{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:7MUHTWWBPYOW7WGLKFYPRWNEIZ","short_pith_number":"pith:7MUHTWWB","schema_version":"1.0","canonical_sha256":"fb2879dac17e1d6fd8cb5170f8d9a44643ebfd1e9bf783aeb2a534012e48ebc8","source":{"kind":"arxiv","id":"1512.07638","version":2},"attestation_state":"computed","paper":{"title":"Satisficing in multi-armed bandit problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Naomi Ehrich Leonard, Paul Reverdy, Vaibhav Srivastava","submitted_at":"2015-12-23T21:05:16Z","abstract_excerpt":"Satisficing is a relaxation of maximizing and allows for less risky decision making in the face of uncertainty. We propose two sets of satisficing objectives for the multi-armed bandit problem, where the objective is to achieve reward-based decision-making performance above a given threshold. We show that these new problems are equivalent to various standard multi-armed bandit problems with maximizing objectives and use the equivalence to find bounds on performance. The different objectives can result in qualitatively different behavior; for example, agents explore their options continually in"},"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":"1512.07638","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-23T21:05:16Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"089cbd551def94408eba52dfa2425e36886a490b1e713aeddc1c06a0ac8f91dc","abstract_canon_sha256":"37ff7ee2c0937c8eab7c693c68ed679710ac2e1d67f2f07f39f7b132464351fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:42.783721Z","signature_b64":"e1nA4WYlYLtJWZDGFVVrAvnA0cz5SU713+U9MWTqaG7HDIFQj8p7LaCs5oNulSsi012lJImbOTnZbJAlA0zBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb2879dac17e1d6fd8cb5170f8d9a44643ebfd1e9bf783aeb2a534012e48ebc8","last_reissued_at":"2026-05-18T00:54:42.783310Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:42.783310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Satisficing in multi-armed bandit problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Naomi Ehrich Leonard, Paul Reverdy, Vaibhav Srivastava","submitted_at":"2015-12-23T21:05:16Z","abstract_excerpt":"Satisficing is a relaxation of maximizing and allows for less risky decision making in the face of uncertainty. We propose two sets of satisficing objectives for the multi-armed bandit problem, where the objective is to achieve reward-based decision-making performance above a given threshold. We show that these new problems are equivalent to various standard multi-armed bandit problems with maximizing objectives and use the equivalence to find bounds on performance. The different objectives can result in qualitatively different behavior; for example, agents explore their options continually in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.07638","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":""},"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":"1512.07638","created_at":"2026-05-18T00:54:42.783391+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.07638v2","created_at":"2026-05-18T00:54:42.783391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.07638","created_at":"2026-05-18T00:54:42.783391+00:00"},{"alias_kind":"pith_short_12","alias_value":"7MUHTWWBPYOW","created_at":"2026-05-18T12:29:10.953037+00:00"},{"alias_kind":"pith_short_16","alias_value":"7MUHTWWBPYOW7WGL","created_at":"2026-05-18T12:29:10.953037+00:00"},{"alias_kind":"pith_short_8","alias_value":"7MUHTWWB","created_at":"2026-05-18T12:29:10.953037+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/7MUHTWWBPYOW7WGLKFYPRWNEIZ","json":"https://pith.science/pith/7MUHTWWBPYOW7WGLKFYPRWNEIZ.json","graph_json":"https://pith.science/api/pith-number/7MUHTWWBPYOW7WGLKFYPRWNEIZ/graph.json","events_json":"https://pith.science/api/pith-number/7MUHTWWBPYOW7WGLKFYPRWNEIZ/events.json","paper":"https://pith.science/paper/7MUHTWWB"},"agent_actions":{"view_html":"https://pith.science/pith/7MUHTWWBPYOW7WGLKFYPRWNEIZ","download_json":"https://pith.science/pith/7MUHTWWBPYOW7WGLKFYPRWNEIZ.json","view_paper":"https://pith.science/paper/7MUHTWWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.07638&json=true","fetch_graph":"https://pith.science/api/pith-number/7MUHTWWBPYOW7WGLKFYPRWNEIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7MUHTWWBPYOW7WGLKFYPRWNEIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7MUHTWWBPYOW7WGLKFYPRWNEIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7MUHTWWBPYOW7WGLKFYPRWNEIZ/action/storage_attestation","attest_author":"https://pith.science/pith/7MUHTWWBPYOW7WGLKFYPRWNEIZ/action/author_attestation","sign_citation":"https://pith.science/pith/7MUHTWWBPYOW7WGLKFYPRWNEIZ/action/citation_signature","submit_replication":"https://pith.science/pith/7MUHTWWBPYOW7WGLKFYPRWNEIZ/action/replication_record"}},"created_at":"2026-05-18T00:54:42.783391+00:00","updated_at":"2026-05-18T00:54:42.783391+00:00"}