{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MQ3P4K65ONR2FOCBQYEVXMR4FF","short_pith_number":"pith:MQ3P4K65","canonical_record":{"source":{"id":"2308.14328","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-28T06:15:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"18e46b5fcaa0bbaad9acd76b243c7de52d5e004cf65006f0da714d48296c60e2","abstract_canon_sha256":"a3107b484b6226bdd66cc051adcec1de5da8021ef8ee12e1356b75c43aa8cb2b"},"schema_version":"1.0"},"canonical_sha256":"6436fe2bdd7363a2b84186095bb23c295ad26d0be7f5181524d037adb09dc1a7","source":{"kind":"arxiv","id":"2308.14328","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.14328","created_at":"2026-07-05T10:18:32Z"},{"alias_kind":"arxiv_version","alias_value":"2308.14328v3","created_at":"2026-07-05T10:18:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14328","created_at":"2026-07-05T10:18:32Z"},{"alias_kind":"pith_short_12","alias_value":"MQ3P4K65ONR2","created_at":"2026-07-05T10:18:32Z"},{"alias_kind":"pith_short_16","alias_value":"MQ3P4K65ONR2FOCB","created_at":"2026-07-05T10:18:32Z"},{"alias_kind":"pith_short_8","alias_value":"MQ3P4K65","created_at":"2026-07-05T10:18:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MQ3P4K65ONR2FOCBQYEVXMR4FF","target":"record","payload":{"canonical_record":{"source":{"id":"2308.14328","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-28T06:15:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"18e46b5fcaa0bbaad9acd76b243c7de52d5e004cf65006f0da714d48296c60e2","abstract_canon_sha256":"a3107b484b6226bdd66cc051adcec1de5da8021ef8ee12e1356b75c43aa8cb2b"},"schema_version":"1.0"},"canonical_sha256":"6436fe2bdd7363a2b84186095bb23c295ad26d0be7f5181524d037adb09dc1a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:32.657007Z","signature_b64":"udwgNLhUQCtg3MO4/QufVt74npDWmHgPjmByn/Skb8UhSbWcwMeVcC8SrUMmbIEi6c5AygOp1WbKvkxJygylAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6436fe2bdd7363a2b84186095bb23c295ad26d0be7f5181524d037adb09dc1a7","last_reissued_at":"2026-07-05T10:18:32.656585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:32.656585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.14328","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":"2026-07-05T10:18:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mU5DgSLXMzvHXstqBNNZWNhK4C32dzfRAq7G/jW8k3uMYY/8FxIpxhLnMCv4EBUPBj9kiOVMvgMsqe696g6HDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:32:01.923727Z"},"content_sha256":"7853f24b62abf89674957ae31b1b0519b2a8769e3822b97101aafe5347b0c452","schema_version":"1.0","event_id":"sha256:7853f24b62abf89674957ae31b1b0519b2a8769e3822b97101aafe5347b0c452"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MQ3P4K65ONR2FOCBQYEVXMR4FF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Generative AI: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Julian McAuley, Lina Yao, Quan Z. Sheng, Yuanjiang Cao","submitted_at":"2023-08-28T06:15:14Z","abstract_excerpt":"Deep Generative AI has been a long-standing essential topic in the machine learning community, which can impact a number of application areas like text generation and computer vision. The major paradigm to train a generative model is maximum likelihood estimation, which pushes the learner to capture and approximate the target data distribution by decreasing the divergence between the model distribution and the target distribution. This formulation successfully establishes the objective of generative tasks, while it is incapable of satisfying all the requirements that a user might expect from a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14328","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/2308.14328/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":"2026-07-05T10:18:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tyie4rUJXW3gveatoQ7H9K+O7P75k8RflUTIdtQv/R4Ys/kxU6xBLlbPGuGS4LGk8FvEpmFMu1lSQwgdMQwQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:32:01.924102Z"},"content_sha256":"7b0490da5661dc5d7135a445df886f41ca1e7ff31248be548feea8bbde662df5","schema_version":"1.0","event_id":"sha256:7b0490da5661dc5d7135a445df886f41ca1e7ff31248be548feea8bbde662df5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MQ3P4K65ONR2FOCBQYEVXMR4FF/bundle.json","state_url":"https://pith.science/pith/MQ3P4K65ONR2FOCBQYEVXMR4FF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MQ3P4K65ONR2FOCBQYEVXMR4FF/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":"2026-07-06T19:32:01Z","links":{"resolver":"https://pith.science/pith/MQ3P4K65ONR2FOCBQYEVXMR4FF","bundle":"https://pith.science/pith/MQ3P4K65ONR2FOCBQYEVXMR4FF/bundle.json","state":"https://pith.science/pith/MQ3P4K65ONR2FOCBQYEVXMR4FF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MQ3P4K65ONR2FOCBQYEVXMR4FF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MQ3P4K65ONR2FOCBQYEVXMR4FF","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":"a3107b484b6226bdd66cc051adcec1de5da8021ef8ee12e1356b75c43aa8cb2b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-28T06:15:14Z","title_canon_sha256":"18e46b5fcaa0bbaad9acd76b243c7de52d5e004cf65006f0da714d48296c60e2"},"schema_version":"1.0","source":{"id":"2308.14328","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.14328","created_at":"2026-07-05T10:18:32Z"},{"alias_kind":"arxiv_version","alias_value":"2308.14328v3","created_at":"2026-07-05T10:18:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14328","created_at":"2026-07-05T10:18:32Z"},{"alias_kind":"pith_short_12","alias_value":"MQ3P4K65ONR2","created_at":"2026-07-05T10:18:32Z"},{"alias_kind":"pith_short_16","alias_value":"MQ3P4K65ONR2FOCB","created_at":"2026-07-05T10:18:32Z"},{"alias_kind":"pith_short_8","alias_value":"MQ3P4K65","created_at":"2026-07-05T10:18:32Z"}],"graph_snapshots":[{"event_id":"sha256:7b0490da5661dc5d7135a445df886f41ca1e7ff31248be548feea8bbde662df5","target":"graph","created_at":"2026-07-05T10:18:32Z","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/2308.14328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Generative AI has been a long-standing essential topic in the machine learning community, which can impact a number of application areas like text generation and computer vision. The major paradigm to train a generative model is maximum likelihood estimation, which pushes the learner to capture and approximate the target data distribution by decreasing the divergence between the model distribution and the target distribution. This formulation successfully establishes the objective of generative tasks, while it is incapable of satisfying all the requirements that a user might expect from a","authors_text":"Julian McAuley, Lina Yao, Quan Z. Sheng, Yuanjiang Cao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-28T06:15:14Z","title":"Reinforcement Learning for Generative AI: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14328","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":"sha256:7853f24b62abf89674957ae31b1b0519b2a8769e3822b97101aafe5347b0c452","target":"record","created_at":"2026-07-05T10:18:32Z","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":"a3107b484b6226bdd66cc051adcec1de5da8021ef8ee12e1356b75c43aa8cb2b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-28T06:15:14Z","title_canon_sha256":"18e46b5fcaa0bbaad9acd76b243c7de52d5e004cf65006f0da714d48296c60e2"},"schema_version":"1.0","source":{"id":"2308.14328","kind":"arxiv","version":3}},"canonical_sha256":"6436fe2bdd7363a2b84186095bb23c295ad26d0be7f5181524d037adb09dc1a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6436fe2bdd7363a2b84186095bb23c295ad26d0be7f5181524d037adb09dc1a7","first_computed_at":"2026-07-05T10:18:32.656585Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:32.656585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"udwgNLhUQCtg3MO4/QufVt74npDWmHgPjmByn/Skb8UhSbWcwMeVcC8SrUMmbIEi6c5AygOp1WbKvkxJygylAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:32.657007Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.14328","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7853f24b62abf89674957ae31b1b0519b2a8769e3822b97101aafe5347b0c452","sha256:7b0490da5661dc5d7135a445df886f41ca1e7ff31248be548feea8bbde662df5"],"state_sha256":"029efeb844fb45257b9f79c26e6ea2ca3bfc7b839d8afed5b6a1158708b193a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9a5zJGBT2rku6KJbzhPZwsLm4//bpccugzw5bWgGuwmFpvKAbdhtKJnzNE1GePYxuGd/iI8bkxK9YREik2MuBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:32:01.926073Z","bundle_sha256":"b83e1e134402979f67b5ce148a2c4c4ba41246f76fb6b8c18bf94b0c4f2530c3"}}