{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QTNWNFF7WVM5P4DQDJ6ZNZAF62","short_pith_number":"pith:QTNWNFF7","schema_version":"1.0","canonical_sha256":"84db6694bfb559d7f0701a7d96e405f682b27166f7d76a5145a0abb11acbddff","source":{"kind":"arxiv","id":"2601.20753","version":4},"attestation_state":"computed","paper":{"title":"GraphAllocBench: A Flexible Benchmark for Preference-Conditioned Multi-Objective Policy Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benjamin T. Files, Ellen Novoseller, Ryan Marr, Volkan Ustun, Yunzhe Wang, Zhiheng Jiang","submitted_at":"2026-01-28T16:36:37Z","abstract_excerpt":"Preference-Conditioned Policy Learning (PCPL) in Multi-Objective Reinforcement Learning (MORL) approximates diverse Pareto-optimal solutions by conditioning a single policy on user-specified preferences, enabling run-time adaptation to arbitrary trade-offs without retraining. However, existing PCPL benchmarks are largely restricted to toy tasks and fixed environments, limiting their realism and scalability. To address this gap, we introduce GraphAllocBench, a flexible benchmark built on CityPlannerEnv, a novel graph-based resource allocation sandbox inspired by city management. GraphAllocBench"},"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":"2601.20753","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-28T16:36:37Z","cross_cats_sorted":[],"title_canon_sha256":"37b3dac4f6112e0d8dccb9cf241063df1df21db8355a0c883b60d25a042ae7e9","abstract_canon_sha256":"4c5e117d8888ea9d7727cf9a83f762f78cdcb29bc980b540b12d413d958c6010"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:24.790332Z","signature_b64":"cLhF/v9jUyu0g8mL0L3usHPtPKVbsWAK7EEO35AvslhirznHraNVUDFEuiyBH9S8UpMIRTMJIGaKfISsFhg7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84db6694bfb559d7f0701a7d96e405f682b27166f7d76a5145a0abb11acbddff","last_reissued_at":"2026-07-08T01:18:24.789785Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:24.789785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphAllocBench: A Flexible Benchmark for Preference-Conditioned Multi-Objective Policy Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benjamin T. Files, Ellen Novoseller, Ryan Marr, Volkan Ustun, Yunzhe Wang, Zhiheng Jiang","submitted_at":"2026-01-28T16:36:37Z","abstract_excerpt":"Preference-Conditioned Policy Learning (PCPL) in Multi-Objective Reinforcement Learning (MORL) approximates diverse Pareto-optimal solutions by conditioning a single policy on user-specified preferences, enabling run-time adaptation to arbitrary trade-offs without retraining. However, existing PCPL benchmarks are largely restricted to toy tasks and fixed environments, limiting their realism and scalability. To address this gap, we introduce GraphAllocBench, a flexible benchmark built on CityPlannerEnv, a novel graph-based resource allocation sandbox inspired by city management. GraphAllocBench"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.20753","kind":"arxiv","version":4},"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/2601.20753/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":"2601.20753","created_at":"2026-07-08T01:18:24.789849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.20753v4","created_at":"2026-07-08T01:18:24.789849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.20753","created_at":"2026-07-08T01:18:24.789849+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTNWNFF7WVM5","created_at":"2026-07-08T01:18:24.789849+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTNWNFF7WVM5P4DQ","created_at":"2026-07-08T01:18:24.789849+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTNWNFF7","created_at":"2026-07-08T01:18:24.789849+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.10585","citing_title":"Controllability in preference-conditioned multi-objective reinforcement learning","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QTNWNFF7WVM5P4DQDJ6ZNZAF62","json":"https://pith.science/pith/QTNWNFF7WVM5P4DQDJ6ZNZAF62.json","graph_json":"https://pith.science/api/pith-number/QTNWNFF7WVM5P4DQDJ6ZNZAF62/graph.json","events_json":"https://pith.science/api/pith-number/QTNWNFF7WVM5P4DQDJ6ZNZAF62/events.json","paper":"https://pith.science/paper/QTNWNFF7"},"agent_actions":{"view_html":"https://pith.science/pith/QTNWNFF7WVM5P4DQDJ6ZNZAF62","download_json":"https://pith.science/pith/QTNWNFF7WVM5P4DQDJ6ZNZAF62.json","view_paper":"https://pith.science/paper/QTNWNFF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.20753&json=true","fetch_graph":"https://pith.science/api/pith-number/QTNWNFF7WVM5P4DQDJ6ZNZAF62/graph.json","fetch_events":"https://pith.science/api/pith-number/QTNWNFF7WVM5P4DQDJ6ZNZAF62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTNWNFF7WVM5P4DQDJ6ZNZAF62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTNWNFF7WVM5P4DQDJ6ZNZAF62/action/storage_attestation","attest_author":"https://pith.science/pith/QTNWNFF7WVM5P4DQDJ6ZNZAF62/action/author_attestation","sign_citation":"https://pith.science/pith/QTNWNFF7WVM5P4DQDJ6ZNZAF62/action/citation_signature","submit_replication":"https://pith.science/pith/QTNWNFF7WVM5P4DQDJ6ZNZAF62/action/replication_record"}},"created_at":"2026-07-08T01:18:24.789849+00:00","updated_at":"2026-07-08T01:18:24.789849+00:00"}