{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PSNXZ5B2HLDVWMQWWSF2CYIWTW","short_pith_number":"pith:PSNXZ5B2","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"},"canonical_sha256":"7c9b7cf43a3ac75b3216b48ba161169db2eda6a464b6259597b8066c43b90de5","source":{"kind":"arxiv","id":"2410.11338","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11338","created_at":"2026-07-05T09:20:52Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11338v1","created_at":"2026-07-05T09:20:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11338","created_at":"2026-07-05T09:20:52Z"},{"alias_kind":"pith_short_12","alias_value":"PSNXZ5B2HLDV","created_at":"2026-07-05T09:20:52Z"},{"alias_kind":"pith_short_16","alias_value":"PSNXZ5B2HLDVWMQW","created_at":"2026-07-05T09:20:52Z"},{"alias_kind":"pith_short_8","alias_value":"PSNXZ5B2","created_at":"2026-07-05T09:20:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PSNXZ5B2HLDVWMQWWSF2CYIWTW","target":"record","payload":{"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"},"canonical_sha256":"7c9b7cf43a3ac75b3216b48ba161169db2eda6a464b6259597b8066c43b90de5","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"},"source_kind":"arxiv","source_id":"2410.11338","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:20:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"go73y1gEbukG1V7G5SvBayEwXw3RXEN4x4l83igrVQDpswfU3jEGCqkVEmSWEpe3mw2/9TIPiETmIABTn/biAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T23:26:58.452809Z"},"content_sha256":"8d82a35d0ffe73328a1d5964f3f2b1afea07f591f1aa4090a43b656f2868027d","schema_version":"1.0","event_id":"sha256:8d82a35d0ffe73328a1d5964f3f2b1afea07f591f1aa4090a43b656f2868027d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PSNXZ5B2HLDVWMQWWSF2CYIWTW","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:20:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pgpJcgBqUnhO0wnhpOryy1e4moaEGu13uR7ZvPzuVUdISaqrY1xCIHHmESYJaoDb7IAZYg2k62jZwVy96eV0Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T23:26:58.453184Z"},"content_sha256":"da2dabbf0bb17e05044bfeee4629704aad917159f6772786e9da8283cb2fcbcf","schema_version":"1.0","event_id":"sha256:da2dabbf0bb17e05044bfeee4629704aad917159f6772786e9da8283cb2fcbcf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PSNXZ5B2HLDVWMQWWSF2CYIWTW/bundle.json","state_url":"https://pith.science/pith/PSNXZ5B2HLDVWMQWWSF2CYIWTW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PSNXZ5B2HLDVWMQWWSF2CYIWTW/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":"2026-07-16T23:26:58Z","links":{"resolver":"https://pith.science/pith/PSNXZ5B2HLDVWMQWWSF2CYIWTW","bundle":"https://pith.science/pith/PSNXZ5B2HLDVWMQWWSF2CYIWTW/bundle.json","state":"https://pith.science/pith/PSNXZ5B2HLDVWMQWWSF2CYIWTW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PSNXZ5B2HLDVWMQWWSF2CYIWTW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PSNXZ5B2HLDVWMQWWSF2CYIWTW","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":"6bba56f62fc76aa38f61af7a56ffcdd1bea2416cc9aaf9c35ecb003126b24c61","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T07:09:56Z","title_canon_sha256":"b66f34e24932e738d489e677195dff7ca023abb9a7a613f28f92ba485d749d42"},"schema_version":"1.0","source":{"id":"2410.11338","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11338","created_at":"2026-07-05T09:20:52Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11338v1","created_at":"2026-07-05T09:20:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11338","created_at":"2026-07-05T09:20:52Z"},{"alias_kind":"pith_short_12","alias_value":"PSNXZ5B2HLDV","created_at":"2026-07-05T09:20:52Z"},{"alias_kind":"pith_short_16","alias_value":"PSNXZ5B2HLDVWMQW","created_at":"2026-07-05T09:20:52Z"},{"alias_kind":"pith_short_8","alias_value":"PSNXZ5B2","created_at":"2026-07-05T09:20:52Z"}],"graph_snapshots":[{"event_id":"sha256:da2dabbf0bb17e05044bfeee4629704aad917159f6772786e9da8283cb2fcbcf","target":"graph","created_at":"2026-07-05T09:20:52Z","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/2410.11338/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Byung-Jun Lee, Jaehyun Park, Sejin Kim, Sundong Kim, Yunho Kim","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T07:09:56Z","title":"DIAR: Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11338","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":"sha256:8d82a35d0ffe73328a1d5964f3f2b1afea07f591f1aa4090a43b656f2868027d","target":"record","created_at":"2026-07-05T09:20:52Z","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":"6bba56f62fc76aa38f61af7a56ffcdd1bea2416cc9aaf9c35ecb003126b24c61","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T07:09:56Z","title_canon_sha256":"b66f34e24932e738d489e677195dff7ca023abb9a7a613f28f92ba485d749d42"},"schema_version":"1.0","source":{"id":"2410.11338","kind":"arxiv","version":1}},"canonical_sha256":"7c9b7cf43a3ac75b3216b48ba161169db2eda6a464b6259597b8066c43b90de5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c9b7cf43a3ac75b3216b48ba161169db2eda6a464b6259597b8066c43b90de5","first_computed_at":"2026-07-05T09:20:52.013971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:52.013971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hUaYFCL5rM9Geqa3jkw9bZLuDDxIgK4OsfuEJO0KXFWBa4gFLeTb48uttYyDAcb3oMrbO1cMKLwpzswmRDJsDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:52.014512Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11338","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d82a35d0ffe73328a1d5964f3f2b1afea07f591f1aa4090a43b656f2868027d","sha256:da2dabbf0bb17e05044bfeee4629704aad917159f6772786e9da8283cb2fcbcf"],"state_sha256":"13d47e97d128ab3623621707abf5d7b9988a71788b1ec1d30d8291ec1f0603d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zef7A6UDnIZNUTC6MKagHb83AHMwJyMFFULhCsZiAdrldJtWS1wPuyqvwNDu6fgGK425nFzh4yRlGh8ZsEXIBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T23:26:58.455360Z","bundle_sha256":"5b84389070e10e992f36bf6832a2978d6ee1bfbc3837711dd80a564ce6f8a4ac"}}