{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:AA6BBL3EISFJWKWXUQIVFEORSY","short_pith_number":"pith:AA6BBL3E","canonical_record":{"source":{"id":"1812.02353","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T05:10:27Z","cross_cats_sorted":["cs.IR","stat.ML"],"title_canon_sha256":"9f855e10bc639a735a8384394f87d91b0b4f2a5eeb7af9eff8cc59762e1f8d13","abstract_canon_sha256":"96533695807d3f26f0d125827320bd2f53b8469e8d56d514b81ebd5aa8d28b5c"},"schema_version":"1.0"},"canonical_sha256":"003c10af64448a9b2ad7a4115291d19638838fb3eddd67ed748df437e01e55b2","source":{"kind":"arxiv","id":"1812.02353","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02353","created_at":"2026-07-05T03:41:00Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02353v3","created_at":"2026-07-05T03:41:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02353","created_at":"2026-07-05T03:41:00Z"},{"alias_kind":"pith_short_12","alias_value":"AA6BBL3EISFJ","created_at":"2026-07-05T03:41:00Z"},{"alias_kind":"pith_short_16","alias_value":"AA6BBL3EISFJWKWX","created_at":"2026-07-05T03:41:00Z"},{"alias_kind":"pith_short_8","alias_value":"AA6BBL3E","created_at":"2026-07-05T03:41:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:AA6BBL3EISFJWKWXUQIVFEORSY","target":"record","payload":{"canonical_record":{"source":{"id":"1812.02353","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T05:10:27Z","cross_cats_sorted":["cs.IR","stat.ML"],"title_canon_sha256":"9f855e10bc639a735a8384394f87d91b0b4f2a5eeb7af9eff8cc59762e1f8d13","abstract_canon_sha256":"96533695807d3f26f0d125827320bd2f53b8469e8d56d514b81ebd5aa8d28b5c"},"schema_version":"1.0"},"canonical_sha256":"003c10af64448a9b2ad7a4115291d19638838fb3eddd67ed748df437e01e55b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:00.881409Z","signature_b64":"Rp2/En5qkQJEa7GJOE3aM/R5nOjcPSrNIpqXDBDpCXSnq/oofiC1Do3jstQFfeUW3FtkFbkEW5svSAG71fXXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"003c10af64448a9b2ad7a4115291d19638838fb3eddd67ed748df437e01e55b2","last_reissued_at":"2026-07-05T03:41:00.880920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:00.880920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.02353","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:41:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jj9aTIsvxJdOSRAOWzlFZdWHETaYqMkbS67Kg1lZCb3IMLPkLHzvRiTu10hqMtEOqxejzXInFhIoaEwZbkFJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:16:01.417151Z"},"content_sha256":"7cf445404fc117907af44b4858f427dc81f4782cd83c748662d10dcd7d76b903","schema_version":"1.0","event_id":"sha256:7cf445404fc117907af44b4858f427dc81f4782cd83c748662d10dcd7d76b903"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:AA6BBL3EISFJWKWXUQIVFEORSY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Top-K Off-Policy Correction for a REINFORCE Recommender System","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Beutel, Ed Chi, Francois Belletti, Minmin Chen, Paul Covington, Sagar Jain","submitted_at":"2018-12-06T05:10:27Z","abstract_excerpt":"Industrial recommender systems deal with extremely large action spaces -- many millions of items to recommend. Moreover, they need to serve billions of users, who are unique at any point in time, making a complex user state space. Luckily, huge quantities of logged implicit feedback (e.g., user clicks, dwell time) are available for learning. Learning from the logged feedback is however subject to biases caused by only observing feedback on recommendations selected by the previous versions of the recommender. In this work, we present a general recipe of addressing such biases in a production to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02353","kind":"arxiv","version":3},"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/1812.02353/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":"2026-07-05T03:41:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VqVQNaaekdRrPdmPvlzqkl9LwhHEgL1jc1me/3f+8WkYhz0Th+nYY6udz3Pm1mCXrHF0j8RXNcmYoGRAEmYQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:16:01.417536Z"},"content_sha256":"58d227bb87b093afa546032da7cb3a805fec56b8fe7f0b0165e7e0e316cf0aed","schema_version":"1.0","event_id":"sha256:58d227bb87b093afa546032da7cb3a805fec56b8fe7f0b0165e7e0e316cf0aed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AA6BBL3EISFJWKWXUQIVFEORSY/bundle.json","state_url":"https://pith.science/pith/AA6BBL3EISFJWKWXUQIVFEORSY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AA6BBL3EISFJWKWXUQIVFEORSY/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":"2026-07-07T11:16:01Z","links":{"resolver":"https://pith.science/pith/AA6BBL3EISFJWKWXUQIVFEORSY","bundle":"https://pith.science/pith/AA6BBL3EISFJWKWXUQIVFEORSY/bundle.json","state":"https://pith.science/pith/AA6BBL3EISFJWKWXUQIVFEORSY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AA6BBL3EISFJWKWXUQIVFEORSY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:AA6BBL3EISFJWKWXUQIVFEORSY","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":"96533695807d3f26f0d125827320bd2f53b8469e8d56d514b81ebd5aa8d28b5c","cross_cats_sorted":["cs.IR","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T05:10:27Z","title_canon_sha256":"9f855e10bc639a735a8384394f87d91b0b4f2a5eeb7af9eff8cc59762e1f8d13"},"schema_version":"1.0","source":{"id":"1812.02353","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02353","created_at":"2026-07-05T03:41:00Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02353v3","created_at":"2026-07-05T03:41:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02353","created_at":"2026-07-05T03:41:00Z"},{"alias_kind":"pith_short_12","alias_value":"AA6BBL3EISFJ","created_at":"2026-07-05T03:41:00Z"},{"alias_kind":"pith_short_16","alias_value":"AA6BBL3EISFJWKWX","created_at":"2026-07-05T03:41:00Z"},{"alias_kind":"pith_short_8","alias_value":"AA6BBL3E","created_at":"2026-07-05T03:41:00Z"}],"graph_snapshots":[{"event_id":"sha256:58d227bb87b093afa546032da7cb3a805fec56b8fe7f0b0165e7e0e316cf0aed","target":"graph","created_at":"2026-07-05T03:41:00Z","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/1812.02353/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Industrial recommender systems deal with extremely large action spaces -- many millions of items to recommend. Moreover, they need to serve billions of users, who are unique at any point in time, making a complex user state space. Luckily, huge quantities of logged implicit feedback (e.g., user clicks, dwell time) are available for learning. Learning from the logged feedback is however subject to biases caused by only observing feedback on recommendations selected by the previous versions of the recommender. In this work, we present a general recipe of addressing such biases in a production to","authors_text":"Alex Beutel, Ed Chi, Francois Belletti, Minmin Chen, Paul Covington, Sagar Jain","cross_cats":["cs.IR","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T05:10:27Z","title":"Top-K Off-Policy Correction for a REINFORCE Recommender System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02353","kind":"arxiv","version":3},"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":"sha256:7cf445404fc117907af44b4858f427dc81f4782cd83c748662d10dcd7d76b903","target":"record","created_at":"2026-07-05T03:41:00Z","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":"96533695807d3f26f0d125827320bd2f53b8469e8d56d514b81ebd5aa8d28b5c","cross_cats_sorted":["cs.IR","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T05:10:27Z","title_canon_sha256":"9f855e10bc639a735a8384394f87d91b0b4f2a5eeb7af9eff8cc59762e1f8d13"},"schema_version":"1.0","source":{"id":"1812.02353","kind":"arxiv","version":3}},"canonical_sha256":"003c10af64448a9b2ad7a4115291d19638838fb3eddd67ed748df437e01e55b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"003c10af64448a9b2ad7a4115291d19638838fb3eddd67ed748df437e01e55b2","first_computed_at":"2026-07-05T03:41:00.880920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:41:00.880920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rp2/En5qkQJEa7GJOE3aM/R5nOjcPSrNIpqXDBDpCXSnq/oofiC1Do3jstQFfeUW3FtkFbkEW5svSAG71fXXCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:41:00.881409Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.02353","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cf445404fc117907af44b4858f427dc81f4782cd83c748662d10dcd7d76b903","sha256:58d227bb87b093afa546032da7cb3a805fec56b8fe7f0b0165e7e0e316cf0aed"],"state_sha256":"32f380e348ecb8535e3a6e2f2c7d0062930c0213fec8a9a7a166ac6a044c0f98"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U42WjXz0zCX1oN7R4KGVAWdDJgONqPfA1thctDyOHuk6rzmaXkZJyOXvXfTF4B/EgD7T14yDsr5Xcj6gmWbmBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:16:01.419481Z","bundle_sha256":"8d066be9a9587bb6d24b59dd7428ae4f853afcc3ac39bb96e4bb51eeeb009710"}}