{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:H6X5JD7HZ4KFJ6G5FX3PQMLSOR","short_pith_number":"pith:H6X5JD7H","canonical_record":{"source":{"id":"2509.05292","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-05T17:57:45Z","cross_cats_sorted":[],"title_canon_sha256":"4e8c8c4eddcd0df384746fcb1fac70675b4f3d22582d0a6c2764dfa1ed45f5bb","abstract_canon_sha256":"82bfca405b49e1c488379322f4d233510a63b51b30d17ecd6e43a85da81e23cd"},"schema_version":"1.0"},"canonical_sha256":"3fafd48fe7cf1454f8dd2df6f83172745fa875f6ed31b5a76bf40e009cbac0a8","source":{"kind":"arxiv","id":"2509.05292","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05292","created_at":"2026-07-05T12:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05292v1","created_at":"2026-07-05T12:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05292","created_at":"2026-07-05T12:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"H6X5JD7HZ4KF","created_at":"2026-07-05T12:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"H6X5JD7HZ4KFJ6G5","created_at":"2026-07-05T12:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"H6X5JD7H","created_at":"2026-07-05T12:05:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:H6X5JD7HZ4KFJ6G5FX3PQMLSOR","target":"record","payload":{"canonical_record":{"source":{"id":"2509.05292","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-05T17:57:45Z","cross_cats_sorted":[],"title_canon_sha256":"4e8c8c4eddcd0df384746fcb1fac70675b4f3d22582d0a6c2764dfa1ed45f5bb","abstract_canon_sha256":"82bfca405b49e1c488379322f4d233510a63b51b30d17ecd6e43a85da81e23cd"},"schema_version":"1.0"},"canonical_sha256":"3fafd48fe7cf1454f8dd2df6f83172745fa875f6ed31b5a76bf40e009cbac0a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:38.966023Z","signature_b64":"+VDxdayLOu2oLdeUANZki3gfltXW8AdPJfrB2GGrvcvrXrxkADun/P9u6XopYMsLT5G7GNBFnIVC30/8rIofCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fafd48fe7cf1454f8dd2df6f83172745fa875f6ed31b5a76bf40e009cbac0a8","last_reissued_at":"2026-07-05T12:05:38.965532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:38.965532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.05292","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":"2026-07-05T12:05:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pzwV17lOXdhwFe8aNZnFvBuWtdQdrQhPnqEJkqDnelG88pZK1qpPde8Fhzksk+lUOMs6suaw38BxUHocRQc9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:59:44.180424Z"},"content_sha256":"bd3783d86b9400f44dc45b120aa416b42aafa1dcb52041bd7857a7b31d61b237","schema_version":"1.0","event_id":"sha256:bd3783d86b9400f44dc45b120aa416b42aafa1dcb52041bd7857a7b31d61b237"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:H6X5JD7HZ4KFJ6G5FX3PQMLSOR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at Pinterest","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abe Engle, Charles Rosenberg, Fan Zhou, Jiajing Xu, Jinfeng Zhuang, Ling Leng, Longyu Zhao, Mehdi Ben Ayed, Prathibha Deshikachar, Xiao Yang, Yuchen Shen","submitted_at":"2025-09-05T17:57:45Z","abstract_excerpt":"The ranking utility function in an ad recommender system, which linearly combines predictions of various business goals, plays a central role in balancing values across the platform, advertisers, and users. Traditional manual tuning, while offering simplicity and interpretability, often yields suboptimal results due to its unprincipled tuning objectives, the vast amount of parameter combinations, and its lack of personalization and adaptability to seasonality. In this work, we propose a general Deep Reinforcement Learning framework for Personalized Utility Tuning (DRL-PUT) to address the chall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05292","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/2509.05292/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":"2026-07-05T12:05:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v55mT0FI78F2Esb1B5sLK7eKuKV8uaGVaASjn935A9v6smV9i7VcFf/g/4LdhhIK7CmUpbdpLbkKI9UVzgVeCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:59:44.180930Z"},"content_sha256":"d8d5209e15ce331e667b6454a689e02d3fe9352d10904ab7832143b30f72633a","schema_version":"1.0","event_id":"sha256:d8d5209e15ce331e667b6454a689e02d3fe9352d10904ab7832143b30f72633a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H6X5JD7HZ4KFJ6G5FX3PQMLSOR/bundle.json","state_url":"https://pith.science/pith/H6X5JD7HZ4KFJ6G5FX3PQMLSOR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H6X5JD7HZ4KFJ6G5FX3PQMLSOR/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":"2026-08-06T21:59:44Z","links":{"resolver":"https://pith.science/pith/H6X5JD7HZ4KFJ6G5FX3PQMLSOR","bundle":"https://pith.science/pith/H6X5JD7HZ4KFJ6G5FX3PQMLSOR/bundle.json","state":"https://pith.science/pith/H6X5JD7HZ4KFJ6G5FX3PQMLSOR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H6X5JD7HZ4KFJ6G5FX3PQMLSOR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H6X5JD7HZ4KFJ6G5FX3PQMLSOR","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":"82bfca405b49e1c488379322f4d233510a63b51b30d17ecd6e43a85da81e23cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-05T17:57:45Z","title_canon_sha256":"4e8c8c4eddcd0df384746fcb1fac70675b4f3d22582d0a6c2764dfa1ed45f5bb"},"schema_version":"1.0","source":{"id":"2509.05292","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05292","created_at":"2026-07-05T12:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05292v1","created_at":"2026-07-05T12:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05292","created_at":"2026-07-05T12:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"H6X5JD7HZ4KF","created_at":"2026-07-05T12:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"H6X5JD7HZ4KFJ6G5","created_at":"2026-07-05T12:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"H6X5JD7H","created_at":"2026-07-05T12:05:38Z"}],"graph_snapshots":[{"event_id":"sha256:d8d5209e15ce331e667b6454a689e02d3fe9352d10904ab7832143b30f72633a","target":"graph","created_at":"2026-07-05T12:05:38Z","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/2509.05292/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ranking utility function in an ad recommender system, which linearly combines predictions of various business goals, plays a central role in balancing values across the platform, advertisers, and users. Traditional manual tuning, while offering simplicity and interpretability, often yields suboptimal results due to its unprincipled tuning objectives, the vast amount of parameter combinations, and its lack of personalization and adaptability to seasonality. In this work, we propose a general Deep Reinforcement Learning framework for Personalized Utility Tuning (DRL-PUT) to address the chall","authors_text":"Abe Engle, Charles Rosenberg, Fan Zhou, Jiajing Xu, Jinfeng Zhuang, Ling Leng, Longyu Zhao, Mehdi Ben Ayed, Prathibha Deshikachar, Xiao Yang, Yuchen Shen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-05T17:57:45Z","title":"Deep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at Pinterest"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05292","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:bd3783d86b9400f44dc45b120aa416b42aafa1dcb52041bd7857a7b31d61b237","target":"record","created_at":"2026-07-05T12:05:38Z","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":"82bfca405b49e1c488379322f4d233510a63b51b30d17ecd6e43a85da81e23cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-05T17:57:45Z","title_canon_sha256":"4e8c8c4eddcd0df384746fcb1fac70675b4f3d22582d0a6c2764dfa1ed45f5bb"},"schema_version":"1.0","source":{"id":"2509.05292","kind":"arxiv","version":1}},"canonical_sha256":"3fafd48fe7cf1454f8dd2df6f83172745fa875f6ed31b5a76bf40e009cbac0a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fafd48fe7cf1454f8dd2df6f83172745fa875f6ed31b5a76bf40e009cbac0a8","first_computed_at":"2026-07-05T12:05:38.965532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:38.965532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+VDxdayLOu2oLdeUANZki3gfltXW8AdPJfrB2GGrvcvrXrxkADun/P9u6XopYMsLT5G7GNBFnIVC30/8rIofCw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:38.966023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.05292","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd3783d86b9400f44dc45b120aa416b42aafa1dcb52041bd7857a7b31d61b237","sha256:d8d5209e15ce331e667b6454a689e02d3fe9352d10904ab7832143b30f72633a"],"state_sha256":"f8c8900711429454991ed874d50e16726071ae994ab9753070c388e04a757980"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sTn4dOBC1iztcJOzPNPvAVxm9bEF8cbTfmWl6T7LQITWI59pFpcUfpux+GltWjdW7FvXsEk7L9XWCqUE1EXjCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:59:44.185098Z","bundle_sha256":"368a2dbf3bc7c4b8ec7d609b382f902872ca9709191b904dada3803e81a082a3"}}