{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CTXOBTUXUHF35SQ2F534JDYH5C","short_pith_number":"pith:CTXOBTUX","schema_version":"1.0","canonical_sha256":"14eee0ce97a1cbbeca1a2f77c48f07e880b1467cf0fc269d15663e66475b54e9","source":{"kind":"arxiv","id":"2606.21321","version":1},"attestation_state":"computed","paper":{"title":"Objective-Behavior Alignment: Diagnostics for MORL Policy Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antonio Mone, Florian Felten, Frans A. Oliehoek, Luciano Cavalcante Siebert, Mark Fuge, Pradeep K. Murukannaiah, Zuzanna Osika","submitted_at":"2026-06-19T11:10:26Z","abstract_excerpt":"Real-world decision-making often requires optimizing multiple competing objectives simultaneously. In reinforcement learning (RL), this is typically addressed by combining reward signals into a single scalar objective via a scalarization function, which can be fragile: small changes in the weights can induce drastically different policies. Multi-objective reinforcement learning (MORL) instead produces sets of policies that explicitly represent trade-offs between objectives. However, these policies are typically presented to the decision maker only through their value vectors, which can obscure"},"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":"2606.21321","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T11:10:26Z","cross_cats_sorted":[],"title_canon_sha256":"094b2f90f0ebcf685d2fa7a367990dabd36bb185820abcc05229f225e1b64dd9","abstract_canon_sha256":"c797e2aad7afbc8de89da784d2471b125c3950203bb2af6f635b1a76a025584f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:37.150207Z","signature_b64":"jjDY6dDlhub/40Uh6zdhD3R57q+p9zyaalDYDa1acTVYmJ+M/+hpkPKGFN6vq5k25utw31BJy4edy9QPELXWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14eee0ce97a1cbbeca1a2f77c48f07e880b1467cf0fc269d15663e66475b54e9","last_reissued_at":"2026-06-23T01:12:37.149712Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:37.149712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Objective-Behavior Alignment: Diagnostics for MORL Policy Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antonio Mone, Florian Felten, Frans A. Oliehoek, Luciano Cavalcante Siebert, Mark Fuge, Pradeep K. Murukannaiah, Zuzanna Osika","submitted_at":"2026-06-19T11:10:26Z","abstract_excerpt":"Real-world decision-making often requires optimizing multiple competing objectives simultaneously. In reinforcement learning (RL), this is typically addressed by combining reward signals into a single scalar objective via a scalarization function, which can be fragile: small changes in the weights can induce drastically different policies. Multi-objective reinforcement learning (MORL) instead produces sets of policies that explicitly represent trade-offs between objectives. However, these policies are typically presented to the decision maker only through their value vectors, which can obscure"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21321","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/2606.21321/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":"2606.21321","created_at":"2026-06-23T01:12:37.149778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21321v1","created_at":"2026-06-23T01:12:37.149778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21321","created_at":"2026-06-23T01:12:37.149778+00:00"},{"alias_kind":"pith_short_12","alias_value":"CTXOBTUXUHF3","created_at":"2026-06-23T01:12:37.149778+00:00"},{"alias_kind":"pith_short_16","alias_value":"CTXOBTUXUHF35SQ2","created_at":"2026-06-23T01:12:37.149778+00:00"},{"alias_kind":"pith_short_8","alias_value":"CTXOBTUX","created_at":"2026-06-23T01:12:37.149778+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/CTXOBTUXUHF35SQ2F534JDYH5C","json":"https://pith.science/pith/CTXOBTUXUHF35SQ2F534JDYH5C.json","graph_json":"https://pith.science/api/pith-number/CTXOBTUXUHF35SQ2F534JDYH5C/graph.json","events_json":"https://pith.science/api/pith-number/CTXOBTUXUHF35SQ2F534JDYH5C/events.json","paper":"https://pith.science/paper/CTXOBTUX"},"agent_actions":{"view_html":"https://pith.science/pith/CTXOBTUXUHF35SQ2F534JDYH5C","download_json":"https://pith.science/pith/CTXOBTUXUHF35SQ2F534JDYH5C.json","view_paper":"https://pith.science/paper/CTXOBTUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21321&json=true","fetch_graph":"https://pith.science/api/pith-number/CTXOBTUXUHF35SQ2F534JDYH5C/graph.json","fetch_events":"https://pith.science/api/pith-number/CTXOBTUXUHF35SQ2F534JDYH5C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CTXOBTUXUHF35SQ2F534JDYH5C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CTXOBTUXUHF35SQ2F534JDYH5C/action/storage_attestation","attest_author":"https://pith.science/pith/CTXOBTUXUHF35SQ2F534JDYH5C/action/author_attestation","sign_citation":"https://pith.science/pith/CTXOBTUXUHF35SQ2F534JDYH5C/action/citation_signature","submit_replication":"https://pith.science/pith/CTXOBTUXUHF35SQ2F534JDYH5C/action/replication_record"}},"created_at":"2026-06-23T01:12:37.149778+00:00","updated_at":"2026-06-23T01:12:37.149778+00:00"}