{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7XAUEHYUABN76H35KBAA33YTU7","short_pith_number":"pith:7XAUEHYU","schema_version":"1.0","canonical_sha256":"fdc1421f14005bff1f7d50400def13a7c769a0db2f2371fc3807e1c7b13524be","source":{"kind":"arxiv","id":"2412.20638","version":2},"attestation_state":"computed","paper":{"title":"Predicting Long Term Sequential Policy Value Using Softer Surrogates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Allen Nie, Emma Brunskill, Ge Gao, Hyunji Nam, Vasilis Syrgkanis","submitted_at":"2024-12-30T01:01:15Z","abstract_excerpt":"Off-policy policy evaluation (OPE) estimates the outcome of a new policy using historical data collected from a different policy. However, existing OPE methods cannot handle cases when the new policy introduces novel actions. This issue commonly occurs in real-world domains, like healthcare, as new drugs and treatments are continuously developed. Novel actions necessitate on-policy data collection, which can be burdensome and expensive if the outcome of interest takes a substantial amount of time to observe--for example, in multi-year clinical trials. This raises a key question of how to predi"},"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":"2412.20638","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-30T01:01:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"be7eb75eba452bc86e45de0e7cfc0c4514bc741405eba4861a38c907ef84080d","abstract_canon_sha256":"c1c4ded046b5507ef35c7c5f556eb343c67cb150245f3fe4405ed6a921d6bf6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:26.934560Z","signature_b64":"4mkYsbxlFcplC12nAYKzsMwHttceTVNlQmbnLfHKsm/BMPnw/b9kSjONvaTPvbs76aqBHupju7/3+EAEAlUmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdc1421f14005bff1f7d50400def13a7c769a0db2f2371fc3807e1c7b13524be","last_reissued_at":"2026-07-05T10:08:26.934037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:26.934037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting Long Term Sequential Policy Value Using Softer Surrogates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Allen Nie, Emma Brunskill, Ge Gao, Hyunji Nam, Vasilis Syrgkanis","submitted_at":"2024-12-30T01:01:15Z","abstract_excerpt":"Off-policy policy evaluation (OPE) estimates the outcome of a new policy using historical data collected from a different policy. However, existing OPE methods cannot handle cases when the new policy introduces novel actions. This issue commonly occurs in real-world domains, like healthcare, as new drugs and treatments are continuously developed. Novel actions necessitate on-policy data collection, which can be burdensome and expensive if the outcome of interest takes a substantial amount of time to observe--for example, in multi-year clinical trials. This raises a key question of how to predi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20638","kind":"arxiv","version":2},"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/2412.20638/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":"2412.20638","created_at":"2026-07-05T10:08:26.934116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.20638v2","created_at":"2026-07-05T10:08:26.934116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20638","created_at":"2026-07-05T10:08:26.934116+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XAUEHYUABN7","created_at":"2026-07-05T10:08:26.934116+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XAUEHYUABN76H35","created_at":"2026-07-05T10:08:26.934116+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XAUEHYU","created_at":"2026-07-05T10:08:26.934116+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/7XAUEHYUABN76H35KBAA33YTU7","json":"https://pith.science/pith/7XAUEHYUABN76H35KBAA33YTU7.json","graph_json":"https://pith.science/api/pith-number/7XAUEHYUABN76H35KBAA33YTU7/graph.json","events_json":"https://pith.science/api/pith-number/7XAUEHYUABN76H35KBAA33YTU7/events.json","paper":"https://pith.science/paper/7XAUEHYU"},"agent_actions":{"view_html":"https://pith.science/pith/7XAUEHYUABN76H35KBAA33YTU7","download_json":"https://pith.science/pith/7XAUEHYUABN76H35KBAA33YTU7.json","view_paper":"https://pith.science/paper/7XAUEHYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.20638&json=true","fetch_graph":"https://pith.science/api/pith-number/7XAUEHYUABN76H35KBAA33YTU7/graph.json","fetch_events":"https://pith.science/api/pith-number/7XAUEHYUABN76H35KBAA33YTU7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XAUEHYUABN76H35KBAA33YTU7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XAUEHYUABN76H35KBAA33YTU7/action/storage_attestation","attest_author":"https://pith.science/pith/7XAUEHYUABN76H35KBAA33YTU7/action/author_attestation","sign_citation":"https://pith.science/pith/7XAUEHYUABN76H35KBAA33YTU7/action/citation_signature","submit_replication":"https://pith.science/pith/7XAUEHYUABN76H35KBAA33YTU7/action/replication_record"}},"created_at":"2026-07-05T10:08:26.934116+00:00","updated_at":"2026-07-05T10:08:26.934116+00:00"}