{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:27XHZGIEBG32J5NVBZIPMPPMJU","short_pith_number":"pith:27XHZGIE","schema_version":"1.0","canonical_sha256":"d7ee7c990409b7a4f5b50e50f63dec4d029efb5418336907c0bf615208a48f31","source":{"kind":"arxiv","id":"1112.5309","version":2},"attestation_state":"computed","paper":{"title":"POWERPLAY: Training an Increasingly General Problem Solver by Continually Searching for the Simplest Still Unsolvable Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"J\\\"urgen Schmidhuber","submitted_at":"2011-12-22T13:50:46Z","abstract_excerpt":"Most of computer science focuses on automatically solving given computational problems. I focus on automatically inventing or discovering problems in a way inspired by the playful behavior of animals and humans, to train a more and more general problem solver from scratch in an unsupervised fashion. Consider the infinite set of all computable descriptions of tasks with possibly computable solutions. The novel algorithmic framework POWERPLAY (2011) continually searches the space of possible pairs of new tasks and modifications of the current problem solver, until it finds a more powerful proble"},"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":"1112.5309","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-12-22T13:50:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3323ad9c7915902c74fcfc102d7223d12ef50645599ec9e150a19bd833dd1fcd","abstract_canon_sha256":"3fdabf57c3384d062602487aacf27631b4bd6f6a65176190a658d196a1c7bd44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:41:40.412633Z","signature_b64":"xfqJNOSnSQLtjQMB3VdcwXMAOZB3KZhz2AeqhEeod4Zv2FGll26gXLJyjNxM8Jjye58JOBYL5mpfPyKdWwSQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7ee7c990409b7a4f5b50e50f63dec4d029efb5418336907c0bf615208a48f31","last_reissued_at":"2026-05-18T03:41:40.410279Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:41:40.410279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"POWERPLAY: Training an Increasingly General Problem Solver by Continually Searching for the Simplest Still Unsolvable Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"J\\\"urgen Schmidhuber","submitted_at":"2011-12-22T13:50:46Z","abstract_excerpt":"Most of computer science focuses on automatically solving given computational problems. I focus on automatically inventing or discovering problems in a way inspired by the playful behavior of animals and humans, to train a more and more general problem solver from scratch in an unsupervised fashion. Consider the infinite set of all computable descriptions of tasks with possibly computable solutions. The novel algorithmic framework POWERPLAY (2011) continually searches the space of possible pairs of new tasks and modifications of the current problem solver, until it finds a more powerful proble"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1112.5309","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":"1112.5309","created_at":"2026-05-18T03:41:40.410417+00:00"},{"alias_kind":"arxiv_version","alias_value":"1112.5309v2","created_at":"2026-05-18T03:41:40.410417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1112.5309","created_at":"2026-05-18T03:41:40.410417+00:00"},{"alias_kind":"pith_short_12","alias_value":"27XHZGIEBG32","created_at":"2026-05-18T12:26:18.847500+00:00"},{"alias_kind":"pith_short_16","alias_value":"27XHZGIEBG32J5NV","created_at":"2026-05-18T12:26:18.847500+00:00"},{"alias_kind":"pith_short_8","alias_value":"27XHZGIE","created_at":"2026-05-18T12:26:18.847500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1910.07113","citing_title":"Solving Rubik's Cube with a Robot Hand","ref_index":97,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03201","citing_title":"Coupled Control, Structured Memory, and Verifiable Action in Agentic AI (SCRAT -- Stochastic Control with Retrieval and Auditable Trajectories): A Comparative Perspective from Squirrel Locomotion and ","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/27XHZGIEBG32J5NVBZIPMPPMJU","json":"https://pith.science/pith/27XHZGIEBG32J5NVBZIPMPPMJU.json","graph_json":"https://pith.science/api/pith-number/27XHZGIEBG32J5NVBZIPMPPMJU/graph.json","events_json":"https://pith.science/api/pith-number/27XHZGIEBG32J5NVBZIPMPPMJU/events.json","paper":"https://pith.science/paper/27XHZGIE"},"agent_actions":{"view_html":"https://pith.science/pith/27XHZGIEBG32J5NVBZIPMPPMJU","download_json":"https://pith.science/pith/27XHZGIEBG32J5NVBZIPMPPMJU.json","view_paper":"https://pith.science/paper/27XHZGIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1112.5309&json=true","fetch_graph":"https://pith.science/api/pith-number/27XHZGIEBG32J5NVBZIPMPPMJU/graph.json","fetch_events":"https://pith.science/api/pith-number/27XHZGIEBG32J5NVBZIPMPPMJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27XHZGIEBG32J5NVBZIPMPPMJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27XHZGIEBG32J5NVBZIPMPPMJU/action/storage_attestation","attest_author":"https://pith.science/pith/27XHZGIEBG32J5NVBZIPMPPMJU/action/author_attestation","sign_citation":"https://pith.science/pith/27XHZGIEBG32J5NVBZIPMPPMJU/action/citation_signature","submit_replication":"https://pith.science/pith/27XHZGIEBG32J5NVBZIPMPPMJU/action/replication_record"}},"created_at":"2026-05-18T03:41:40.410417+00:00","updated_at":"2026-05-18T03:41:40.410417+00:00"}