{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:3TSI63BZCJ3IYX2ONAG56WUQOE","short_pith_number":"pith:3TSI63BZ","canonical_record":{"source":{"id":"2012.02476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T08:58:35Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"9a04cbb4dfb7dd1b1e0cea19634f1f87ad75a86e6079637eae5a66fa5cd6fe55","abstract_canon_sha256":"307d3b2291603c8eb6247f1bc2645e64aea5cc84088efdd23ddc80723754d72b"},"schema_version":"1.0"},"canonical_sha256":"dce48f6c3912768c5f4e680ddf5a90711bc145611744fa0990aca686b2a531fc","source":{"kind":"arxiv","id":"2012.02476","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02476","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02476v1","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02476","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"pith_short_12","alias_value":"3TSI63BZCJ3I","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"pith_short_16","alias_value":"3TSI63BZCJ3IYX2O","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"pith_short_8","alias_value":"3TSI63BZ","created_at":"2026-07-05T01:56:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:3TSI63BZCJ3IYX2ONAG56WUQOE","target":"record","payload":{"canonical_record":{"source":{"id":"2012.02476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T08:58:35Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"9a04cbb4dfb7dd1b1e0cea19634f1f87ad75a86e6079637eae5a66fa5cd6fe55","abstract_canon_sha256":"307d3b2291603c8eb6247f1bc2645e64aea5cc84088efdd23ddc80723754d72b"},"schema_version":"1.0"},"canonical_sha256":"dce48f6c3912768c5f4e680ddf5a90711bc145611744fa0990aca686b2a531fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:59.995928Z","signature_b64":"UT+bcYAiYEAfPrFOMrKFBLqD37Vg1gbnzWpJ7NN5nLqbrCiK53/uHyOP+S2p1J7wpDNTC11nE68BHjiYurTcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dce48f6c3912768c5f4e680ddf5a90711bc145611744fa0990aca686b2a531fc","last_reissued_at":"2026-07-05T01:56:59.995481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:59.995481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.02476","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":"2026-07-05T01:56:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kUx2HdUq1QWdYSZT804Cn1C0Xn0bmtTD4W/HVVq4i0cf/BQDVSBa8ZhNP1H9HBFi99pmx53ykBe1lLDNc0ZJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T00:41:35.516241Z"},"content_sha256":"8f5c28f7b08d28b274ad23579c745256f3dde14ec94aa0e18b22eda1a1bd6d3b","schema_version":"1.0","event_id":"sha256:8f5c28f7b08d28b274ad23579c745256f3dde14ec94aa0e18b22eda1a1bd6d3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:3TSI63BZCJ3IYX2ONAG56WUQOE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Meta-level Model-based Reinforcement Learning Approach for Cold-Start Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Li Li, Rui Chen, Tong Xu, Yanan Wang, Yong Ge","submitted_at":"2020-12-04T08:58:35Z","abstract_excerpt":"Reinforcement learning (RL) has shown great promise in optimizing long-term user interest in recommender systems. However, existing RL-based recommendation methods need a large number of interactions for each user to learn a robust recommendation policy. The challenge becomes more critical when recommending to new users who have a limited number of interactions. To that end, in this paper, we address the cold-start challenge in the RL-based recommender systems by proposing a meta-level model-based reinforcement learning approach for fast user adaptation. In our approach, we learn to infer each"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02476","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/2012.02476/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":"2026-07-05T01:56:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kgbvTdRe+KwS7mVL1JTpkblkiV10G2eOtZZ1VqygQCBnWyIDE/aGj2Vsa/C7Q+VfwYqfXC0tbVFdHb3rFRNZDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T00:41:35.517454Z"},"content_sha256":"b93d4e473ef3da740ab6d1f795bb33bf7c84e37fbeee1e70b4b4513cfc4381bd","schema_version":"1.0","event_id":"sha256:b93d4e473ef3da740ab6d1f795bb33bf7c84e37fbeee1e70b4b4513cfc4381bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3TSI63BZCJ3IYX2ONAG56WUQOE/bundle.json","state_url":"https://pith.science/pith/3TSI63BZCJ3IYX2ONAG56WUQOE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3TSI63BZCJ3IYX2ONAG56WUQOE/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":"2026-08-17T00:41:35Z","links":{"resolver":"https://pith.science/pith/3TSI63BZCJ3IYX2ONAG56WUQOE","bundle":"https://pith.science/pith/3TSI63BZCJ3IYX2ONAG56WUQOE/bundle.json","state":"https://pith.science/pith/3TSI63BZCJ3IYX2ONAG56WUQOE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3TSI63BZCJ3IYX2ONAG56WUQOE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3TSI63BZCJ3IYX2ONAG56WUQOE","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":"307d3b2291603c8eb6247f1bc2645e64aea5cc84088efdd23ddc80723754d72b","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T08:58:35Z","title_canon_sha256":"9a04cbb4dfb7dd1b1e0cea19634f1f87ad75a86e6079637eae5a66fa5cd6fe55"},"schema_version":"1.0","source":{"id":"2012.02476","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02476","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02476v1","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02476","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"pith_short_12","alias_value":"3TSI63BZCJ3I","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"pith_short_16","alias_value":"3TSI63BZCJ3IYX2O","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"pith_short_8","alias_value":"3TSI63BZ","created_at":"2026-07-05T01:56:59Z"}],"graph_snapshots":[{"event_id":"sha256:b93d4e473ef3da740ab6d1f795bb33bf7c84e37fbeee1e70b4b4513cfc4381bd","target":"graph","created_at":"2026-07-05T01:56:59Z","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/2012.02476/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has shown great promise in optimizing long-term user interest in recommender systems. However, existing RL-based recommendation methods need a large number of interactions for each user to learn a robust recommendation policy. The challenge becomes more critical when recommending to new users who have a limited number of interactions. To that end, in this paper, we address the cold-start challenge in the RL-based recommender systems by proposing a meta-level model-based reinforcement learning approach for fast user adaptation. In our approach, we learn to infer each","authors_text":"Li Li, Rui Chen, Tong Xu, Yanan Wang, Yong Ge","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T08:58:35Z","title":"Offline Meta-level Model-based Reinforcement Learning Approach for Cold-Start Recommendation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02476","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":"sha256:8f5c28f7b08d28b274ad23579c745256f3dde14ec94aa0e18b22eda1a1bd6d3b","target":"record","created_at":"2026-07-05T01:56:59Z","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":"307d3b2291603c8eb6247f1bc2645e64aea5cc84088efdd23ddc80723754d72b","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T08:58:35Z","title_canon_sha256":"9a04cbb4dfb7dd1b1e0cea19634f1f87ad75a86e6079637eae5a66fa5cd6fe55"},"schema_version":"1.0","source":{"id":"2012.02476","kind":"arxiv","version":1}},"canonical_sha256":"dce48f6c3912768c5f4e680ddf5a90711bc145611744fa0990aca686b2a531fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dce48f6c3912768c5f4e680ddf5a90711bc145611744fa0990aca686b2a531fc","first_computed_at":"2026-07-05T01:56:59.995481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:56:59.995481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UT+bcYAiYEAfPrFOMrKFBLqD37Vg1gbnzWpJ7NN5nLqbrCiK53/uHyOP+S2p1J7wpDNTC11nE68BHjiYurTcBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:56:59.995928Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.02476","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f5c28f7b08d28b274ad23579c745256f3dde14ec94aa0e18b22eda1a1bd6d3b","sha256:b93d4e473ef3da740ab6d1f795bb33bf7c84e37fbeee1e70b4b4513cfc4381bd"],"state_sha256":"67e2b382207efd0f4b79d8b7828f2df366fccaa8ff86138bddff79ed475cdc75"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yqyMAKjgkc4mDf7xLXaGXZoMgt00W6cu6xlvlqUqMo25886PiG9UfM2ePRFUSALMh+K8yXQiCtkk/83OL6FdAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T00:41:35.524311Z","bundle_sha256":"fa8604ebad9edd9b855a450b43efd60500e0cc77f86919bc4c6c7607e7319cec"}}