{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FZ6A3Q6ZNWRHT72CNSIO7B3EZD","short_pith_number":"pith:FZ6A3Q6Z","schema_version":"1.0","canonical_sha256":"2e7c0dc3d96da279ff426c90ef8764c8c9039086e6af4c040d1a987ef763568e","source":{"kind":"arxiv","id":"2203.08957","version":2},"attestation_state":"computed","paper":{"title":"Risk-Averse No-Regret Learning in Online Convex Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","math.OC"],"primary_cat":"cs.LG","authors_text":"Michael M. Zavlanos, Yi Shen, Zifan Wang","submitted_at":"2022-03-16T21:36:47Z","abstract_excerpt":"We consider an online stochastic game with risk-averse agents whose goal is to learn optimal decisions that minimize the risk of incurring significantly high costs. Specifically, we use the Conditional Value at Risk (CVaR) as a risk measure that the agents can estimate using bandit feedback in the form of the cost values of only their selected actions. Since the distributions of the cost functions depend on the actions of all agents that are generally unobservable, they are themselves unknown and, therefore, the CVaR values of the costs are difficult to compute. To address this challenge, we p"},"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":"2203.08957","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-16T21:36:47Z","cross_cats_sorted":["cs.GT","math.OC"],"title_canon_sha256":"a209ba9874d998cda8a6a6e29c60babbc10122caf0f6e27fc71d99daaa04d154","abstract_canon_sha256":"3bb9c83ac74c7aa85052ee220a714b067d9ecddc8b3bd66cc3aa7ee49871e75e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:15.571170Z","signature_b64":"OZDG7DXXFFC29HQYc3bJ2xi1kLizs6TElzOh588wby2NqweV+1wKbwpyA9UK5TijH4F5qzm60yMJPcZXRZkrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e7c0dc3d96da279ff426c90ef8764c8c9039086e6af4c040d1a987ef763568e","last_reissued_at":"2026-07-05T04:32:15.570680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:15.570680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Risk-Averse No-Regret Learning in Online Convex Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","math.OC"],"primary_cat":"cs.LG","authors_text":"Michael M. Zavlanos, Yi Shen, Zifan Wang","submitted_at":"2022-03-16T21:36:47Z","abstract_excerpt":"We consider an online stochastic game with risk-averse agents whose goal is to learn optimal decisions that minimize the risk of incurring significantly high costs. Specifically, we use the Conditional Value at Risk (CVaR) as a risk measure that the agents can estimate using bandit feedback in the form of the cost values of only their selected actions. Since the distributions of the cost functions depend on the actions of all agents that are generally unobservable, they are themselves unknown and, therefore, the CVaR values of the costs are difficult to compute. To address this challenge, we p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08957","kind":"arxiv","version":2},"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/2203.08957/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":"2203.08957","created_at":"2026-07-05T04:32:15.570739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.08957v2","created_at":"2026-07-05T04:32:15.570739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08957","created_at":"2026-07-05T04:32:15.570739+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZ6A3Q6ZNWRH","created_at":"2026-07-05T04:32:15.570739+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZ6A3Q6ZNWRHT72C","created_at":"2026-07-05T04:32:15.570739+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZ6A3Q6Z","created_at":"2026-07-05T04:32:15.570739+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/FZ6A3Q6ZNWRHT72CNSIO7B3EZD","json":"https://pith.science/pith/FZ6A3Q6ZNWRHT72CNSIO7B3EZD.json","graph_json":"https://pith.science/api/pith-number/FZ6A3Q6ZNWRHT72CNSIO7B3EZD/graph.json","events_json":"https://pith.science/api/pith-number/FZ6A3Q6ZNWRHT72CNSIO7B3EZD/events.json","paper":"https://pith.science/paper/FZ6A3Q6Z"},"agent_actions":{"view_html":"https://pith.science/pith/FZ6A3Q6ZNWRHT72CNSIO7B3EZD","download_json":"https://pith.science/pith/FZ6A3Q6ZNWRHT72CNSIO7B3EZD.json","view_paper":"https://pith.science/paper/FZ6A3Q6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.08957&json=true","fetch_graph":"https://pith.science/api/pith-number/FZ6A3Q6ZNWRHT72CNSIO7B3EZD/graph.json","fetch_events":"https://pith.science/api/pith-number/FZ6A3Q6ZNWRHT72CNSIO7B3EZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZ6A3Q6ZNWRHT72CNSIO7B3EZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZ6A3Q6ZNWRHT72CNSIO7B3EZD/action/storage_attestation","attest_author":"https://pith.science/pith/FZ6A3Q6ZNWRHT72CNSIO7B3EZD/action/author_attestation","sign_citation":"https://pith.science/pith/FZ6A3Q6ZNWRHT72CNSIO7B3EZD/action/citation_signature","submit_replication":"https://pith.science/pith/FZ6A3Q6ZNWRHT72CNSIO7B3EZD/action/replication_record"}},"created_at":"2026-07-05T04:32:15.570739+00:00","updated_at":"2026-07-05T04:32:15.570739+00:00"}