{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DKHZCQBNCQ45C7YNJS7G3H4ZDP","short_pith_number":"pith:DKHZCQBN","canonical_record":{"source":{"id":"2212.04720","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-09T08:26:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"615cd9035d171b9e11042ab091daea46ff4dec7ac4f9df574a321009720c0f3c","abstract_canon_sha256":"467d83841726e211d5399c3efaa4f7b105446ea245c91e9723e2cf582b234c60"},"schema_version":"1.0"},"canonical_sha256":"1a8f91402d1439d17f0d4cbe6d9f991bd366d7919bc6aebd3c06656f4b2e3f40","source":{"kind":"arxiv","id":"2212.04720","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.04720","created_at":"2026-07-05T05:23:50Z"},{"alias_kind":"arxiv_version","alias_value":"2212.04720v1","created_at":"2026-07-05T05:23:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04720","created_at":"2026-07-05T05:23:50Z"},{"alias_kind":"pith_short_12","alias_value":"DKHZCQBNCQ45","created_at":"2026-07-05T05:23:50Z"},{"alias_kind":"pith_short_16","alias_value":"DKHZCQBNCQ45C7YN","created_at":"2026-07-05T05:23:50Z"},{"alias_kind":"pith_short_8","alias_value":"DKHZCQBN","created_at":"2026-07-05T05:23:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DKHZCQBNCQ45C7YNJS7G3H4ZDP","target":"record","payload":{"canonical_record":{"source":{"id":"2212.04720","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-09T08:26:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"615cd9035d171b9e11042ab091daea46ff4dec7ac4f9df574a321009720c0f3c","abstract_canon_sha256":"467d83841726e211d5399c3efaa4f7b105446ea245c91e9723e2cf582b234c60"},"schema_version":"1.0"},"canonical_sha256":"1a8f91402d1439d17f0d4cbe6d9f991bd366d7919bc6aebd3c06656f4b2e3f40","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:50.809922Z","signature_b64":"GQxL7wTTOnWrWLgMokL3wlwHMnmJe2V69Xg5rN+Iy0cV5ZpTJvsZL4qOmgsqbywz/ORm30YoILHjQGOiAOFWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a8f91402d1439d17f0d4cbe6d9f991bd366d7919bc6aebd3c06656f4b2e3f40","last_reissued_at":"2026-07-05T05:23:50.809569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:50.809569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.04720","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":"2026-07-05T05:23:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gOZ5x+qHY6v/l3fnYBjR0Sb4DsM9ZHcdWvxeRGNam9xLTAMJNAtiaxhnxR9fXDuXfJgYVYgiM2cju9+TUgHlDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:48:54.789933Z"},"content_sha256":"1ccf6d84509ccef3bbaad7f1f4ea94f88d4f50b94a40588eb4fab736a18b9de1","schema_version":"1.0","event_id":"sha256:1ccf6d84509ccef3bbaad7f1f4ea94f88d4f50b94a40588eb4fab736a18b9de1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DKHZCQBNCQ45C7YNJS7G3H4ZDP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Task Off-Policy Learning from Bandit Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Branislav Kveton, Joey Hong, Manzil Zaheer, Mohammad Ghavamzadeh, Sumeet Katariya","submitted_at":"2022-12-09T08:26:27Z","abstract_excerpt":"Many practical applications, such as recommender systems and learning to rank, involve solving multiple similar tasks. One example is learning of recommendation policies for users with similar movie preferences, where the users may still rank the individual movies slightly differently. Such tasks can be organized in a hierarchy, where similar tasks are related through a shared structure. In this work, we formulate this problem as a contextual off-policy optimization in a hierarchical graphical model from logged bandit feedback. To solve the problem, we propose a hierarchical off-policy optimiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04720","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/2212.04720/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":"2026-07-05T05:23:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eKedJxO/SD1HlhDsrRkphU/jXCbjbjKJwdRAUF/wGkrIAAIgXjx5g99QAxan3ttiF2mc3cJi30YFK2lLRTzyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:48:54.790891Z"},"content_sha256":"4b27db819a6873cb832958e39b43d818b731dd1382ef4aa069ab97f209125736","schema_version":"1.0","event_id":"sha256:4b27db819a6873cb832958e39b43d818b731dd1382ef4aa069ab97f209125736"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DKHZCQBNCQ45C7YNJS7G3H4ZDP/bundle.json","state_url":"https://pith.science/pith/DKHZCQBNCQ45C7YNJS7G3H4ZDP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DKHZCQBNCQ45C7YNJS7G3H4ZDP/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":"2026-08-04T16:48:54Z","links":{"resolver":"https://pith.science/pith/DKHZCQBNCQ45C7YNJS7G3H4ZDP","bundle":"https://pith.science/pith/DKHZCQBNCQ45C7YNJS7G3H4ZDP/bundle.json","state":"https://pith.science/pith/DKHZCQBNCQ45C7YNJS7G3H4ZDP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DKHZCQBNCQ45C7YNJS7G3H4ZDP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DKHZCQBNCQ45C7YNJS7G3H4ZDP","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":"467d83841726e211d5399c3efaa4f7b105446ea245c91e9723e2cf582b234c60","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-09T08:26:27Z","title_canon_sha256":"615cd9035d171b9e11042ab091daea46ff4dec7ac4f9df574a321009720c0f3c"},"schema_version":"1.0","source":{"id":"2212.04720","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.04720","created_at":"2026-07-05T05:23:50Z"},{"alias_kind":"arxiv_version","alias_value":"2212.04720v1","created_at":"2026-07-05T05:23:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04720","created_at":"2026-07-05T05:23:50Z"},{"alias_kind":"pith_short_12","alias_value":"DKHZCQBNCQ45","created_at":"2026-07-05T05:23:50Z"},{"alias_kind":"pith_short_16","alias_value":"DKHZCQBNCQ45C7YN","created_at":"2026-07-05T05:23:50Z"},{"alias_kind":"pith_short_8","alias_value":"DKHZCQBN","created_at":"2026-07-05T05:23:50Z"}],"graph_snapshots":[{"event_id":"sha256:4b27db819a6873cb832958e39b43d818b731dd1382ef4aa069ab97f209125736","target":"graph","created_at":"2026-07-05T05:23:50Z","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/2212.04720/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many practical applications, such as recommender systems and learning to rank, involve solving multiple similar tasks. One example is learning of recommendation policies for users with similar movie preferences, where the users may still rank the individual movies slightly differently. Such tasks can be organized in a hierarchy, where similar tasks are related through a shared structure. In this work, we formulate this problem as a contextual off-policy optimization in a hierarchical graphical model from logged bandit feedback. To solve the problem, we propose a hierarchical off-policy optimiz","authors_text":"Branislav Kveton, Joey Hong, Manzil Zaheer, Mohammad Ghavamzadeh, Sumeet Katariya","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-09T08:26:27Z","title":"Multi-Task Off-Policy Learning from Bandit Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04720","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":"sha256:1ccf6d84509ccef3bbaad7f1f4ea94f88d4f50b94a40588eb4fab736a18b9de1","target":"record","created_at":"2026-07-05T05:23:50Z","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":"467d83841726e211d5399c3efaa4f7b105446ea245c91e9723e2cf582b234c60","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-09T08:26:27Z","title_canon_sha256":"615cd9035d171b9e11042ab091daea46ff4dec7ac4f9df574a321009720c0f3c"},"schema_version":"1.0","source":{"id":"2212.04720","kind":"arxiv","version":1}},"canonical_sha256":"1a8f91402d1439d17f0d4cbe6d9f991bd366d7919bc6aebd3c06656f4b2e3f40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a8f91402d1439d17f0d4cbe6d9f991bd366d7919bc6aebd3c06656f4b2e3f40","first_computed_at":"2026-07-05T05:23:50.809569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:23:50.809569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GQxL7wTTOnWrWLgMokL3wlwHMnmJe2V69Xg5rN+Iy0cV5ZpTJvsZL4qOmgsqbywz/ORm30YoILHjQGOiAOFWAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:23:50.809922Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.04720","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ccf6d84509ccef3bbaad7f1f4ea94f88d4f50b94a40588eb4fab736a18b9de1","sha256:4b27db819a6873cb832958e39b43d818b731dd1382ef4aa069ab97f209125736"],"state_sha256":"f1211ef73879b4c6bbd7d46b6c85791c21951f6e8d3aba4f2c89fea494b230e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R+06srGXLa+qSuBA+mDZcwlhlzOKDtH761Ma5HLZSOFSlvZjugzirqUymDahsN2D9QhZc0QmzG2HXfC1YlxnBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:48:54.796808Z","bundle_sha256":"d2a222680517003ff3b76ba6459fd00bef4c7f0eeef03fd4a6cad391e5191798"}}