{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4MGNWS2E7PIRES4JZGLJQOUNDP","short_pith_number":"pith:4MGNWS2E","schema_version":"1.0","canonical_sha256":"e30cdb4b44fbd1124b89c996983a8d1bd058edfbb7ca214391be115ee457274b","source":{"kind":"arxiv","id":"2306.01711","version":3},"attestation_state":"computed","paper":{"title":"OMNI: Open-endedness via Models of human Notions of Interestingness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jeff Clune, Jenny Zhang, Joel Lehman, Kenneth Stanley","submitted_at":"2023-06-02T17:32:17Z","abstract_excerpt":"Open-ended algorithms aim to learn new, interesting behaviors forever. That requires a vast environment search space, but there are thus infinitely many possible tasks. Even after filtering for tasks the current agent can learn (i.e., learning progress), countless learnable yet uninteresting tasks remain (e.g., minor variations of previously learned tasks). An Achilles Heel of open-endedness research is the inability to quantify (and thus prioritize) tasks that are not just learnable, but also $\\textit{interesting}$ (e.g., worthwhile and novel). We propose solving this problem by $\\textit{Open"},"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":"2306.01711","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-06-02T17:32:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d4c4f5ef061c6113892fa78ef56e8c4b948a2bc9714fd49b29e191bf06e8aeaa","abstract_canon_sha256":"c119d3107277f64dc9eecf487a0bffd842fa472c02ca7661781b70184793dd2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:27.783105Z","signature_b64":"A3oa+UI+49q+QttGX/EkAsXUVE4VnmbNEWxOUFs7IURQY87BMikc8uLwKamUKJZWnXhbsOBEMbhIWPovLMRkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e30cdb4b44fbd1124b89c996983a8d1bd058edfbb7ca214391be115ee457274b","last_reissued_at":"2026-07-05T07:45:27.782599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:27.782599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OMNI: Open-endedness via Models of human Notions of Interestingness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jeff Clune, Jenny Zhang, Joel Lehman, Kenneth Stanley","submitted_at":"2023-06-02T17:32:17Z","abstract_excerpt":"Open-ended algorithms aim to learn new, interesting behaviors forever. That requires a vast environment search space, but there are thus infinitely many possible tasks. Even after filtering for tasks the current agent can learn (i.e., learning progress), countless learnable yet uninteresting tasks remain (e.g., minor variations of previously learned tasks). An Achilles Heel of open-endedness research is the inability to quantify (and thus prioritize) tasks that are not just learnable, but also $\\textit{interesting}$ (e.g., worthwhile and novel). We propose solving this problem by $\\textit{Open"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01711","kind":"arxiv","version":3},"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/2306.01711/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":"2306.01711","created_at":"2026-07-05T07:45:27.782655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01711v3","created_at":"2026-07-05T07:45:27.782655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01711","created_at":"2026-07-05T07:45:27.782655+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MGNWS2E7PIR","created_at":"2026-07-05T07:45:27.782655+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MGNWS2E7PIRES4J","created_at":"2026-07-05T07:45:27.782655+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MGNWS2E","created_at":"2026-07-05T07:45:27.782655+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25198","citing_title":"Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14831","citing_title":"Interestingness as an Inductive Heuristic for Future Compression Progress","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25198","citing_title":"Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23551","citing_title":"Goal-Conditioned Agents that Learn Everything All at Once","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03295","citing_title":"Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05859","citing_title":"When Do We Need LLMs? A Diagnostic for Language-Driven Bandits","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4MGNWS2E7PIRES4JZGLJQOUNDP","json":"https://pith.science/pith/4MGNWS2E7PIRES4JZGLJQOUNDP.json","graph_json":"https://pith.science/api/pith-number/4MGNWS2E7PIRES4JZGLJQOUNDP/graph.json","events_json":"https://pith.science/api/pith-number/4MGNWS2E7PIRES4JZGLJQOUNDP/events.json","paper":"https://pith.science/paper/4MGNWS2E"},"agent_actions":{"view_html":"https://pith.science/pith/4MGNWS2E7PIRES4JZGLJQOUNDP","download_json":"https://pith.science/pith/4MGNWS2E7PIRES4JZGLJQOUNDP.json","view_paper":"https://pith.science/paper/4MGNWS2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01711&json=true","fetch_graph":"https://pith.science/api/pith-number/4MGNWS2E7PIRES4JZGLJQOUNDP/graph.json","fetch_events":"https://pith.science/api/pith-number/4MGNWS2E7PIRES4JZGLJQOUNDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MGNWS2E7PIRES4JZGLJQOUNDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MGNWS2E7PIRES4JZGLJQOUNDP/action/storage_attestation","attest_author":"https://pith.science/pith/4MGNWS2E7PIRES4JZGLJQOUNDP/action/author_attestation","sign_citation":"https://pith.science/pith/4MGNWS2E7PIRES4JZGLJQOUNDP/action/citation_signature","submit_replication":"https://pith.science/pith/4MGNWS2E7PIRES4JZGLJQOUNDP/action/replication_record"}},"created_at":"2026-07-05T07:45:27.782655+00:00","updated_at":"2026-07-05T07:45:27.782655+00:00"}