031","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T20:34:50Z","cross_cats_sorted":[],"title_canon_sha256":"3e4b499dced071a0a118861b1b9224dd78870d03057ca915643b09027b368c80","abstract_canon_sha256":"c34bd810a2caec93c203ae1b30c53bb4b57c9e1c36eda437068da00a646782b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:48.588038Z","signature_b64":"EK7wtuoP+P+r3XTYFHeqCQws1AsrMNucNwKbQ4GvA8+qucRXBi8AIewAKmugMWqh1nLKbuwjy8zrcil20nIBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a27ef422638975aba7730e36a2720c4fc6d47eea5ef80f620579c9ed3cb5d2f8","last_reissued_at":"2026-06-03T01:05:48.587528Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:48.587528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Laplacian Representations for Decision-Time Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dikshant Shehmar, Marlos C. Machado, Matthew E. Taylor, Matthew Schlegel","submitted_at":"2026-02-04T20:34:50Z","abstract_excerpt":"Planning with a learned model remains a key challenge in model-based reinforcement learning (RL). In decision-time planning, state representations are critical as they must support local cost computation while preserving long-horizon structure. In this paper, we show that the Laplacian representation provides an effective latent space for planning by capturing state-space distances at multiple time scales. This representation preserves meaningful distances and naturally decomposes long-horizon problems into subgoals, also mitigating the compounding errors that arise over long prediction horizo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.05031","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/2602.05031/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":"2602.05031","created_at":"2026-06-03T01:05:48.587592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.05031v2","created_at":"2026-06-03T01:05:48.587592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.05031","created_at":"2026-06-03T01:05:48.587592+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJ7PIITDRF22","created_at":"2026-06-03T01:05:48.587592+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJ7PIITDRF22XJ3T","created_at":"2026-06-03T01:05:48.587592+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJ7PIITD","created_at":"2026-06-03T01:05:48.587592+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.20103","citing_title":"Spectral Alignment in Forward-Backward Representations via Temporal Abstraction","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UJ7PIITDRF22XJ3TBY3KE4QMJ7","json":"https://pith.science/pith/UJ7PIITDRF22XJ3TBY3KE4QMJ7.json","graph_json":"https://pith.science/api/pith-number/UJ7PIITDRF22XJ3TBY3KE4QMJ7/graph.json","events_json":"https://pith.science/api/pith-number/UJ7PIITDRF22XJ3TBY3KE4QMJ7/events.json","paper":"https://pith.science/paper/UJ7PIITD"},"agent_actions":{"view_html":"https://pith.science/pith/UJ7PIITDRF22XJ3TBY3KE4QMJ7","download_json":"https://pith.science/pith/UJ7PIITDRF22XJ3TBY3KE4QMJ7.json","view_paper":"https://pith.science/paper/UJ7PIITD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.05031&json=true","fetch_graph":"https://pith.science/api/pith-number/UJ7PIITDRF22XJ3TBY3KE4QMJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/UJ7PIITDRF22XJ3TBY3KE4QMJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJ7PIITDRF22XJ3TBY3KE4QMJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJ7PIITDRF22XJ3TBY3KE4QMJ7/action/storage_attestation","attest_author":"https://pith.science/pith/UJ7PIITDRF22XJ3TBY3KE4QMJ7/action/author_attestation","sign_citation":"https://pith.science/pith/UJ7PIITDRF22XJ3TBY3KE4QMJ7/action/citation_signature","submit_replication":"https://pith.science/pith/UJ7PIITDRF22XJ3TBY3KE4QMJ7/action/replication_record"}},"created_at":"2026-06-03T01:05:48.587592+00:00","updated_at":"2026-06-03T01:05:48.587592+00:00"}