{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HTCIIOCK6VIMSEO7GZ6BCV5GTW","short_pith_number":"pith:HTCIIOCK","schema_version":"1.0","canonical_sha256":"3cc484384af550c911df367c1157a69d88041a0ac327d0f91dfe97a312ef6619","source":{"kind":"arxiv","id":"2310.18617","version":1},"attestation_state":"computed","paper":{"title":"Pessimistic Off-Policy Multi-Objective Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aniruddha Bhargava, Branislav Kveton, Ge Liu, Karthick Gopalswamy, Lalit Jain, Shima Alizadeh","submitted_at":"2023-10-28T06:50:15Z","abstract_excerpt":"Multi-objective optimization is a type of decision making problems where multiple conflicting objectives are optimized. We study offline optimization of multi-objective policies from data collected by an existing policy. We propose a pessimistic estimator for the multi-objective policy values that can be easily plugged into existing formulas for hypervolume computation and optimized. The estimator is based on inverse propensity scores (IPS), and improves upon a naive IPS estimator in both theory and experiments. Our analysis is general, and applies beyond our IPS estimators and methods for opt"},"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":"2310.18617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-28T06:50:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b3bccf7b841227c8393fe51a3bd020df185beaa846b71481cf0166fdd8f51f74","abstract_canon_sha256":"453f1ca1f6a45b49bd79e87b236f636eb7de84d8810b79ee63fca527640df834"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:11.222779Z","signature_b64":"5f0YTmi50ElQhnVmLhkEFiEtj34umycOur0mChARz3msbI1jzmWdNDggQq09ujqRDr5ZI+WzrkuLA+H8V1UUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cc484384af550c911df367c1157a69d88041a0ac327d0f91dfe97a312ef6619","last_reissued_at":"2026-07-05T07:06:11.222235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:11.222235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pessimistic Off-Policy Multi-Objective Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aniruddha Bhargava, Branislav Kveton, Ge Liu, Karthick Gopalswamy, Lalit Jain, Shima Alizadeh","submitted_at":"2023-10-28T06:50:15Z","abstract_excerpt":"Multi-objective optimization is a type of decision making problems where multiple conflicting objectives are optimized. We study offline optimization of multi-objective policies from data collected by an existing policy. We propose a pessimistic estimator for the multi-objective policy values that can be easily plugged into existing formulas for hypervolume computation and optimized. The estimator is based on inverse propensity scores (IPS), and improves upon a naive IPS estimator in both theory and experiments. Our analysis is general, and applies beyond our IPS estimators and methods for opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18617","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/2310.18617/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":"2310.18617","created_at":"2026-07-05T07:06:11.222292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18617v1","created_at":"2026-07-05T07:06:11.222292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18617","created_at":"2026-07-05T07:06:11.222292+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTCIIOCK6VIM","created_at":"2026-07-05T07:06:11.222292+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTCIIOCK6VIMSEO7","created_at":"2026-07-05T07:06:11.222292+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTCIIOCK","created_at":"2026-07-05T07:06:11.222292+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/HTCIIOCK6VIMSEO7GZ6BCV5GTW","json":"https://pith.science/pith/HTCIIOCK6VIMSEO7GZ6BCV5GTW.json","graph_json":"https://pith.science/api/pith-number/HTCIIOCK6VIMSEO7GZ6BCV5GTW/graph.json","events_json":"https://pith.science/api/pith-number/HTCIIOCK6VIMSEO7GZ6BCV5GTW/events.json","paper":"https://pith.science/paper/HTCIIOCK"},"agent_actions":{"view_html":"https://pith.science/pith/HTCIIOCK6VIMSEO7GZ6BCV5GTW","download_json":"https://pith.science/pith/HTCIIOCK6VIMSEO7GZ6BCV5GTW.json","view_paper":"https://pith.science/paper/HTCIIOCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18617&json=true","fetch_graph":"https://pith.science/api/pith-number/HTCIIOCK6VIMSEO7GZ6BCV5GTW/graph.json","fetch_events":"https://pith.science/api/pith-number/HTCIIOCK6VIMSEO7GZ6BCV5GTW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTCIIOCK6VIMSEO7GZ6BCV5GTW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTCIIOCK6VIMSEO7GZ6BCV5GTW/action/storage_attestation","attest_author":"https://pith.science/pith/HTCIIOCK6VIMSEO7GZ6BCV5GTW/action/author_attestation","sign_citation":"https://pith.science/pith/HTCIIOCK6VIMSEO7GZ6BCV5GTW/action/citation_signature","submit_replication":"https://pith.science/pith/HTCIIOCK6VIMSEO7GZ6BCV5GTW/action/replication_record"}},"created_at":"2026-07-05T07:06:11.222292+00:00","updated_at":"2026-07-05T07:06:11.222292+00:00"}