{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:45ZQNX23LZN3WOQ4AIYS55FC34","short_pith_number":"pith:45ZQNX23","canonical_record":{"source":{"id":"2406.00725","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-02T12:21:10Z","cross_cats_sorted":[],"title_canon_sha256":"4d5c2001d8641c0335fe666e3a54fede43146b5d6a6ea55ee525be4ccae5cb63","abstract_canon_sha256":"8383f2c94da291c4d67d4202a8661bf938fe46a55070dfb3a3dd65d89f46bc61"},"schema_version":"1.0"},"canonical_sha256":"e77306df5b5e5bbb3a1c02312ef4a2df33d9d1140f91a84f346b51f5b6698146","source":{"kind":"arxiv","id":"2406.00725","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00725","created_at":"2026-07-05T08:26:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00725v1","created_at":"2026-07-05T08:26:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00725","created_at":"2026-07-05T08:26:29Z"},{"alias_kind":"pith_short_12","alias_value":"45ZQNX23LZN3","created_at":"2026-07-05T08:26:29Z"},{"alias_kind":"pith_short_16","alias_value":"45ZQNX23LZN3WOQ4","created_at":"2026-07-05T08:26:29Z"},{"alias_kind":"pith_short_8","alias_value":"45ZQNX23","created_at":"2026-07-05T08:26:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:45ZQNX23LZN3WOQ4AIYS55FC34","target":"record","payload":{"canonical_record":{"source":{"id":"2406.00725","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-02T12:21:10Z","cross_cats_sorted":[],"title_canon_sha256":"4d5c2001d8641c0335fe666e3a54fede43146b5d6a6ea55ee525be4ccae5cb63","abstract_canon_sha256":"8383f2c94da291c4d67d4202a8661bf938fe46a55070dfb3a3dd65d89f46bc61"},"schema_version":"1.0"},"canonical_sha256":"e77306df5b5e5bbb3a1c02312ef4a2df33d9d1140f91a84f346b51f5b6698146","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:29.958364Z","signature_b64":"SbqCRsYsaBvmDcAkqhCOb8eRO1sC3PXPHkATtZKickFzRbqlRKE1CUwUpz5pRC16uhgSeIILIVnWQAIrNmrrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e77306df5b5e5bbb3a1c02312ef4a2df33d9d1140f91a84f346b51f5b6698146","last_reissued_at":"2026-07-05T08:26:29.957958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:29.957958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.00725","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":"2026-07-05T08:26:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eK66M/q0BSZ3ZS0ajpkcjKyExU79MgQvF9pzKMBE6jsggQZDc7oJSWzTyGOt/x+N6FDFrys2nbq9Ltc3g8jJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:40:15.429849Z"},"content_sha256":"eae997fdfe8c58863265e05e1c5ed2c81f089739dff0699fe8647ac4a3e2798b","schema_version":"1.0","event_id":"sha256:eae997fdfe8c58863265e05e1c5ed2c81f089739dff0699fe8647ac4a3e2798b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:45ZQNX23LZN3WOQ4AIYS55FC34","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Maximum-Entropy Regularized Decision Transformer with Reward Relabelling for Dynamic Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Lina Yao, Siyu Wang, Xiaocong Chen","submitted_at":"2024-06-02T12:21:10Z","abstract_excerpt":"Reinforcement learning-based recommender systems have recently gained popularity. However, due to the typical limitations of simulation environments (e.g., data inefficiency), most of the work cannot be broadly applied in all domains. To counter these challenges, recent advancements have leveraged offline reinforcement learning methods, notable for their data-driven approach utilizing offline datasets. A prominent example of this is the Decision Transformer. Despite its popularity, the Decision Transformer approach has inherent drawbacks, particularly evident in recommendation methods based on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00725","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/2406.00725/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":"2026-07-05T08:26:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gKHVf6csOp4HTUl60u5+GM0A7MqPdjIaHN1BkJchuO9XF2JcdBBBbX1FewajD6B1idhyycimojzFcB3hff9RCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:40:15.430489Z"},"content_sha256":"cb75f72888d9d6ce3273454af5532deae552589ab72e33089219cbe3c2b33e60","schema_version":"1.0","event_id":"sha256:cb75f72888d9d6ce3273454af5532deae552589ab72e33089219cbe3c2b33e60"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/45ZQNX23LZN3WOQ4AIYS55FC34/bundle.json","state_url":"https://pith.science/pith/45ZQNX23LZN3WOQ4AIYS55FC34/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/45ZQNX23LZN3WOQ4AIYS55FC34/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":"2026-07-07T02:40:15Z","links":{"resolver":"https://pith.science/pith/45ZQNX23LZN3WOQ4AIYS55FC34","bundle":"https://pith.science/pith/45ZQNX23LZN3WOQ4AIYS55FC34/bundle.json","state":"https://pith.science/pith/45ZQNX23LZN3WOQ4AIYS55FC34/state.json","well_known_bundle":"https://pith.science/.well-known/pith/45ZQNX23LZN3WOQ4AIYS55FC34/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:45ZQNX23LZN3WOQ4AIYS55FC34","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":"8383f2c94da291c4d67d4202a8661bf938fe46a55070dfb3a3dd65d89f46bc61","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-02T12:21:10Z","title_canon_sha256":"4d5c2001d8641c0335fe666e3a54fede43146b5d6a6ea55ee525be4ccae5cb63"},"schema_version":"1.0","source":{"id":"2406.00725","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00725","created_at":"2026-07-05T08:26:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00725v1","created_at":"2026-07-05T08:26:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00725","created_at":"2026-07-05T08:26:29Z"},{"alias_kind":"pith_short_12","alias_value":"45ZQNX23LZN3","created_at":"2026-07-05T08:26:29Z"},{"alias_kind":"pith_short_16","alias_value":"45ZQNX23LZN3WOQ4","created_at":"2026-07-05T08:26:29Z"},{"alias_kind":"pith_short_8","alias_value":"45ZQNX23","created_at":"2026-07-05T08:26:29Z"}],"graph_snapshots":[{"event_id":"sha256:cb75f72888d9d6ce3273454af5532deae552589ab72e33089219cbe3c2b33e60","target":"graph","created_at":"2026-07-05T08:26:29Z","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/2406.00725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning-based recommender systems have recently gained popularity. However, due to the typical limitations of simulation environments (e.g., data inefficiency), most of the work cannot be broadly applied in all domains. To counter these challenges, recent advancements have leveraged offline reinforcement learning methods, notable for their data-driven approach utilizing offline datasets. A prominent example of this is the Decision Transformer. Despite its popularity, the Decision Transformer approach has inherent drawbacks, particularly evident in recommendation methods based on","authors_text":"Lina Yao, Siyu Wang, Xiaocong Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-02T12:21:10Z","title":"Maximum-Entropy Regularized Decision Transformer with Reward Relabelling for Dynamic Recommendation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00725","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:eae997fdfe8c58863265e05e1c5ed2c81f089739dff0699fe8647ac4a3e2798b","target":"record","created_at":"2026-07-05T08:26:29Z","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":"8383f2c94da291c4d67d4202a8661bf938fe46a55070dfb3a3dd65d89f46bc61","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-02T12:21:10Z","title_canon_sha256":"4d5c2001d8641c0335fe666e3a54fede43146b5d6a6ea55ee525be4ccae5cb63"},"schema_version":"1.0","source":{"id":"2406.00725","kind":"arxiv","version":1}},"canonical_sha256":"e77306df5b5e5bbb3a1c02312ef4a2df33d9d1140f91a84f346b51f5b6698146","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e77306df5b5e5bbb3a1c02312ef4a2df33d9d1140f91a84f346b51f5b6698146","first_computed_at":"2026-07-05T08:26:29.957958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:29.957958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SbqCRsYsaBvmDcAkqhCOb8eRO1sC3PXPHkATtZKickFzRbqlRKE1CUwUpz5pRC16uhgSeIILIVnWQAIrNmrrAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:29.958364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00725","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eae997fdfe8c58863265e05e1c5ed2c81f089739dff0699fe8647ac4a3e2798b","sha256:cb75f72888d9d6ce3273454af5532deae552589ab72e33089219cbe3c2b33e60"],"state_sha256":"d21628822af8cb2345a357cd8a30f5dbd11131a052c0020d1c45a99495504fad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fRzEFIDCIgMapHXV0LFdZuoL0HowfdM8IDdyHaT6KfkugswAhMLRppjKRsxuhlPJlF8zxR7CmZ9DJvJZ0q4OCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T02:40:15.433960Z","bundle_sha256":"b8d76b58c2e211acba1173f884f89b53de01e2e19600e0469ff9aba389d63dba"}}