{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W6WUUYXADXVQCJNSBZF6P7QCZA","short_pith_number":"pith:W6WUUYXA","schema_version":"1.0","canonical_sha256":"b7ad4a62e01deb0125b20e4be7fe02c82460b20b9f4d98e2b4c8200ba0b2286a","source":{"kind":"arxiv","id":"2303.13360","version":1},"attestation_state":"computed","paper":{"title":"Towards the Scalable Evaluation of Cooperativeness in Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alan Chan, Jesse Clifton, Maxime Rich\\'e","submitted_at":"2023-03-16T15:34:23Z","abstract_excerpt":"It is likely that AI systems driven by pre-trained language models (PLMs) will increasingly be used to assist humans in high-stakes interactions with other agents, such as negotiation or conflict resolution. Consistent with the goals of Cooperative AI \\citep{dafoe_open_2020}, we wish to understand and shape the multi-agent behaviors of PLMs in a pro-social manner. An important first step is the evaluation of model behaviour across diverse cooperation problems. Since desired behaviour in an interaction depends upon precise game-theoretic structure, we focus on generating scenarios with particul"},"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":"2303.13360","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-16T15:34:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"78671b38765203446f0cea1a936dd2cd60a014c21d50593ea524efb3c081c3ae","abstract_canon_sha256":"3696c33f841be6d8cc042b44d95eb404e215ddac59798cef8ee7d0fe9a7536de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:01.114078Z","signature_b64":"Et4YQv8T+IaX6pf67sfNWF3caFPJgnaNCeyclwfYf93N8QFriHuwlcYP7Ufw7rladP4OhbuH3UTtdC/uocLSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7ad4a62e01deb0125b20e4be7fe02c82460b20b9f4d98e2b4c8200ba0b2286a","last_reissued_at":"2026-07-05T05:54:01.113682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:01.113682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards the Scalable Evaluation of Cooperativeness in Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alan Chan, Jesse Clifton, Maxime Rich\\'e","submitted_at":"2023-03-16T15:34:23Z","abstract_excerpt":"It is likely that AI systems driven by pre-trained language models (PLMs) will increasingly be used to assist humans in high-stakes interactions with other agents, such as negotiation or conflict resolution. Consistent with the goals of Cooperative AI \\citep{dafoe_open_2020}, we wish to understand and shape the multi-agent behaviors of PLMs in a pro-social manner. An important first step is the evaluation of model behaviour across diverse cooperation problems. Since desired behaviour in an interaction depends upon precise game-theoretic structure, we focus on generating scenarios with particul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13360","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/2303.13360/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":"2303.13360","created_at":"2026-07-05T05:54:01.113742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.13360v1","created_at":"2026-07-05T05:54:01.113742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13360","created_at":"2026-07-05T05:54:01.113742+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6WUUYXADXVQ","created_at":"2026-07-05T05:54:01.113742+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6WUUYXADXVQCJNS","created_at":"2026-07-05T05:54:01.113742+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6WUUYXA","created_at":"2026-07-05T05:54:01.113742+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10588","citing_title":"A dataset of questions on decision-theoretic reasoning in Newcomb-like problems","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6WUUYXADXVQCJNSBZF6P7QCZA","json":"https://pith.science/pith/W6WUUYXADXVQCJNSBZF6P7QCZA.json","graph_json":"https://pith.science/api/pith-number/W6WUUYXADXVQCJNSBZF6P7QCZA/graph.json","events_json":"https://pith.science/api/pith-number/W6WUUYXADXVQCJNSBZF6P7QCZA/events.json","paper":"https://pith.science/paper/W6WUUYXA"},"agent_actions":{"view_html":"https://pith.science/pith/W6WUUYXADXVQCJNSBZF6P7QCZA","download_json":"https://pith.science/pith/W6WUUYXADXVQCJNSBZF6P7QCZA.json","view_paper":"https://pith.science/paper/W6WUUYXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.13360&json=true","fetch_graph":"https://pith.science/api/pith-number/W6WUUYXADXVQCJNSBZF6P7QCZA/graph.json","fetch_events":"https://pith.science/api/pith-number/W6WUUYXADXVQCJNSBZF6P7QCZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6WUUYXADXVQCJNSBZF6P7QCZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6WUUYXADXVQCJNSBZF6P7QCZA/action/storage_attestation","attest_author":"https://pith.science/pith/W6WUUYXADXVQCJNSBZF6P7QCZA/action/author_attestation","sign_citation":"https://pith.science/pith/W6WUUYXADXVQCJNSBZF6P7QCZA/action/citation_signature","submit_replication":"https://pith.science/pith/W6WUUYXADXVQCJNSBZF6P7QCZA/action/replication_record"}},"created_at":"2026-07-05T05:54:01.113742+00:00","updated_at":"2026-07-05T05:54:01.113742+00:00"}