{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:53T3DDC7RPAIURQFLWVW2VWCNU","short_pith_number":"pith:53T3DDC7","schema_version":"1.0","canonical_sha256":"eee7b18c5f8bc08a46055dab6d56c26d2827de955bf17171b5abe4ea3dc5daf1","source":{"kind":"arxiv","id":"2112.10859","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Incentive Design with Multi-Agent Meta-Gradient Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Ethan Wang, Hongyuan Zha, Jiachen Yang, Rakshit Trivedi, Tuo Zhao","submitted_at":"2021-12-20T21:07:44Z","abstract_excerpt":"Critical sectors of human society are progressing toward the adoption of powerful artificial intelligence (AI) agents, which are trained individually on behalf of self-interested principals but deployed in a shared environment. Short of direct centralized regulation of AI, which is as difficult an issue as regulation of human actions, one must design institutional mechanisms that indirectly guide agents' behaviors to safeguard and improve social welfare in the shared environment. Our paper focuses on one important class of such mechanisms: the problem of adaptive incentive design, whereby a ce"},"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":"2112.10859","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2021-12-20T21:07:44Z","cross_cats_sorted":[],"title_canon_sha256":"537798c2da9a1abd0a08e41eb14de268057c4e3f7f39e9cb253b8235678a38c2","abstract_canon_sha256":"516eb65406c7e6aae668e8dc6921c228229128ffdfe17d03d52e70e4e54ead10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:42:27.037524Z","signature_b64":"H3C18WDFsrih16aliBkjwBDo8UjDjMBC3ern/eNtpzYEw9+uAkiLTyM9WlYepVlWlv0hGvPQXP17tdoFPGHZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eee7b18c5f8bc08a46055dab6d56c26d2827de955bf17171b5abe4ea3dc5daf1","last_reissued_at":"2026-07-05T03:42:27.036949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:42:27.036949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Incentive Design with Multi-Agent Meta-Gradient Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Ethan Wang, Hongyuan Zha, Jiachen Yang, Rakshit Trivedi, Tuo Zhao","submitted_at":"2021-12-20T21:07:44Z","abstract_excerpt":"Critical sectors of human society are progressing toward the adoption of powerful artificial intelligence (AI) agents, which are trained individually on behalf of self-interested principals but deployed in a shared environment. Short of direct centralized regulation of AI, which is as difficult an issue as regulation of human actions, one must design institutional mechanisms that indirectly guide agents' behaviors to safeguard and improve social welfare in the shared environment. Our paper focuses on one important class of such mechanisms: the problem of adaptive incentive design, whereby a ce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10859","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/2112.10859/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":"2112.10859","created_at":"2026-07-05T03:42:27.037007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.10859v1","created_at":"2026-07-05T03:42:27.037007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10859","created_at":"2026-07-05T03:42:27.037007+00:00"},{"alias_kind":"pith_short_12","alias_value":"53T3DDC7RPAI","created_at":"2026-07-05T03:42:27.037007+00:00"},{"alias_kind":"pith_short_16","alias_value":"53T3DDC7RPAIURQF","created_at":"2026-07-05T03:42:27.037007+00:00"},{"alias_kind":"pith_short_8","alias_value":"53T3DDC7","created_at":"2026-07-05T03:42:27.037007+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23027","citing_title":"PIMbot: A Self-Adaptive Attack Framework for Adversarial Manipulation of Multi-Robot Reinforcement Learning","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/53T3DDC7RPAIURQFLWVW2VWCNU","json":"https://pith.science/pith/53T3DDC7RPAIURQFLWVW2VWCNU.json","graph_json":"https://pith.science/api/pith-number/53T3DDC7RPAIURQFLWVW2VWCNU/graph.json","events_json":"https://pith.science/api/pith-number/53T3DDC7RPAIURQFLWVW2VWCNU/events.json","paper":"https://pith.science/paper/53T3DDC7"},"agent_actions":{"view_html":"https://pith.science/pith/53T3DDC7RPAIURQFLWVW2VWCNU","download_json":"https://pith.science/pith/53T3DDC7RPAIURQFLWVW2VWCNU.json","view_paper":"https://pith.science/paper/53T3DDC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.10859&json=true","fetch_graph":"https://pith.science/api/pith-number/53T3DDC7RPAIURQFLWVW2VWCNU/graph.json","fetch_events":"https://pith.science/api/pith-number/53T3DDC7RPAIURQFLWVW2VWCNU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53T3DDC7RPAIURQFLWVW2VWCNU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53T3DDC7RPAIURQFLWVW2VWCNU/action/storage_attestation","attest_author":"https://pith.science/pith/53T3DDC7RPAIURQFLWVW2VWCNU/action/author_attestation","sign_citation":"https://pith.science/pith/53T3DDC7RPAIURQFLWVW2VWCNU/action/citation_signature","submit_replication":"https://pith.science/pith/53T3DDC7RPAIURQFLWVW2VWCNU/action/replication_record"}},"created_at":"2026-07-05T03:42:27.037007+00:00","updated_at":"2026-07-05T03:42:27.037007+00:00"}