{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QQA3LKMCXZEZD3RGPNECGVKWGV","short_pith_number":"pith:QQA3LKMC","canonical_record":{"source":{"id":"2406.09089","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T13:15:40Z","cross_cats_sorted":[],"title_canon_sha256":"4c2deca38fbb09ef8c43f36ee3f7ecdcd4c471bcfe20bcc002c401e064d68592","abstract_canon_sha256":"a9bb3acbda60cdda8f40818b38ae2fcdb2af2fc705f9bb0ad175a3f29604e8bf"},"schema_version":"1.0"},"canonical_sha256":"8401b5a982be4991ee267b4823555635776892afd6f3e4518bd8b7ba5ff54810","source":{"kind":"arxiv","id":"2406.09089","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09089","created_at":"2026-07-05T08:31:28Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09089v1","created_at":"2026-07-05T08:31:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09089","created_at":"2026-07-05T08:31:28Z"},{"alias_kind":"pith_short_12","alias_value":"QQA3LKMCXZEZ","created_at":"2026-07-05T08:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"QQA3LKMCXZEZD3RG","created_at":"2026-07-05T08:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"QQA3LKMC","created_at":"2026-07-05T08:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QQA3LKMCXZEZD3RGPNECGVKWGV","target":"record","payload":{"canonical_record":{"source":{"id":"2406.09089","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T13:15:40Z","cross_cats_sorted":[],"title_canon_sha256":"4c2deca38fbb09ef8c43f36ee3f7ecdcd4c471bcfe20bcc002c401e064d68592","abstract_canon_sha256":"a9bb3acbda60cdda8f40818b38ae2fcdb2af2fc705f9bb0ad175a3f29604e8bf"},"schema_version":"1.0"},"canonical_sha256":"8401b5a982be4991ee267b4823555635776892afd6f3e4518bd8b7ba5ff54810","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:28.017324Z","signature_b64":"I/SuO8kOFaIs/Ph+iol8E8R80+oYG7rIr0+E3zbDpk22i8fWU+cdvmUZVb//Gc77adVcBQFiQVT50F8mDP/GBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8401b5a982be4991ee267b4823555635776892afd6f3e4518bd8b7ba5ff54810","last_reissued_at":"2026-07-05T08:31:28.016860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:28.016860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.09089","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":"2026-07-05T08:31:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K52/VDMxdOPsxGW6lzPPW7gmO64NyKz7TeCoDwM5LwtYQSYkc7syaH+bbCTBZCShHEzu5+RliHDg+jW7+j+RDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:14:23.156585Z"},"content_sha256":"05d85c46070ba77b4a9b89dccf42f2bc28a77626c98816d0e8e423e307d5967b","schema_version":"1.0","event_id":"sha256:05d85c46070ba77b4a9b89dccf42f2bc28a77626c98816d0e8e423e307d5967b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QQA3LKMCXZEZD3RGPNECGVKWGV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiffPoGAN: Diffusion Policies with Generative Adversarial Networks for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Tang, Long Chen, Shen Li, Xuemin Hu, Yingfen Xu","submitted_at":"2024-06-13T13:15:40Z","abstract_excerpt":"Offline reinforcement learning (RL) can learn optimal policies from pre-collected offline datasets without interacting with the environment, but the sampled actions of the agent cannot often cover the action distribution under a given state, resulting in the extrapolation error issue. Recent works address this issue by employing generative adversarial networks (GANs). However, these methods often suffer from insufficient constraints on policy exploration and inaccurate representation of behavior policies. Moreover, the generator in GANs fails in fooling the discriminator while maximizing the e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09089","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/2406.09089/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":"2026-07-05T08:31:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DVjvLeMtJ+Rit0k16AprAvzOx8P0IlQhHf465Y3vNpaG3dIjGsb/JoFQ1twTTAtUfFn5WBwvYxUd3Y0T4jELBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:14:23.157562Z"},"content_sha256":"00cb26199fc29a69b8f3933de811d48e423ddf261055e33d86fbe12a14c6b00c","schema_version":"1.0","event_id":"sha256:00cb26199fc29a69b8f3933de811d48e423ddf261055e33d86fbe12a14c6b00c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QQA3LKMCXZEZD3RGPNECGVKWGV/bundle.json","state_url":"https://pith.science/pith/QQA3LKMCXZEZD3RGPNECGVKWGV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QQA3LKMCXZEZD3RGPNECGVKWGV/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":"2026-08-03T20:14:23Z","links":{"resolver":"https://pith.science/pith/QQA3LKMCXZEZD3RGPNECGVKWGV","bundle":"https://pith.science/pith/QQA3LKMCXZEZD3RGPNECGVKWGV/bundle.json","state":"https://pith.science/pith/QQA3LKMCXZEZD3RGPNECGVKWGV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QQA3LKMCXZEZD3RGPNECGVKWGV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QQA3LKMCXZEZD3RGPNECGVKWGV","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":"a9bb3acbda60cdda8f40818b38ae2fcdb2af2fc705f9bb0ad175a3f29604e8bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T13:15:40Z","title_canon_sha256":"4c2deca38fbb09ef8c43f36ee3f7ecdcd4c471bcfe20bcc002c401e064d68592"},"schema_version":"1.0","source":{"id":"2406.09089","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09089","created_at":"2026-07-05T08:31:28Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09089v1","created_at":"2026-07-05T08:31:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09089","created_at":"2026-07-05T08:31:28Z"},{"alias_kind":"pith_short_12","alias_value":"QQA3LKMCXZEZ","created_at":"2026-07-05T08:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"QQA3LKMCXZEZD3RG","created_at":"2026-07-05T08:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"QQA3LKMC","created_at":"2026-07-05T08:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:00cb26199fc29a69b8f3933de811d48e423ddf261055e33d86fbe12a14c6b00c","target":"graph","created_at":"2026-07-05T08:31:28Z","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/2406.09089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) can learn optimal policies from pre-collected offline datasets without interacting with the environment, but the sampled actions of the agent cannot often cover the action distribution under a given state, resulting in the extrapolation error issue. Recent works address this issue by employing generative adversarial networks (GANs). However, these methods often suffer from insufficient constraints on policy exploration and inaccurate representation of behavior policies. Moreover, the generator in GANs fails in fooling the discriminator while maximizing the e","authors_text":"Bo Tang, Long Chen, Shen Li, Xuemin Hu, Yingfen Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T13:15:40Z","title":"DiffPoGAN: Diffusion Policies with Generative Adversarial Networks for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09089","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":"sha256:05d85c46070ba77b4a9b89dccf42f2bc28a77626c98816d0e8e423e307d5967b","target":"record","created_at":"2026-07-05T08:31:28Z","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":"a9bb3acbda60cdda8f40818b38ae2fcdb2af2fc705f9bb0ad175a3f29604e8bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T13:15:40Z","title_canon_sha256":"4c2deca38fbb09ef8c43f36ee3f7ecdcd4c471bcfe20bcc002c401e064d68592"},"schema_version":"1.0","source":{"id":"2406.09089","kind":"arxiv","version":1}},"canonical_sha256":"8401b5a982be4991ee267b4823555635776892afd6f3e4518bd8b7ba5ff54810","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8401b5a982be4991ee267b4823555635776892afd6f3e4518bd8b7ba5ff54810","first_computed_at":"2026-07-05T08:31:28.016860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:28.016860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I/SuO8kOFaIs/Ph+iol8E8R80+oYG7rIr0+E3zbDpk22i8fWU+cdvmUZVb//Gc77adVcBQFiQVT50F8mDP/GBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:28.017324Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09089","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05d85c46070ba77b4a9b89dccf42f2bc28a77626c98816d0e8e423e307d5967b","sha256:00cb26199fc29a69b8f3933de811d48e423ddf261055e33d86fbe12a14c6b00c"],"state_sha256":"5d393f002b548035e96b90d53f898e3c1c67fe4281085d3d632db340766be55a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wYzeIHKMZ2456eCrBBeZS/FfouZlbSkGl41/0n4BlMNBmbmPMar+c15WUOWnYyFYxh1O2U6vTbIwniG5fmFvDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:14:23.164002Z","bundle_sha256":"ff2b2184f9b28d872f918499a8224640d4e0a49c2abb95cc4e3cd6cfe4f960d8"}}