{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:KIK5NYZL7QCTBOHVJ54BOB3HED","short_pith_number":"pith:KIK5NYZL","canonical_record":{"source":{"id":"2109.12509","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-09-26T06:54:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bb948ad4a5ad5e5c175a4766610eb71e8261a300d351029d7bf78ecc827dd847","abstract_canon_sha256":"2eadb125aa5f7975c20c9ef5fdd7bdc4b1aada443addcd8e6de488f2d3bbf6d1"},"schema_version":"1.0"},"canonical_sha256":"5215d6e32bfc0530b8f54f7817076720c28ae0654481457b6adb57f49521509c","source":{"kind":"arxiv","id":"2109.12509","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.12509","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"arxiv_version","alias_value":"2109.12509v4","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.12509","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"pith_short_12","alias_value":"KIK5NYZL7QCT","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"pith_short_16","alias_value":"KIK5NYZL7QCTBOHV","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"pith_short_8","alias_value":"KIK5NYZL","created_at":"2026-07-05T06:35:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:KIK5NYZL7QCTBOHVJ54BOB3HED","target":"record","payload":{"canonical_record":{"source":{"id":"2109.12509","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-09-26T06:54:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bb948ad4a5ad5e5c175a4766610eb71e8261a300d351029d7bf78ecc827dd847","abstract_canon_sha256":"2eadb125aa5f7975c20c9ef5fdd7bdc4b1aada443addcd8e6de488f2d3bbf6d1"},"schema_version":"1.0"},"canonical_sha256":"5215d6e32bfc0530b8f54f7817076720c28ae0654481457b6adb57f49521509c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:42.272776Z","signature_b64":"yN7N0DsuHq7KXkwQ1UbK3009NuzO3JBQ5IK3VTBntig9kP7MVuZ3/pSfC0DX9cnpTkkx4CoJh8UigJ2kuKUBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5215d6e32bfc0530b8f54f7817076720c28ae0654481457b6adb57f49521509c","last_reissued_at":"2026-07-05T06:35:42.272240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:42.272240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.12509","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:35:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W4h925LHzWzWzcW6Hal1hOzHefT0EL6jWvBx/8nUqWyuseOeCqXIrZNq6Gk3/YEa33rZTgxuW8hA0j+t9HAaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:56:04.281715Z"},"content_sha256":"f98151635213f34fe88b138e0a8a2f4273a09a56f3ca51f8d908effc14e93f61","schema_version":"1.0","event_id":"sha256:f98151635213f34fe88b138e0a8a2f4273a09a56f3ca51f8d908effc14e93f61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:KIK5NYZL7QCTBOHVJ54BOB3HED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Exploration for Recommendation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Benjamin Van Roy, Zheqing Zhu","submitted_at":"2021-09-26T06:54:26Z","abstract_excerpt":"Modern recommendation systems ought to benefit by probing for and learning from delayed feedback. Research has tended to focus on learning from a user's response to a single recommendation. Such work, which leverages methods of supervised and bandit learning, forgoes learning from the user's subsequent behavior. Where past work has aimed to learn from subsequent behavior, there has been a lack of effective methods for probing to elicit informative delayed feedback. Effective exploration through probing for delayed feedback becomes particularly challenging when rewards are sparse. To address th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.12509","kind":"arxiv","version":4},"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/2109.12509/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":"2026-07-05T06:35:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Wmu+ho7vU4HO+eKP9wEE/fq9y8SyfxD0R7D9Lh2/LDqnMWdAwes5E32/vbrwueLYN8RSulkO+d6cJJOdpg/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:56:04.282240Z"},"content_sha256":"e8bda2500f19a49a1a2bc1172d75138a0291f112180b5cebd05d18e66618ed51","schema_version":"1.0","event_id":"sha256:e8bda2500f19a49a1a2bc1172d75138a0291f112180b5cebd05d18e66618ed51"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KIK5NYZL7QCTBOHVJ54BOB3HED/bundle.json","state_url":"https://pith.science/pith/KIK5NYZL7QCTBOHVJ54BOB3HED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KIK5NYZL7QCTBOHVJ54BOB3HED/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":"2026-08-15T22:56:04Z","links":{"resolver":"https://pith.science/pith/KIK5NYZL7QCTBOHVJ54BOB3HED","bundle":"https://pith.science/pith/KIK5NYZL7QCTBOHVJ54BOB3HED/bundle.json","state":"https://pith.science/pith/KIK5NYZL7QCTBOHVJ54BOB3HED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KIK5NYZL7QCTBOHVJ54BOB3HED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KIK5NYZL7QCTBOHVJ54BOB3HED","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":"2eadb125aa5f7975c20c9ef5fdd7bdc4b1aada443addcd8e6de488f2d3bbf6d1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-09-26T06:54:26Z","title_canon_sha256":"bb948ad4a5ad5e5c175a4766610eb71e8261a300d351029d7bf78ecc827dd847"},"schema_version":"1.0","source":{"id":"2109.12509","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.12509","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"arxiv_version","alias_value":"2109.12509v4","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.12509","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"pith_short_12","alias_value":"KIK5NYZL7QCT","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"pith_short_16","alias_value":"KIK5NYZL7QCTBOHV","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"pith_short_8","alias_value":"KIK5NYZL","created_at":"2026-07-05T06:35:42Z"}],"graph_snapshots":[{"event_id":"sha256:e8bda2500f19a49a1a2bc1172d75138a0291f112180b5cebd05d18e66618ed51","target":"graph","created_at":"2026-07-05T06:35:42Z","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/2109.12509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern recommendation systems ought to benefit by probing for and learning from delayed feedback. Research has tended to focus on learning from a user's response to a single recommendation. Such work, which leverages methods of supervised and bandit learning, forgoes learning from the user's subsequent behavior. Where past work has aimed to learn from subsequent behavior, there has been a lack of effective methods for probing to elicit informative delayed feedback. Effective exploration through probing for delayed feedback becomes particularly challenging when rewards are sparse. To address th","authors_text":"Benjamin Van Roy, Zheqing Zhu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-09-26T06:54:26Z","title":"Deep Exploration for Recommendation Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.12509","kind":"arxiv","version":4},"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:f98151635213f34fe88b138e0a8a2f4273a09a56f3ca51f8d908effc14e93f61","target":"record","created_at":"2026-07-05T06:35:42Z","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":"2eadb125aa5f7975c20c9ef5fdd7bdc4b1aada443addcd8e6de488f2d3bbf6d1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-09-26T06:54:26Z","title_canon_sha256":"bb948ad4a5ad5e5c175a4766610eb71e8261a300d351029d7bf78ecc827dd847"},"schema_version":"1.0","source":{"id":"2109.12509","kind":"arxiv","version":4}},"canonical_sha256":"5215d6e32bfc0530b8f54f7817076720c28ae0654481457b6adb57f49521509c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5215d6e32bfc0530b8f54f7817076720c28ae0654481457b6adb57f49521509c","first_computed_at":"2026-07-05T06:35:42.272240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:42.272240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yN7N0DsuHq7KXkwQ1UbK3009NuzO3JBQ5IK3VTBntig9kP7MVuZ3/pSfC0DX9cnpTkkx4CoJh8UigJ2kuKUBBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:42.272776Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.12509","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f98151635213f34fe88b138e0a8a2f4273a09a56f3ca51f8d908effc14e93f61","sha256:e8bda2500f19a49a1a2bc1172d75138a0291f112180b5cebd05d18e66618ed51"],"state_sha256":"7d674484ed038b56e54bf045b5f6e51b0315745da95ef984507953df192cec08"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OCFRHODSQ9xrTc4QSY9vtPunaE84gwgiLkN1Tj77uxFP1244vKhlwbjIKbyR4lV20TofHLxDJ5TBhASusFINAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T22:56:04.287497Z","bundle_sha256":"07b59fad9e3b0f85d7951f3449456f20e5e598463fb853960a37b574b3dcbe6a"}}