{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PSNXZ5B2HLDVWMQWWSF2CYIWTW","short_pith_number":"pith:PSNXZ5B2","schema_version":"1.0","canonical_sha256":"7c9b7cf43a3ac75b3216b48ba161169db2eda6a464b6259597b8066c43b90de5","source":{"kind":"arxiv","id":"2410.11338","version":1},"attestation_state":"computed","paper":{"title":"DIAR: Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Byung-Jun Lee, Jaehyun Park, Sejin Kim, Sundong Kim, Yunho Kim","submitted_at":"2024-10-15T07:09:56Z","abstract_excerpt":"We propose a novel offline reinforcement learning (offline RL) approach, introducing the Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation (DIAR) framework. We address two key challenges in offline RL: out-of-distribution samples and long-horizon problems. We leverage diffusion models to learn state-action sequence distributions and incorporate value functions for more balanced and adaptive decision-making. DIAR introduces an Adaptive Revaluation mechanism that dynamically adjusts decision lengths by comparing current and future state values, enabling flexible long-term deci"},"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":"2410.11338","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T07:09:56Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"b66f34e24932e738d489e677195dff7ca023abb9a7a613f28f92ba485d749d42","abstract_canon_sha256":"6bba56f62fc76aa38f61af7a56ffcdd1bea2416cc9aaf9c35ecb003126b24c61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:52.014512Z","signature_b64":"hUaYFCL5rM9Geqa3jkw9bZLuDDxIgK4OsfuEJO0KXFWBa4gFLeTb48uttYyDAcb3oMrbO1cMKLwpzswmRDJsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c9b7cf43a3ac75b3216b48ba161169db2eda6a464b6259597b8066c43b90de5","last_reissued_at":"2026-07-05T09:20:52.013971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:52.013971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIAR: Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Byung-Jun Lee, Jaehyun Park, Sejin Kim, Sundong Kim, Yunho Kim","submitted_at":"2024-10-15T07:09:56Z","abstract_excerpt":"We propose a novel offline reinforcement learning (offline RL) approach, introducing the Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation (DIAR) framework. We address two key challenges in offline RL: out-of-distribution samples and long-horizon problems. We leverage diffusion models to learn state-action sequence distributions and incorporate value functions for more balanced and adaptive decision-making. DIAR introduces an Adaptive Revaluation mechanism that dynamically adjusts decision lengths by comparing current and future state values, enabling flexible long-term deci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11338","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/2410.11338/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":"2410.11338","created_at":"2026-07-05T09:20:52.014039+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11338v1","created_at":"2026-07-05T09:20:52.014039+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11338","created_at":"2026-07-05T09:20:52.014039+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSNXZ5B2HLDV","created_at":"2026-07-05T09:20:52.014039+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSNXZ5B2HLDVWMQW","created_at":"2026-07-05T09:20:52.014039+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSNXZ5B2","created_at":"2026-07-05T09:20:52.014039+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/PSNXZ5B2HLDVWMQWWSF2CYIWTW","json":"https://pith.science/pith/PSNXZ5B2HLDVWMQWWSF2CYIWTW.json","graph_json":"https://pith.science/api/pith-number/PSNXZ5B2HLDVWMQWWSF2CYIWTW/graph.json","events_json":"https://pith.science/api/pith-number/PSNXZ5B2HLDVWMQWWSF2CYIWTW/events.json","paper":"https://pith.science/paper/PSNXZ5B2"},"agent_actions":{"view_html":"https://pith.science/pith/PSNXZ5B2HLDVWMQWWSF2CYIWTW","download_json":"https://pith.science/pith/PSNXZ5B2HLDVWMQWWSF2CYIWTW.json","view_paper":"https://pith.science/paper/PSNXZ5B2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11338&json=true","fetch_graph":"https://pith.science/api/pith-number/PSNXZ5B2HLDVWMQWWSF2CYIWTW/graph.json","fetch_events":"https://pith.science/api/pith-number/PSNXZ5B2HLDVWMQWWSF2CYIWTW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSNXZ5B2HLDVWMQWWSF2CYIWTW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSNXZ5B2HLDVWMQWWSF2CYIWTW/action/storage_attestation","attest_author":"https://pith.science/pith/PSNXZ5B2HLDVWMQWWSF2CYIWTW/action/author_attestation","sign_citation":"https://pith.science/pith/PSNXZ5B2HLDVWMQWWSF2CYIWTW/action/citation_signature","submit_replication":"https://pith.science/pith/PSNXZ5B2HLDVWMQWWSF2CYIWTW/action/replication_record"}},"created_at":"2026-07-05T09:20:52.014039+00:00","updated_at":"2026-07-05T09:20:52.014039+00:00"}