{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JD5X3XNHHGPHKPI2RXJ4HGFNKI","short_pith_number":"pith:JD5X3XNH","schema_version":"1.0","canonical_sha256":"48fb7ddda7399e753d1a8dd3c398ad523d209338a597de09a33e598971ccaaf6","source":{"kind":"arxiv","id":"2608.12489","version":1},"attestation_state":"computed","paper":{"title":"When Can You Trust Offline Evaluation of Equal-Cost Top-k Allocation? A Controlled, Reproducible Benchmark and Practitioner's Guide","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Binshuang Li","submitted_at":"2026-08-12T18:10:10Z","abstract_excerpt":"Organizations decide whom to treat under a budget and want to know what a targeting rule would have earned before deploying it. Off-policy evaluation promises this from logged data, but the deployable rule is a deterministic top-k policy: it removes all averaging over actions, so weak overlap hits the estimate directly. We benchmark six estimators across five datasets and two known-effect sweeps, and validate the mechanisms against a non-simulated paired reference. First, weak overlap is governed by logger-target action alignment, not by logging sharpness alone: what governs support is the log"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.12489","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-12T18:10:10Z","cross_cats_sorted":["stat.ME","stat.ML"],"title_canon_sha256":"0153c8f576e38c46df1f023ec647eaa078e582fe6d3c6ae89d8278ab26597fa0","abstract_canon_sha256":"c1cb36b706aa21440c31ebbe937ea36c4502a5cb51623ec8364b21bf38c8e78e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:43:57.957229Z","signature_b64":"A4pEqfL09WXruCXqhFww++xbGdu6wBCi403MjBHpn2ejEsiy4y5O+uhRExL8k29GEhux76DibYeB+50JoXe/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48fb7ddda7399e753d1a8dd3c398ad523d209338a597de09a33e598971ccaaf6","last_reissued_at":"2026-08-14T00:43:57.954139Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:43:57.954139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Can You Trust Offline Evaluation of Equal-Cost Top-k Allocation? A Controlled, Reproducible Benchmark and Practitioner's Guide","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Binshuang Li","submitted_at":"2026-08-12T18:10:10Z","abstract_excerpt":"Organizations decide whom to treat under a budget and want to know what a targeting rule would have earned before deploying it. Off-policy evaluation promises this from logged data, but the deployable rule is a deterministic top-k policy: it removes all averaging over actions, so weak overlap hits the estimate directly. We benchmark six estimators across five datasets and two known-effect sweeps, and validate the mechanisms against a non-simulated paired reference. First, weak overlap is governed by logger-target action alignment, not by logging sharpness alone: what governs support is the log"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12489","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/2608.12489/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.12489","created_at":"2026-08-14T00:43:57.955411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.12489v1","created_at":"2026-08-14T00:43:57.955411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12489","created_at":"2026-08-14T00:43:57.955411+00:00"},{"alias_kind":"pith_short_12","alias_value":"JD5X3XNHHGPH","created_at":"2026-08-14T00:43:57.955411+00:00"},{"alias_kind":"pith_short_16","alias_value":"JD5X3XNHHGPHKPI2","created_at":"2026-08-14T00:43:57.955411+00:00"},{"alias_kind":"pith_short_8","alias_value":"JD5X3XNH","created_at":"2026-08-14T00:43:57.955411+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JD5X3XNHHGPHKPI2RXJ4HGFNKI","json":"https://pith.science/pith/JD5X3XNHHGPHKPI2RXJ4HGFNKI.json","graph_json":"https://pith.science/api/pith-number/JD5X3XNHHGPHKPI2RXJ4HGFNKI/graph.json","events_json":"https://pith.science/api/pith-number/JD5X3XNHHGPHKPI2RXJ4HGFNKI/events.json","paper":"https://pith.science/paper/JD5X3XNH"},"agent_actions":{"view_html":"https://pith.science/pith/JD5X3XNHHGPHKPI2RXJ4HGFNKI","download_json":"https://pith.science/pith/JD5X3XNHHGPHKPI2RXJ4HGFNKI.json","view_paper":"https://pith.science/paper/JD5X3XNH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.12489&json=true","fetch_graph":"https://pith.science/api/pith-number/JD5X3XNHHGPHKPI2RXJ4HGFNKI/graph.json","fetch_events":"https://pith.science/api/pith-number/JD5X3XNHHGPHKPI2RXJ4HGFNKI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JD5X3XNHHGPHKPI2RXJ4HGFNKI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JD5X3XNHHGPHKPI2RXJ4HGFNKI/action/storage_attestation","attest_author":"https://pith.science/pith/JD5X3XNHHGPHKPI2RXJ4HGFNKI/action/author_attestation","sign_citation":"https://pith.science/pith/JD5X3XNHHGPHKPI2RXJ4HGFNKI/action/citation_signature","submit_replication":"https://pith.science/pith/JD5X3XNHHGPHKPI2RXJ4HGFNKI/action/replication_record"}},"created_at":"2026-08-14T00:43:57.955411+00:00","updated_at":"2026-08-14T00:43:57.955411+00:00"}