{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5UTC4TNSKEGCMDRFW3B4AHABWH","short_pith_number":"pith:5UTC4TNS","canonical_record":{"source":{"id":"2212.11431","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-22T00:47:40Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"8ca73747f12b6f495de89ece7524649df4b3fc9b1e5d9d330e677459273c6bcb","abstract_canon_sha256":"ab10578e05e54554c8f6e4921ed4543a7d7d74466245a16de742675a0542b08e"},"schema_version":"1.0"},"canonical_sha256":"ed262e4db2510c260e25b6c3c01c01b1d405f10d90a706ac00475399e680cf4b","source":{"kind":"arxiv","id":"2212.11431","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.11431","created_at":"2026-07-05T06:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2212.11431v2","created_at":"2026-07-05T06:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.11431","created_at":"2026-07-05T06:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"5UTC4TNSKEGC","created_at":"2026-07-05T06:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"5UTC4TNSKEGCMDRF","created_at":"2026-07-05T06:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"5UTC4TNS","created_at":"2026-07-05T06:04:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5UTC4TNSKEGCMDRFW3B4AHABWH","target":"record","payload":{"canonical_record":{"source":{"id":"2212.11431","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-22T00:47:40Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"8ca73747f12b6f495de89ece7524649df4b3fc9b1e5d9d330e677459273c6bcb","abstract_canon_sha256":"ab10578e05e54554c8f6e4921ed4543a7d7d74466245a16de742675a0542b08e"},"schema_version":"1.0"},"canonical_sha256":"ed262e4db2510c260e25b6c3c01c01b1d405f10d90a706ac00475399e680cf4b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:52.999979Z","signature_b64":"6ua5Pv+hJDz8TW23+812FrmooEsnPHVN6IPRONmOLA8ISltVpAYdN3pmB9fsJvh2WIjgt8uSIP+jlO3DQlrSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed262e4db2510c260e25b6c3c01c01b1d405f10d90a706ac00475399e680cf4b","last_reissued_at":"2026-07-05T06:04:52.999641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:52.999641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.11431","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:04:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FIO5ttG4IQluSWSYSdejmZK5NKiow3RnEdDuxy3hhcXc0cNr/iOQrUjVL5SmYtNG2AGTQvVMbSparVejQwhsCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:20:39.367867Z"},"content_sha256":"baa8924bb197c5bb50ab3ba6374f0cc15211ffbf3798523e36272a64160cc959","schema_version":"1.0","event_id":"sha256:baa8924bb197c5bb50ab3ba6374f0cc15211ffbf3798523e36272a64160cc959"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5UTC4TNSKEGCMDRFW3B4AHABWH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Local Policy Improvement for Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Dawen Liang, Nikos Vlassis","submitted_at":"2022-12-22T00:47:40Z","abstract_excerpt":"Recommender systems predict what items a user will interact with next, based on their past interactions. The problem is often approached through supervised learning, but recent advancements have shifted towards policy optimization of rewards (e.g., user engagement). One challenge with the latter is policy mismatch: we are only able to train a new policy given data collected from a previously-deployed policy. The conventional way to address this problem is through importance sampling correction, but this comes with practical limitations. We suggest an alternative approach of local policy improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.11431","kind":"arxiv","version":2},"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/2212.11431/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":"2026-07-05T06:04:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lDevJpu9bggkkBgeRe4EmKyeo25tTflSI40tCtz0sTI1bRcbDhHCH5enwEF2cqLGzPiev2kTfKLd+Fad76yHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:20:39.368681Z"},"content_sha256":"345ad0f2c9b63f91c3a4a18374e191ec60afdd973ca1dfa8893d1faf96f0f8be","schema_version":"1.0","event_id":"sha256:345ad0f2c9b63f91c3a4a18374e191ec60afdd973ca1dfa8893d1faf96f0f8be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5UTC4TNSKEGCMDRFW3B4AHABWH/bundle.json","state_url":"https://pith.science/pith/5UTC4TNSKEGCMDRFW3B4AHABWH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5UTC4TNSKEGCMDRFW3B4AHABWH/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":"2026-08-05T14:20:39Z","links":{"resolver":"https://pith.science/pith/5UTC4TNSKEGCMDRFW3B4AHABWH","bundle":"https://pith.science/pith/5UTC4TNSKEGCMDRFW3B4AHABWH/bundle.json","state":"https://pith.science/pith/5UTC4TNSKEGCMDRFW3B4AHABWH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5UTC4TNSKEGCMDRFW3B4AHABWH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5UTC4TNSKEGCMDRFW3B4AHABWH","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":"ab10578e05e54554c8f6e4921ed4543a7d7d74466245a16de742675a0542b08e","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-22T00:47:40Z","title_canon_sha256":"8ca73747f12b6f495de89ece7524649df4b3fc9b1e5d9d330e677459273c6bcb"},"schema_version":"1.0","source":{"id":"2212.11431","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.11431","created_at":"2026-07-05T06:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2212.11431v2","created_at":"2026-07-05T06:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.11431","created_at":"2026-07-05T06:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"5UTC4TNSKEGC","created_at":"2026-07-05T06:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"5UTC4TNSKEGCMDRF","created_at":"2026-07-05T06:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"5UTC4TNS","created_at":"2026-07-05T06:04:52Z"}],"graph_snapshots":[{"event_id":"sha256:345ad0f2c9b63f91c3a4a18374e191ec60afdd973ca1dfa8893d1faf96f0f8be","target":"graph","created_at":"2026-07-05T06:04:52Z","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/2212.11431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recommender systems predict what items a user will interact with next, based on their past interactions. The problem is often approached through supervised learning, but recent advancements have shifted towards policy optimization of rewards (e.g., user engagement). One challenge with the latter is policy mismatch: we are only able to train a new policy given data collected from a previously-deployed policy. The conventional way to address this problem is through importance sampling correction, but this comes with practical limitations. We suggest an alternative approach of local policy improv","authors_text":"Dawen Liang, Nikos Vlassis","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-22T00:47:40Z","title":"Local Policy Improvement for Recommender Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.11431","kind":"arxiv","version":2},"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:baa8924bb197c5bb50ab3ba6374f0cc15211ffbf3798523e36272a64160cc959","target":"record","created_at":"2026-07-05T06:04:52Z","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":"ab10578e05e54554c8f6e4921ed4543a7d7d74466245a16de742675a0542b08e","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-22T00:47:40Z","title_canon_sha256":"8ca73747f12b6f495de89ece7524649df4b3fc9b1e5d9d330e677459273c6bcb"},"schema_version":"1.0","source":{"id":"2212.11431","kind":"arxiv","version":2}},"canonical_sha256":"ed262e4db2510c260e25b6c3c01c01b1d405f10d90a706ac00475399e680cf4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed262e4db2510c260e25b6c3c01c01b1d405f10d90a706ac00475399e680cf4b","first_computed_at":"2026-07-05T06:04:52.999641Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:04:52.999641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6ua5Pv+hJDz8TW23+812FrmooEsnPHVN6IPRONmOLA8ISltVpAYdN3pmB9fsJvh2WIjgt8uSIP+jlO3DQlrSBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:04:52.999979Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.11431","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:baa8924bb197c5bb50ab3ba6374f0cc15211ffbf3798523e36272a64160cc959","sha256:345ad0f2c9b63f91c3a4a18374e191ec60afdd973ca1dfa8893d1faf96f0f8be"],"state_sha256":"3a678bb9bc7d39fd31bc391aee3c3e89cb015c2dd964879e7d9f9a0d26a5e472"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ng11ZlWbV9Gyxe8yL4XwC1u68jie2/9AGkwjyO5OADBIWvogUTAOfLyEZwQxype+/8GEd7B18/u/lpf4lYQSDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T14:20:39.393588Z","bundle_sha256":"0b08971a05a3c3509a23bf1f217e232f3f0c87a2f596355840311b3d693ea6ae"}}