{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ID7JSI6OEO2XRG4P3YF3A5KO2Z","short_pith_number":"pith:ID7JSI6O","schema_version":"1.0","canonical_sha256":"40fe9923ce23b5789b8fde0bb0754ed64d8c26419fcea51fb7b7882dbabd72e0","source":{"kind":"arxiv","id":"2111.13872","version":1},"attestation_state":"computed","paper":{"title":"Normative Disagreement as a Challenge for Cooperative AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.LG"],"primary_cat":"cs.MA","authors_text":"Alexander Lyzhov, Allan Dafoe, Jesse Clifton, Johannes Treutlein, Julian Stastny, Maxime Rich\\'e","submitted_at":"2021-11-27T11:37:42Z","abstract_excerpt":"Cooperation in settings where agents have both common and conflicting interests (mixed-motive environments) has recently received considerable attention in multi-agent learning. However, the mixed-motive environments typically studied have a single cooperative outcome on which all agents can agree. Many real-world multi-agent environments are instead bargaining problems (BPs): they have several Pareto-optimal payoff profiles over which agents have conflicting preferences. We argue that typical cooperation-inducing learning algorithms fail to cooperate in BPs when there is room for normative di"},"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":"2111.13872","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2021-11-27T11:37:42Z","cross_cats_sorted":["cs.AI","cs.GT","cs.LG"],"title_canon_sha256":"8e1017a4b61fd9c3822192e59fe1321cde0acfd61ae785af0f6685827a31e2d3","abstract_canon_sha256":"7c377a0e61454228c9560b3a614342ddce7a532e66e7dd74ce97468600bae11c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:36.725028Z","signature_b64":"zqEbydDUvRbw3vAAsHxf4EShJSuYdMS3Ft2ZJGr6XDpQWZ9I79PrM6mWqdMFklQ++HZ7Y9rvmWukwi7G3tXXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40fe9923ce23b5789b8fde0bb0754ed64d8c26419fcea51fb7b7882dbabd72e0","last_reissued_at":"2026-07-05T03:35:36.724606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:36.724606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Normative Disagreement as a Challenge for Cooperative AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.LG"],"primary_cat":"cs.MA","authors_text":"Alexander Lyzhov, Allan Dafoe, Jesse Clifton, Johannes Treutlein, Julian Stastny, Maxime Rich\\'e","submitted_at":"2021-11-27T11:37:42Z","abstract_excerpt":"Cooperation in settings where agents have both common and conflicting interests (mixed-motive environments) has recently received considerable attention in multi-agent learning. However, the mixed-motive environments typically studied have a single cooperative outcome on which all agents can agree. Many real-world multi-agent environments are instead bargaining problems (BPs): they have several Pareto-optimal payoff profiles over which agents have conflicting preferences. We argue that typical cooperation-inducing learning algorithms fail to cooperate in BPs when there is room for normative di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13872","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/2111.13872/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":"2111.13872","created_at":"2026-07-05T03:35:36.724669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13872v1","created_at":"2026-07-05T03:35:36.724669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13872","created_at":"2026-07-05T03:35:36.724669+00:00"},{"alias_kind":"pith_short_12","alias_value":"ID7JSI6OEO2X","created_at":"2026-07-05T03:35:36.724669+00:00"},{"alias_kind":"pith_short_16","alias_value":"ID7JSI6OEO2XRG4P","created_at":"2026-07-05T03:35:36.724669+00:00"},{"alias_kind":"pith_short_8","alias_value":"ID7JSI6O","created_at":"2026-07-05T03:35:36.724669+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.29559","citing_title":"LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback","ref_index":282,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ID7JSI6OEO2XRG4P3YF3A5KO2Z","json":"https://pith.science/pith/ID7JSI6OEO2XRG4P3YF3A5KO2Z.json","graph_json":"https://pith.science/api/pith-number/ID7JSI6OEO2XRG4P3YF3A5KO2Z/graph.json","events_json":"https://pith.science/api/pith-number/ID7JSI6OEO2XRG4P3YF3A5KO2Z/events.json","paper":"https://pith.science/paper/ID7JSI6O"},"agent_actions":{"view_html":"https://pith.science/pith/ID7JSI6OEO2XRG4P3YF3A5KO2Z","download_json":"https://pith.science/pith/ID7JSI6OEO2XRG4P3YF3A5KO2Z.json","view_paper":"https://pith.science/paper/ID7JSI6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13872&json=true","fetch_graph":"https://pith.science/api/pith-number/ID7JSI6OEO2XRG4P3YF3A5KO2Z/graph.json","fetch_events":"https://pith.science/api/pith-number/ID7JSI6OEO2XRG4P3YF3A5KO2Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ID7JSI6OEO2XRG4P3YF3A5KO2Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ID7JSI6OEO2XRG4P3YF3A5KO2Z/action/storage_attestation","attest_author":"https://pith.science/pith/ID7JSI6OEO2XRG4P3YF3A5KO2Z/action/author_attestation","sign_citation":"https://pith.science/pith/ID7JSI6OEO2XRG4P3YF3A5KO2Z/action/citation_signature","submit_replication":"https://pith.science/pith/ID7JSI6OEO2XRG4P3YF3A5KO2Z/action/replication_record"}},"created_at":"2026-07-05T03:35:36.724669+00:00","updated_at":"2026-07-05T03:35:36.724669+00:00"}