{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IO22FBZE65NA5R6EJFI5LZMOM2","short_pith_number":"pith:IO22FBZE","canonical_record":{"source":{"id":"2407.20109","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-29T15:36:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fc6f38c4fc1944a180eea01250200060666ab422913709f524a3d77d05beab92","abstract_canon_sha256":"76dd7fd6a125dfc17324e2f7c575bea531a6d529caafbe99ff650a9c63120fba"},"schema_version":"1.0"},"canonical_sha256":"43b5a28724f75a0ec7c44951d5e58e66bbc3636db186461609d310088e1a0f67","source":{"kind":"arxiv","id":"2407.20109","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.20109","created_at":"2026-07-05T09:28:53Z"},{"alias_kind":"arxiv_version","alias_value":"2407.20109v2","created_at":"2026-07-05T09:28:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20109","created_at":"2026-07-05T09:28:53Z"},{"alias_kind":"pith_short_12","alias_value":"IO22FBZE65NA","created_at":"2026-07-05T09:28:53Z"},{"alias_kind":"pith_short_16","alias_value":"IO22FBZE65NA5R6E","created_at":"2026-07-05T09:28:53Z"},{"alias_kind":"pith_short_8","alias_value":"IO22FBZE","created_at":"2026-07-05T09:28:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IO22FBZE65NA5R6EJFI5LZMOM2","target":"record","payload":{"canonical_record":{"source":{"id":"2407.20109","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-29T15:36:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fc6f38c4fc1944a180eea01250200060666ab422913709f524a3d77d05beab92","abstract_canon_sha256":"76dd7fd6a125dfc17324e2f7c575bea531a6d529caafbe99ff650a9c63120fba"},"schema_version":"1.0"},"canonical_sha256":"43b5a28724f75a0ec7c44951d5e58e66bbc3636db186461609d310088e1a0f67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:53.685068Z","signature_b64":"y+PGWY9LncrcKqMmirhQdWScqHKd7Uz8ssQXSesyknBAz944DQLemaliQoo8EmsDOCHwl4CV9ISIjBCFHVu5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43b5a28724f75a0ec7c44951d5e58e66bbc3636db186461609d310088e1a0f67","last_reissued_at":"2026-07-05T09:28:53.684579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:53.684579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.20109","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:28:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Oh/uORfaxzJwuRDhwi2ibz2w1ELeaPwcfzc7eEVHYzBwQWYvbKJAeMDfF42UX1KVamwT2JbYdewPBpfnA/G6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:15:24.766290Z"},"content_sha256":"fc6902ad9c9940fc08d1d51bd12fa7e2a672e14057c65aea7d61d59cf520eedf","schema_version":"1.0","event_id":"sha256:fc6902ad9c9940fc08d1d51bd12fa7e2a672e14057c65aea7d61d59cf520eedf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IO22FBZE65NA5R6EJFI5LZMOM2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amy Zhang, Haoran Xu, Liyuan Mao, Weinan Zhang, Xianyuan Zhan","submitted_at":"2024-07-29T15:36:42Z","abstract_excerpt":"One important property of DIstribution Correction Estimation (DICE) methods is that the solution is the optimal stationary distribution ratio between the optimized and data collection policy. In this work, we show that DICE-based methods can be viewed as a transformation from the behavior distribution to the optimal policy distribution. Based on this, we propose a novel approach, Diffusion-DICE, that directly performs this transformation using diffusion models. We find that the optimal policy's score function can be decomposed into two terms: the behavior policy's score function and the gradie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20109","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/2407.20109/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":"2026-07-05T09:28:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I6IOhxjGJB8ZIpPRvVCg80NvUrJnonPoNUqyQl9Vxw9/A+hQlEM6+lV1LDKzZnG/eELIUn0lQgFiFwKzy0Y1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:15:24.766946Z"},"content_sha256":"4e9952aa6c8c9851d759a98e99d45a94cbd3db9ba625e96afb4e3a92ff1a1249","schema_version":"1.0","event_id":"sha256:4e9952aa6c8c9851d759a98e99d45a94cbd3db9ba625e96afb4e3a92ff1a1249"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IO22FBZE65NA5R6EJFI5LZMOM2/bundle.json","state_url":"https://pith.science/pith/IO22FBZE65NA5R6EJFI5LZMOM2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IO22FBZE65NA5R6EJFI5LZMOM2/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":"2026-08-03T17:15:24Z","links":{"resolver":"https://pith.science/pith/IO22FBZE65NA5R6EJFI5LZMOM2","bundle":"https://pith.science/pith/IO22FBZE65NA5R6EJFI5LZMOM2/bundle.json","state":"https://pith.science/pith/IO22FBZE65NA5R6EJFI5LZMOM2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IO22FBZE65NA5R6EJFI5LZMOM2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IO22FBZE65NA5R6EJFI5LZMOM2","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":"76dd7fd6a125dfc17324e2f7c575bea531a6d529caafbe99ff650a9c63120fba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-29T15:36:42Z","title_canon_sha256":"fc6f38c4fc1944a180eea01250200060666ab422913709f524a3d77d05beab92"},"schema_version":"1.0","source":{"id":"2407.20109","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.20109","created_at":"2026-07-05T09:28:53Z"},{"alias_kind":"arxiv_version","alias_value":"2407.20109v2","created_at":"2026-07-05T09:28:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20109","created_at":"2026-07-05T09:28:53Z"},{"alias_kind":"pith_short_12","alias_value":"IO22FBZE65NA","created_at":"2026-07-05T09:28:53Z"},{"alias_kind":"pith_short_16","alias_value":"IO22FBZE65NA5R6E","created_at":"2026-07-05T09:28:53Z"},{"alias_kind":"pith_short_8","alias_value":"IO22FBZE","created_at":"2026-07-05T09:28:53Z"}],"graph_snapshots":[{"event_id":"sha256:4e9952aa6c8c9851d759a98e99d45a94cbd3db9ba625e96afb4e3a92ff1a1249","target":"graph","created_at":"2026-07-05T09:28:53Z","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/2407.20109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One important property of DIstribution Correction Estimation (DICE) methods is that the solution is the optimal stationary distribution ratio between the optimized and data collection policy. In this work, we show that DICE-based methods can be viewed as a transformation from the behavior distribution to the optimal policy distribution. Based on this, we propose a novel approach, Diffusion-DICE, that directly performs this transformation using diffusion models. We find that the optimal policy's score function can be decomposed into two terms: the behavior policy's score function and the gradie","authors_text":"Amy Zhang, Haoran Xu, Liyuan Mao, Weinan Zhang, Xianyuan Zhan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-29T15:36:42Z","title":"Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20109","kind":"arxiv","version":2},"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:fc6902ad9c9940fc08d1d51bd12fa7e2a672e14057c65aea7d61d59cf520eedf","target":"record","created_at":"2026-07-05T09:28:53Z","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":"76dd7fd6a125dfc17324e2f7c575bea531a6d529caafbe99ff650a9c63120fba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-29T15:36:42Z","title_canon_sha256":"fc6f38c4fc1944a180eea01250200060666ab422913709f524a3d77d05beab92"},"schema_version":"1.0","source":{"id":"2407.20109","kind":"arxiv","version":2}},"canonical_sha256":"43b5a28724f75a0ec7c44951d5e58e66bbc3636db186461609d310088e1a0f67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43b5a28724f75a0ec7c44951d5e58e66bbc3636db186461609d310088e1a0f67","first_computed_at":"2026-07-05T09:28:53.684579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:53.684579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y+PGWY9LncrcKqMmirhQdWScqHKd7Uz8ssQXSesyknBAz944DQLemaliQoo8EmsDOCHwl4CV9ISIjBCFHVu5Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:53.685068Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.20109","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc6902ad9c9940fc08d1d51bd12fa7e2a672e14057c65aea7d61d59cf520eedf","sha256:4e9952aa6c8c9851d759a98e99d45a94cbd3db9ba625e96afb4e3a92ff1a1249"],"state_sha256":"d30cc8effdcb8fea924021565dd8310920b16ff229f5605dc6255e475990b6e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vnFMVg1u4pqXrp6Kpe30/Ut19xc7kjIIHT9GXF4RdwyNulBA3s+SM3cdb6+A8M5W1ij/+HayD1+DSaXOxeldAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:15:24.772093Z","bundle_sha256":"bac8c5fcde330aa7a7ca31bfd22aba0ee77d160c73c2753e00f74196cbd299be"}}