{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XRQH3MFJXJKBGAJFXP6C2KG5TF","short_pith_number":"pith:XRQH3MFJ","canonical_record":{"source":{"id":"2310.17496","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2023-10-26T15:52:34Z","cross_cats_sorted":["cs.LG","econ.EM"],"title_canon_sha256":"e3f25902d93ea695731fbae8885322de52655040de5345a51b8dc00af67bb116","abstract_canon_sha256":"41608c03f9fc330b6c5cb15ae17a5ae4a9c14bed46bcc812592715cccb941e3d"},"schema_version":"1.0"},"canonical_sha256":"bc607db0a9ba54130125bbfc2d28dd997b1ef4578d1870d04836cbbde6fbdf43","source":{"kind":"arxiv","id":"2310.17496","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17496","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17496v5","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17496","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"XRQH3MFJXJKB","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"XRQH3MFJXJKBGAJF","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"XRQH3MFJ","created_at":"2026-07-05T08:04:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XRQH3MFJXJKBGAJFXP6C2KG5TF","target":"record","payload":{"canonical_record":{"source":{"id":"2310.17496","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2023-10-26T15:52:34Z","cross_cats_sorted":["cs.LG","econ.EM"],"title_canon_sha256":"e3f25902d93ea695731fbae8885322de52655040de5345a51b8dc00af67bb116","abstract_canon_sha256":"41608c03f9fc330b6c5cb15ae17a5ae4a9c14bed46bcc812592715cccb941e3d"},"schema_version":"1.0"},"canonical_sha256":"bc607db0a9ba54130125bbfc2d28dd997b1ef4578d1870d04836cbbde6fbdf43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:34.722580Z","signature_b64":"BSOWLr7LBw4YmXz+cgk6QrKvS+1mz7d442uoujl699oxG35RezYu5dZh8RUKLTrft3/akqbJO9G+dLjhboSTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc607db0a9ba54130125bbfc2d28dd997b1ef4578d1870d04836cbbde6fbdf43","last_reissued_at":"2026-07-05T08:04:34.722113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:34.722113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.17496","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:04:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TlMIyffUyigUxJySAQ7Uf8kHwGl0UKSGEiwO7aqnKPS/gjurlWsroHadQLcOKsIcbZ1NYbeRT0a3R/XufbFxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:04:00.485079Z"},"content_sha256":"c51a797d9ca6bf397de658bfae89b09c6d331a5008211e9731f10ddd289e4145","schema_version":"1.0","event_id":"sha256:c51a797d9ca6bf397de658bfae89b09c6d331a5008211e9731f10ddd289e4145"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XRQH3MFJXJKBGAJFXP6C2KG5TF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tackling Interference Induced by Data Training Loops in A/B Tests: A Weighted Training Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","econ.EM"],"primary_cat":"stat.ME","authors_text":"Nian Si","submitted_at":"2023-10-26T15:52:34Z","abstract_excerpt":"In modern recommendation systems, the standard pipeline involves training machine learning models on historical data to predict user behaviors and improve recommendations continuously. However, these data training loops can introduce interference in A/B tests, where data generated by control and treatment algorithms, potentially with different distributions, are combined. To address these challenges, we introduce a novel approach called weighted training. This approach entails training a model to predict the probability of each data point appearing in either the treatment or control data and s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17496","kind":"arxiv","version":5},"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/2310.17496/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":"2026-07-05T08:04:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5s45WuEeiF22ZIE+BMq14SKrljU4GnYD5VX9CZwapRfHUQWGcj/JReXyAi2QJxD3gWlfdL9qKXa8kPt0V6C9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:04:00.485946Z"},"content_sha256":"c840dc513a17673f4b6ed2ff29255659957665a46b35261192e92e666ba18d89","schema_version":"1.0","event_id":"sha256:c840dc513a17673f4b6ed2ff29255659957665a46b35261192e92e666ba18d89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XRQH3MFJXJKBGAJFXP6C2KG5TF/bundle.json","state_url":"https://pith.science/pith/XRQH3MFJXJKBGAJFXP6C2KG5TF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XRQH3MFJXJKBGAJFXP6C2KG5TF/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":"2026-08-05T05:04:00Z","links":{"resolver":"https://pith.science/pith/XRQH3MFJXJKBGAJFXP6C2KG5TF","bundle":"https://pith.science/pith/XRQH3MFJXJKBGAJFXP6C2KG5TF/bundle.json","state":"https://pith.science/pith/XRQH3MFJXJKBGAJFXP6C2KG5TF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XRQH3MFJXJKBGAJFXP6C2KG5TF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XRQH3MFJXJKBGAJFXP6C2KG5TF","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":"41608c03f9fc330b6c5cb15ae17a5ae4a9c14bed46bcc812592715cccb941e3d","cross_cats_sorted":["cs.LG","econ.EM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2023-10-26T15:52:34Z","title_canon_sha256":"e3f25902d93ea695731fbae8885322de52655040de5345a51b8dc00af67bb116"},"schema_version":"1.0","source":{"id":"2310.17496","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17496","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17496v5","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17496","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"XRQH3MFJXJKB","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"XRQH3MFJXJKBGAJF","created_at":"2026-07-05T08:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"XRQH3MFJ","created_at":"2026-07-05T08:04:34Z"}],"graph_snapshots":[{"event_id":"sha256:c840dc513a17673f4b6ed2ff29255659957665a46b35261192e92e666ba18d89","target":"graph","created_at":"2026-07-05T08:04:34Z","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/2310.17496/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In modern recommendation systems, the standard pipeline involves training machine learning models on historical data to predict user behaviors and improve recommendations continuously. However, these data training loops can introduce interference in A/B tests, where data generated by control and treatment algorithms, potentially with different distributions, are combined. To address these challenges, we introduce a novel approach called weighted training. This approach entails training a model to predict the probability of each data point appearing in either the treatment or control data and s","authors_text":"Nian Si","cross_cats":["cs.LG","econ.EM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2023-10-26T15:52:34Z","title":"Tackling Interference Induced by Data Training Loops in A/B Tests: A Weighted Training Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17496","kind":"arxiv","version":5},"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:c51a797d9ca6bf397de658bfae89b09c6d331a5008211e9731f10ddd289e4145","target":"record","created_at":"2026-07-05T08:04:34Z","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":"41608c03f9fc330b6c5cb15ae17a5ae4a9c14bed46bcc812592715cccb941e3d","cross_cats_sorted":["cs.LG","econ.EM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2023-10-26T15:52:34Z","title_canon_sha256":"e3f25902d93ea695731fbae8885322de52655040de5345a51b8dc00af67bb116"},"schema_version":"1.0","source":{"id":"2310.17496","kind":"arxiv","version":5}},"canonical_sha256":"bc607db0a9ba54130125bbfc2d28dd997b1ef4578d1870d04836cbbde6fbdf43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc607db0a9ba54130125bbfc2d28dd997b1ef4578d1870d04836cbbde6fbdf43","first_computed_at":"2026-07-05T08:04:34.722113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:34.722113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BSOWLr7LBw4YmXz+cgk6QrKvS+1mz7d442uoujl699oxG35RezYu5dZh8RUKLTrft3/akqbJO9G+dLjhboSTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:34.722580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.17496","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c51a797d9ca6bf397de658bfae89b09c6d331a5008211e9731f10ddd289e4145","sha256:c840dc513a17673f4b6ed2ff29255659957665a46b35261192e92e666ba18d89"],"state_sha256":"e498f38ac0d609c29641d4da478b5524f0d00fba4b2d9f50d312ca70bdcbddd4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E1rZn+gbCL84JnFUpaXhS4orpl/qf5GFt0FHSCUtOylIZJVl7Ua20QaYx5rSg5Qh/S9QojkjJzTV0DIjwIFgDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T05:04:00.492212Z","bundle_sha256":"6cea609b0bdd7e142e8ec450a1f61ffe6954c3bf86856506b8e5f76993bb5d8f"}}