{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:B5MX465YZGY64CUITUFSBOI677","short_pith_number":"pith:B5MX465Y","canonical_record":{"source":{"id":"2209.08228","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-09-17T03:09:06Z","cross_cats_sorted":[],"title_canon_sha256":"749acdfda847b193bbd954765f2250c578e65ee4685c8e31bbbc61768fa441cd","abstract_canon_sha256":"185853013a16145c30d359103af0d994d4618c47d4c89cdaf49610d8b68a5337"},"schema_version":"1.0"},"canonical_sha256":"0f597e7bb8c9b1ee0a889d0b20b91effc2a2b2421f93a9117e15ccc94ab920bf","source":{"kind":"arxiv","id":"2209.08228","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.08228","created_at":"2026-07-05T04:58:18Z"},{"alias_kind":"arxiv_version","alias_value":"2209.08228v1","created_at":"2026-07-05T04:58:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08228","created_at":"2026-07-05T04:58:18Z"},{"alias_kind":"pith_short_12","alias_value":"B5MX465YZGY6","created_at":"2026-07-05T04:58:18Z"},{"alias_kind":"pith_short_16","alias_value":"B5MX465YZGY64CUI","created_at":"2026-07-05T04:58:18Z"},{"alias_kind":"pith_short_8","alias_value":"B5MX465Y","created_at":"2026-07-05T04:58:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:B5MX465YZGY64CUITUFSBOI677","target":"record","payload":{"canonical_record":{"source":{"id":"2209.08228","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-09-17T03:09:06Z","cross_cats_sorted":[],"title_canon_sha256":"749acdfda847b193bbd954765f2250c578e65ee4685c8e31bbbc61768fa441cd","abstract_canon_sha256":"185853013a16145c30d359103af0d994d4618c47d4c89cdaf49610d8b68a5337"},"schema_version":"1.0"},"canonical_sha256":"0f597e7bb8c9b1ee0a889d0b20b91effc2a2b2421f93a9117e15ccc94ab920bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:18.736360Z","signature_b64":"7kHRTMYZzx+ussUCmzAGKuoEDLuKggUB2ryJMMRd2EKCG5yCq2xzrprA4iQLftQeMG119Rn1lXOuW9H0UR4NBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f597e7bb8c9b1ee0a889d0b20b91effc2a2b2421f93a9117e15ccc94ab920bf","last_reissued_at":"2026-07-05T04:58:18.735898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:18.735898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.08228","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":"2026-07-05T04:58:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CkwkFNv9sBxAJfMQx3hUeJ5wU3ucImMAu8ut2h2pXyyS0SrOalUNeZuO+lXHKgRLEBQrRgAXLD1hBD35iDlwDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:14:19.169724Z"},"content_sha256":"33eb3407cbe9ed3140ccb641f3c326c1b18adba3d1c69e1330afa25f5709eaf6","schema_version":"1.0","event_id":"sha256:33eb3407cbe9ed3140ccb641f3c326c1b18adba3d1c69e1330afa25f5709eaf6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:B5MX465YZGY64CUITUFSBOI677","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Intrinsically Motivated Reinforcement Learning based Recommendation with Counterfactual Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Lianyong Qi, Lina Yao, Siyu Wang, Xiaocong Chen, Yong Li","submitted_at":"2022-09-17T03:09:06Z","abstract_excerpt":"Deep reinforcement learning (DRL) has been proven its efficiency in capturing users' dynamic interests in recent literature. However, training a DRL agent is challenging, because of the sparse environment in recommender systems (RS), DRL agents could spend times either exploring informative user-item interaction trajectories or using existing trajectories for policy learning. It is also known as the exploration and exploitation trade-off which affects the recommendation performance significantly when the environment is sparse. It is more challenging to balance the exploration and exploitation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08228","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/2209.08228/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":"2026-07-05T04:58:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M5KZM9tTzBLg9Mq5kVtGbBDQ6wBOYB+9MDAUbh0h9F9fKudlbCeeZJhhFv5LYBaTlBi1nClsh5qCpJbm9pX6Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:14:19.170092Z"},"content_sha256":"5fac2927bf88a8f2cfe2a5df24aa2d57896db1f6d24dd29e3b1bf078bf3c574b","schema_version":"1.0","event_id":"sha256:5fac2927bf88a8f2cfe2a5df24aa2d57896db1f6d24dd29e3b1bf078bf3c574b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B5MX465YZGY64CUITUFSBOI677/bundle.json","state_url":"https://pith.science/pith/B5MX465YZGY64CUITUFSBOI677/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B5MX465YZGY64CUITUFSBOI677/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":"2026-07-07T06:14:19Z","links":{"resolver":"https://pith.science/pith/B5MX465YZGY64CUITUFSBOI677","bundle":"https://pith.science/pith/B5MX465YZGY64CUITUFSBOI677/bundle.json","state":"https://pith.science/pith/B5MX465YZGY64CUITUFSBOI677/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B5MX465YZGY64CUITUFSBOI677/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:B5MX465YZGY64CUITUFSBOI677","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":"185853013a16145c30d359103af0d994d4618c47d4c89cdaf49610d8b68a5337","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-09-17T03:09:06Z","title_canon_sha256":"749acdfda847b193bbd954765f2250c578e65ee4685c8e31bbbc61768fa441cd"},"schema_version":"1.0","source":{"id":"2209.08228","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.08228","created_at":"2026-07-05T04:58:18Z"},{"alias_kind":"arxiv_version","alias_value":"2209.08228v1","created_at":"2026-07-05T04:58:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08228","created_at":"2026-07-05T04:58:18Z"},{"alias_kind":"pith_short_12","alias_value":"B5MX465YZGY6","created_at":"2026-07-05T04:58:18Z"},{"alias_kind":"pith_short_16","alias_value":"B5MX465YZGY64CUI","created_at":"2026-07-05T04:58:18Z"},{"alias_kind":"pith_short_8","alias_value":"B5MX465Y","created_at":"2026-07-05T04:58:18Z"}],"graph_snapshots":[{"event_id":"sha256:5fac2927bf88a8f2cfe2a5df24aa2d57896db1f6d24dd29e3b1bf078bf3c574b","target":"graph","created_at":"2026-07-05T04:58:18Z","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/2209.08228/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (DRL) has been proven its efficiency in capturing users' dynamic interests in recent literature. However, training a DRL agent is challenging, because of the sparse environment in recommender systems (RS), DRL agents could spend times either exploring informative user-item interaction trajectories or using existing trajectories for policy learning. It is also known as the exploration and exploitation trade-off which affects the recommendation performance significantly when the environment is sparse. It is more challenging to balance the exploration and exploitation ","authors_text":"Lianyong Qi, Lina Yao, Siyu Wang, Xiaocong Chen, Yong Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-09-17T03:09:06Z","title":"Intrinsically Motivated Reinforcement Learning based Recommendation with Counterfactual Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08228","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":"sha256:33eb3407cbe9ed3140ccb641f3c326c1b18adba3d1c69e1330afa25f5709eaf6","target":"record","created_at":"2026-07-05T04:58:18Z","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":"185853013a16145c30d359103af0d994d4618c47d4c89cdaf49610d8b68a5337","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-09-17T03:09:06Z","title_canon_sha256":"749acdfda847b193bbd954765f2250c578e65ee4685c8e31bbbc61768fa441cd"},"schema_version":"1.0","source":{"id":"2209.08228","kind":"arxiv","version":1}},"canonical_sha256":"0f597e7bb8c9b1ee0a889d0b20b91effc2a2b2421f93a9117e15ccc94ab920bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f597e7bb8c9b1ee0a889d0b20b91effc2a2b2421f93a9117e15ccc94ab920bf","first_computed_at":"2026-07-05T04:58:18.735898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:58:18.735898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7kHRTMYZzx+ussUCmzAGKuoEDLuKggUB2ryJMMRd2EKCG5yCq2xzrprA4iQLftQeMG119Rn1lXOuW9H0UR4NBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:58:18.736360Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.08228","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33eb3407cbe9ed3140ccb641f3c326c1b18adba3d1c69e1330afa25f5709eaf6","sha256:5fac2927bf88a8f2cfe2a5df24aa2d57896db1f6d24dd29e3b1bf078bf3c574b"],"state_sha256":"8be25e1ef26b6b4f81bdaa0b7ae8e0c0f656dc28add25c06e4a8d5d550a296f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zscP1wTp+IBM9eQ5VZbXuYax4F8DhSKQ2p2I1w9A7v8kEO91ILpsFPu3ON8/CNRowvES8MbyE7V+STZDNv6yDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:14:19.172074Z","bundle_sha256":"ca7a33a4a7cd48bc6546c31dfd28e2a50b848b5ef287b928df270b1e217a6ce7"}}