{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VUWRWNXPUHDQZ3JD5RLEF2FCGO","short_pith_number":"pith:VUWRWNXP","canonical_record":{"source":{"id":"2506.17919","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-22T06:58:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c475278028ffcecac62ee7f8baf1193f550a3b362316dc63fbe020061dbc8b2b","abstract_canon_sha256":"5d9f6f0add409b1ff6f21918b145ae94a300704f2022873149e2ccd11249130b"},"schema_version":"1.0"},"canonical_sha256":"ad2d1b36efa1c70ced23ec5642e8a2339a5a5fc3dbc97e92297cffd5d89ef17d","source":{"kind":"arxiv","id":"2506.17919","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17919","created_at":"2026-07-05T11:25:25Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17919v1","created_at":"2026-07-05T11:25:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17919","created_at":"2026-07-05T11:25:25Z"},{"alias_kind":"pith_short_12","alias_value":"VUWRWNXPUHDQ","created_at":"2026-07-05T11:25:25Z"},{"alias_kind":"pith_short_16","alias_value":"VUWRWNXPUHDQZ3JD","created_at":"2026-07-05T11:25:25Z"},{"alias_kind":"pith_short_8","alias_value":"VUWRWNXP","created_at":"2026-07-05T11:25:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VUWRWNXPUHDQZ3JD5RLEF2FCGO","target":"record","payload":{"canonical_record":{"source":{"id":"2506.17919","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-22T06:58:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c475278028ffcecac62ee7f8baf1193f550a3b362316dc63fbe020061dbc8b2b","abstract_canon_sha256":"5d9f6f0add409b1ff6f21918b145ae94a300704f2022873149e2ccd11249130b"},"schema_version":"1.0"},"canonical_sha256":"ad2d1b36efa1c70ced23ec5642e8a2339a5a5fc3dbc97e92297cffd5d89ef17d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:25.588104Z","signature_b64":"sl/JTPDf8wnK04Fv6gbv0Ff7Rsx6XHhF3bD+WX3blz6UitZotaSzKaaZBV44wkhzznhRrInOsMKRKATv3osqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad2d1b36efa1c70ced23ec5642e8a2339a5a5fc3dbc97e92297cffd5d89ef17d","last_reissued_at":"2026-07-05T11:25:25.587614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:25.587614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.17919","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":"2026-07-05T11:25:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+xNoCt7IfS4KTHaYqxXkXdIHljBYr2vL9CeUH6AQDIeZvEWpyMkGN1BwozgVSp3U2TGgpPLPxAoUaM6gDCzEBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:50:31.614383Z"},"content_sha256":"b92317680c7c6a014ca2c5b0b5ce1d9efff2063c45981adcd1c1222609c0887b","schema_version":"1.0","event_id":"sha256:b92317680c7c6a014ca2c5b0b5ce1d9efff2063c45981adcd1c1222609c0887b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VUWRWNXPUHDQZ3JD5RLEF2FCGO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Permutation Equivariant Model-based Offline Reinforcement Learning for Auto-bidding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chuan Yu, Jian Xu, Miao Xu, Rongquan Bai, Wei Chen, Zhiyu Mou","submitted_at":"2025-06-22T06:58:36Z","abstract_excerpt":"Reinforcement learning (RL) for auto-bidding has shifted from using simplistic offline simulators (Simulation-based RL Bidding, SRLB) to offline RL on fixed real datasets (Offline RL Bidding, ORLB). However, ORLB policies are limited by the dataset's state space coverage, offering modest gains. While SRLB expands state coverage, its simulator-reality gap risks misleading policies. This paper introduces Model-based RL Bidding (MRLB), which learns an environment model from real data to bridge this gap. MRLB trains policies using both real and model-generated data, expanding state coverage beyond"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17919","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/2506.17919/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":"2026-07-05T11:25:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WcsmdfjUGl4S0pqvXrqiGdb3JsvNQJ53gVo6szdXHRshQ34uTJ4KalRbOiwMO/9y+ZsCr8MQ1mUOr55wVIE2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:50:31.614963Z"},"content_sha256":"637d3c13ad119485260c41c2c4e59d4e88a56e08bbd1a20690c8493101051b66","schema_version":"1.0","event_id":"sha256:637d3c13ad119485260c41c2c4e59d4e88a56e08bbd1a20690c8493101051b66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VUWRWNXPUHDQZ3JD5RLEF2FCGO/bundle.json","state_url":"https://pith.science/pith/VUWRWNXPUHDQZ3JD5RLEF2FCGO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VUWRWNXPUHDQZ3JD5RLEF2FCGO/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":"2026-08-23T17:50:31Z","links":{"resolver":"https://pith.science/pith/VUWRWNXPUHDQZ3JD5RLEF2FCGO","bundle":"https://pith.science/pith/VUWRWNXPUHDQZ3JD5RLEF2FCGO/bundle.json","state":"https://pith.science/pith/VUWRWNXPUHDQZ3JD5RLEF2FCGO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VUWRWNXPUHDQZ3JD5RLEF2FCGO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VUWRWNXPUHDQZ3JD5RLEF2FCGO","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":"5d9f6f0add409b1ff6f21918b145ae94a300704f2022873149e2ccd11249130b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-22T06:58:36Z","title_canon_sha256":"c475278028ffcecac62ee7f8baf1193f550a3b362316dc63fbe020061dbc8b2b"},"schema_version":"1.0","source":{"id":"2506.17919","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17919","created_at":"2026-07-05T11:25:25Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17919v1","created_at":"2026-07-05T11:25:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17919","created_at":"2026-07-05T11:25:25Z"},{"alias_kind":"pith_short_12","alias_value":"VUWRWNXPUHDQ","created_at":"2026-07-05T11:25:25Z"},{"alias_kind":"pith_short_16","alias_value":"VUWRWNXPUHDQZ3JD","created_at":"2026-07-05T11:25:25Z"},{"alias_kind":"pith_short_8","alias_value":"VUWRWNXP","created_at":"2026-07-05T11:25:25Z"}],"graph_snapshots":[{"event_id":"sha256:637d3c13ad119485260c41c2c4e59d4e88a56e08bbd1a20690c8493101051b66","target":"graph","created_at":"2026-07-05T11:25:25Z","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/2506.17919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) for auto-bidding has shifted from using simplistic offline simulators (Simulation-based RL Bidding, SRLB) to offline RL on fixed real datasets (Offline RL Bidding, ORLB). However, ORLB policies are limited by the dataset's state space coverage, offering modest gains. While SRLB expands state coverage, its simulator-reality gap risks misleading policies. This paper introduces Model-based RL Bidding (MRLB), which learns an environment model from real data to bridge this gap. MRLB trains policies using both real and model-generated data, expanding state coverage beyond","authors_text":"Chuan Yu, Jian Xu, Miao Xu, Rongquan Bai, Wei Chen, Zhiyu Mou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-22T06:58:36Z","title":"Permutation Equivariant Model-based Offline Reinforcement Learning for Auto-bidding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17919","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:b92317680c7c6a014ca2c5b0b5ce1d9efff2063c45981adcd1c1222609c0887b","target":"record","created_at":"2026-07-05T11:25:25Z","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":"5d9f6f0add409b1ff6f21918b145ae94a300704f2022873149e2ccd11249130b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-22T06:58:36Z","title_canon_sha256":"c475278028ffcecac62ee7f8baf1193f550a3b362316dc63fbe020061dbc8b2b"},"schema_version":"1.0","source":{"id":"2506.17919","kind":"arxiv","version":1}},"canonical_sha256":"ad2d1b36efa1c70ced23ec5642e8a2339a5a5fc3dbc97e92297cffd5d89ef17d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad2d1b36efa1c70ced23ec5642e8a2339a5a5fc3dbc97e92297cffd5d89ef17d","first_computed_at":"2026-07-05T11:25:25.587614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:25.587614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sl/JTPDf8wnK04Fv6gbv0Ff7Rsx6XHhF3bD+WX3blz6UitZotaSzKaaZBV44wkhzznhRrInOsMKRKATv3osqBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:25.588104Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17919","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b92317680c7c6a014ca2c5b0b5ce1d9efff2063c45981adcd1c1222609c0887b","sha256:637d3c13ad119485260c41c2c4e59d4e88a56e08bbd1a20690c8493101051b66"],"state_sha256":"56c9d95405870748f380a21a2d1a34b904be69096f56801e71f00bd5d370184a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OQmbITsYkqCMQDismKY84RTzhdDlmxpJX8l9oES3nQA/oH7QWhE/kovDsnRM1Y+eNb35GBZSZ2zze7Jfz7I8BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T17:50:31.620239Z","bundle_sha256":"91fd9b94a2537bf98324ccfcc726d81d19c32b3e407602efb0a5c53ad7a81127"}}