{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ASLBHYQ6M7QPC5FMCM7EF3WLAB","short_pith_number":"pith:ASLBHYQ6","canonical_record":{"source":{"id":"2408.12307","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T11:31:51Z","cross_cats_sorted":[],"title_canon_sha256":"c3c0d061b010cbad31fa3cbef192aa0fc1cc68bcb1d6b642aaebc16a791e00e2","abstract_canon_sha256":"b98a4a0cbddd1f1ab29ca0e5e5ea78322f5eb3ed7c360eb5f5038a9a0a91dde4"},"schema_version":"1.0"},"canonical_sha256":"049613e21e67e0f174ac133e42eecb007c612b5954d0fc548cb31cacd236fcd4","source":{"kind":"arxiv","id":"2408.12307","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12307","created_at":"2026-07-05T11:11:34Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12307v3","created_at":"2026-07-05T11:11:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12307","created_at":"2026-07-05T11:11:34Z"},{"alias_kind":"pith_short_12","alias_value":"ASLBHYQ6M7QP","created_at":"2026-07-05T11:11:34Z"},{"alias_kind":"pith_short_16","alias_value":"ASLBHYQ6M7QPC5FM","created_at":"2026-07-05T11:11:34Z"},{"alias_kind":"pith_short_8","alias_value":"ASLBHYQ6","created_at":"2026-07-05T11:11:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ASLBHYQ6M7QPC5FMCM7EF3WLAB","target":"record","payload":{"canonical_record":{"source":{"id":"2408.12307","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T11:31:51Z","cross_cats_sorted":[],"title_canon_sha256":"c3c0d061b010cbad31fa3cbef192aa0fc1cc68bcb1d6b642aaebc16a791e00e2","abstract_canon_sha256":"b98a4a0cbddd1f1ab29ca0e5e5ea78322f5eb3ed7c360eb5f5038a9a0a91dde4"},"schema_version":"1.0"},"canonical_sha256":"049613e21e67e0f174ac133e42eecb007c612b5954d0fc548cb31cacd236fcd4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:34.261940Z","signature_b64":"bXKP7f3AOsND+LKHCHuRUSj/jZ7gkA8kKZFW5mr7jrHuoAG7OQUvk+2tcJsHrbgqLlgfJwXoz47xbd6P/8uXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"049613e21e67e0f174ac133e42eecb007c612b5954d0fc548cb31cacd236fcd4","last_reissued_at":"2026-07-05T11:11:34.261388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:34.261388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.12307","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9NXS2M1k3M74NowDz1YdAuC+8XtNQwyS3icLB5Yi39hgNDcZUcMGOS+WRqcwdmQqj/dgtOsad87gPg8JTRejAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:51:01.229525Z"},"content_sha256":"b2694b5b82e17fdcf8fcec2d70638307c3b5adbbd3f765cdfb4d6f20bc94624c","schema_version":"1.0","event_id":"sha256:b2694b5b82e17fdcf8fcec2d70638307c3b5adbbd3f765cdfb4d6f20bc94624c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ASLBHYQ6M7QPC5FMCM7EF3WLAB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Unlabeled Data Sharing through Kernel Function Approximation in Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fu-Chieh Chang, Pei-Yuan Wu, Yen-Ru Lai","submitted_at":"2024-08-22T11:31:51Z","abstract_excerpt":"Offline reinforcement learning (RL) learns policies from a fixed dataset, but often requires large amounts of data. The challenge arises when labeled datasets are expensive, especially when rewards have to be provided by human labelers for large datasets. In contrast, unlabelled data tends to be less expensive. This situation highlights the importance of finding effective ways to use unlabelled data in offline RL, especially when labelled data is limited or expensive to obtain. In this paper, we present the algorithm to utilize the unlabeled data in the offline RL method with kernel function a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12307","kind":"arxiv","version":3},"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/2408.12307/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":"2026-07-05T11:11:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g9GRURmF+oHBy4OP34Ize/rgnyrioAMWJNZ7xVz8hYgth07NuO4O1j9bjIHjxU3JGG6MMNyNTg3vhBrNTgFTCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:51:01.230158Z"},"content_sha256":"206620e9f3a4cc6b29e0799eacb120057a1a08b3255f6a7423981470c538d329","schema_version":"1.0","event_id":"sha256:206620e9f3a4cc6b29e0799eacb120057a1a08b3255f6a7423981470c538d329"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ASLBHYQ6M7QPC5FMCM7EF3WLAB/bundle.json","state_url":"https://pith.science/pith/ASLBHYQ6M7QPC5FMCM7EF3WLAB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ASLBHYQ6M7QPC5FMCM7EF3WLAB/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":"2026-08-11T02:51:01Z","links":{"resolver":"https://pith.science/pith/ASLBHYQ6M7QPC5FMCM7EF3WLAB","bundle":"https://pith.science/pith/ASLBHYQ6M7QPC5FMCM7EF3WLAB/bundle.json","state":"https://pith.science/pith/ASLBHYQ6M7QPC5FMCM7EF3WLAB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ASLBHYQ6M7QPC5FMCM7EF3WLAB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ASLBHYQ6M7QPC5FMCM7EF3WLAB","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":"b98a4a0cbddd1f1ab29ca0e5e5ea78322f5eb3ed7c360eb5f5038a9a0a91dde4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T11:31:51Z","title_canon_sha256":"c3c0d061b010cbad31fa3cbef192aa0fc1cc68bcb1d6b642aaebc16a791e00e2"},"schema_version":"1.0","source":{"id":"2408.12307","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12307","created_at":"2026-07-05T11:11:34Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12307v3","created_at":"2026-07-05T11:11:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12307","created_at":"2026-07-05T11:11:34Z"},{"alias_kind":"pith_short_12","alias_value":"ASLBHYQ6M7QP","created_at":"2026-07-05T11:11:34Z"},{"alias_kind":"pith_short_16","alias_value":"ASLBHYQ6M7QPC5FM","created_at":"2026-07-05T11:11:34Z"},{"alias_kind":"pith_short_8","alias_value":"ASLBHYQ6","created_at":"2026-07-05T11:11:34Z"}],"graph_snapshots":[{"event_id":"sha256:206620e9f3a4cc6b29e0799eacb120057a1a08b3255f6a7423981470c538d329","target":"graph","created_at":"2026-07-05T11:11:34Z","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/2408.12307/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) learns policies from a fixed dataset, but often requires large amounts of data. The challenge arises when labeled datasets are expensive, especially when rewards have to be provided by human labelers for large datasets. In contrast, unlabelled data tends to be less expensive. This situation highlights the importance of finding effective ways to use unlabelled data in offline RL, especially when labelled data is limited or expensive to obtain. In this paper, we present the algorithm to utilize the unlabeled data in the offline RL method with kernel function a","authors_text":"Fu-Chieh Chang, Pei-Yuan Wu, Yen-Ru Lai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T11:31:51Z","title":"Leveraging Unlabeled Data Sharing through Kernel Function Approximation in Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12307","kind":"arxiv","version":3},"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:b2694b5b82e17fdcf8fcec2d70638307c3b5adbbd3f765cdfb4d6f20bc94624c","target":"record","created_at":"2026-07-05T11:11:34Z","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":"b98a4a0cbddd1f1ab29ca0e5e5ea78322f5eb3ed7c360eb5f5038a9a0a91dde4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T11:31:51Z","title_canon_sha256":"c3c0d061b010cbad31fa3cbef192aa0fc1cc68bcb1d6b642aaebc16a791e00e2"},"schema_version":"1.0","source":{"id":"2408.12307","kind":"arxiv","version":3}},"canonical_sha256":"049613e21e67e0f174ac133e42eecb007c612b5954d0fc548cb31cacd236fcd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"049613e21e67e0f174ac133e42eecb007c612b5954d0fc548cb31cacd236fcd4","first_computed_at":"2026-07-05T11:11:34.261388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:34.261388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bXKP7f3AOsND+LKHCHuRUSj/jZ7gkA8kKZFW5mr7jrHuoAG7OQUvk+2tcJsHrbgqLlgfJwXoz47xbd6P/8uXCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:34.261940Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.12307","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2694b5b82e17fdcf8fcec2d70638307c3b5adbbd3f765cdfb4d6f20bc94624c","sha256:206620e9f3a4cc6b29e0799eacb120057a1a08b3255f6a7423981470c538d329"],"state_sha256":"6fb47bf4b849fe3f1f8f56dfa9c42703aa9c04296442b44502107d2e3add9896"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F4gQ+uIzpdRCvbV7SHG6MldSWuUwT4ao4YRWh0tSHCXBbQnC0yA3s320Le/2ULRmXYSEceyKNKGVypJ+e4X8AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T02:51:01.233949Z","bundle_sha256":"cc66c32d417d67f2f68c6c51cff84d74234fad8189a16689adfb3c84540e101e"}}