{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FWL2VFZIIZHERJ3ILFXMYKU25O","short_pith_number":"pith:FWL2VFZI","canonical_record":{"source":{"id":"2505.07257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-12T06:18:31Z","cross_cats_sorted":[],"title_canon_sha256":"7e4c9edbdad746acfe8a84b05977f59eba103acd6cc9b77cbbb12d98694178f3","abstract_canon_sha256":"4589d47288c2444f3bbcb780169b7ded59e20650d0050eb2ee5ba2834e4e6f86"},"schema_version":"1.0"},"canonical_sha256":"2d97aa9728464e48a768596ecc2a9aeb9142ccbd9e636a27140ca1bfb2cce57b","source":{"kind":"arxiv","id":"2505.07257","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07257","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07257v1","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07257","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"pith_short_12","alias_value":"FWL2VFZIIZHE","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"pith_short_16","alias_value":"FWL2VFZIIZHERJ3I","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"pith_short_8","alias_value":"FWL2VFZI","created_at":"2026-07-05T11:01:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FWL2VFZIIZHERJ3ILFXMYKU25O","target":"record","payload":{"canonical_record":{"source":{"id":"2505.07257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-12T06:18:31Z","cross_cats_sorted":[],"title_canon_sha256":"7e4c9edbdad746acfe8a84b05977f59eba103acd6cc9b77cbbb12d98694178f3","abstract_canon_sha256":"4589d47288c2444f3bbcb780169b7ded59e20650d0050eb2ee5ba2834e4e6f86"},"schema_version":"1.0"},"canonical_sha256":"2d97aa9728464e48a768596ecc2a9aeb9142ccbd9e636a27140ca1bfb2cce57b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:45.079689Z","signature_b64":"+fSC3HRP6lh+Qck2ixQTohX3+h9XdFC7r2uT6DgOtoV6yZH+G6KfzUq2NXA5kAfmySz3dDlbNjjoYAo/WbCLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d97aa9728464e48a768596ecc2a9aeb9142ccbd9e636a27140ca1bfb2cce57b","last_reissued_at":"2026-07-05T11:01:45.079203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:45.079203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.07257","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":"2026-07-05T11:01:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NuHvJVs9j9Y+cfDJ4R5SaQxDPVIpPQWSqnQm8JzUkZcrPS3Fxu6Z1nuJzFoVRk+IWz+JAX2RaO5/qfEha7rtCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:53:13.294767Z"},"content_sha256":"7cb283240dfae3a562462898b3936e1cffe03d6f7f151567544d72c25b8d2395","schema_version":"1.0","event_id":"sha256:7cb283240dfae3a562462898b3936e1cffe03d6f7f151567544d72c25b8d2395"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FWL2VFZIIZHERJ3ILFXMYKU25O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Reward","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jiajun Liu, Ruihong Qiu, Sen Wang, Xuwei Xu, Yi Zhang","submitted_at":"2025-05-12T06:18:31Z","abstract_excerpt":"Model-based offline reinforcement learning (RL) has emerged as a promising approach for recommender systems, enabling effective policy learning by interacting with frozen world models. However, the reward functions in these world models, trained on sparse offline logs, often suffer from inaccuracies. Specifically, existing methods face two major limitations in addressing this challenge: (1) deterministic use of reward functions as static look-up tables, which propagates inaccuracies during policy learning, and (2) static uncertainty designs that fail to effectively capture decision risks and m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07257","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/2505.07257/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":"2026-07-05T11:01:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sxgjNGFUfx7GFGlChAhzjFREgbtGxaMu3UVvcg9myaOk3n3LQgL8K3yUlg0jelO/NiyEhqt2PGKg53FkkrPWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:53:13.295708Z"},"content_sha256":"156d0061c85899be97e79b627c34941dc01b1605cbc9a5c6678bba2f3f4b0352","schema_version":"1.0","event_id":"sha256:156d0061c85899be97e79b627c34941dc01b1605cbc9a5c6678bba2f3f4b0352"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FWL2VFZIIZHERJ3ILFXMYKU25O/bundle.json","state_url":"https://pith.science/pith/FWL2VFZIIZHERJ3ILFXMYKU25O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FWL2VFZIIZHERJ3ILFXMYKU25O/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":"2026-08-19T22:53:13Z","links":{"resolver":"https://pith.science/pith/FWL2VFZIIZHERJ3ILFXMYKU25O","bundle":"https://pith.science/pith/FWL2VFZIIZHERJ3ILFXMYKU25O/bundle.json","state":"https://pith.science/pith/FWL2VFZIIZHERJ3ILFXMYKU25O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FWL2VFZIIZHERJ3ILFXMYKU25O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FWL2VFZIIZHERJ3ILFXMYKU25O","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":"4589d47288c2444f3bbcb780169b7ded59e20650d0050eb2ee5ba2834e4e6f86","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-12T06:18:31Z","title_canon_sha256":"7e4c9edbdad746acfe8a84b05977f59eba103acd6cc9b77cbbb12d98694178f3"},"schema_version":"1.0","source":{"id":"2505.07257","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07257","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07257v1","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07257","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"pith_short_12","alias_value":"FWL2VFZIIZHE","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"pith_short_16","alias_value":"FWL2VFZIIZHERJ3I","created_at":"2026-07-05T11:01:45Z"},{"alias_kind":"pith_short_8","alias_value":"FWL2VFZI","created_at":"2026-07-05T11:01:45Z"}],"graph_snapshots":[{"event_id":"sha256:156d0061c85899be97e79b627c34941dc01b1605cbc9a5c6678bba2f3f4b0352","target":"graph","created_at":"2026-07-05T11:01:45Z","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/2505.07257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based offline reinforcement learning (RL) has emerged as a promising approach for recommender systems, enabling effective policy learning by interacting with frozen world models. However, the reward functions in these world models, trained on sparse offline logs, often suffer from inaccuracies. Specifically, existing methods face two major limitations in addressing this challenge: (1) deterministic use of reward functions as static look-up tables, which propagates inaccuracies during policy learning, and (2) static uncertainty designs that fail to effectively capture decision risks and m","authors_text":"Jiajun Liu, Ruihong Qiu, Sen Wang, Xuwei Xu, Yi Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-12T06:18:31Z","title":"DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07257","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":"sha256:7cb283240dfae3a562462898b3936e1cffe03d6f7f151567544d72c25b8d2395","target":"record","created_at":"2026-07-05T11:01:45Z","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":"4589d47288c2444f3bbcb780169b7ded59e20650d0050eb2ee5ba2834e4e6f86","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-12T06:18:31Z","title_canon_sha256":"7e4c9edbdad746acfe8a84b05977f59eba103acd6cc9b77cbbb12d98694178f3"},"schema_version":"1.0","source":{"id":"2505.07257","kind":"arxiv","version":1}},"canonical_sha256":"2d97aa9728464e48a768596ecc2a9aeb9142ccbd9e636a27140ca1bfb2cce57b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d97aa9728464e48a768596ecc2a9aeb9142ccbd9e636a27140ca1bfb2cce57b","first_computed_at":"2026-07-05T11:01:45.079203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:45.079203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+fSC3HRP6lh+Qck2ixQTohX3+h9XdFC7r2uT6DgOtoV6yZH+G6KfzUq2NXA5kAfmySz3dDlbNjjoYAo/WbCLAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:45.079689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07257","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cb283240dfae3a562462898b3936e1cffe03d6f7f151567544d72c25b8d2395","sha256:156d0061c85899be97e79b627c34941dc01b1605cbc9a5c6678bba2f3f4b0352"],"state_sha256":"ed3df562d2e99d0a1ab05bdb8efac8ef1b1810f90b5ca42f2f2edef655082c64"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WPOW0TV0Ulq3hIYx+Kg7ErpYqln0lRFUProZJkr4MtDuTP8B/oOeUgkaYcFmPR8MTLs4PcNzQbS9daFWAEs3CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T22:53:13.302554Z","bundle_sha256":"721e7dbd9b93d3cb51a5b5cb74224903e20d18d2c66fa4d21302dabe55c3e854"}}