{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P7RGUUICRWPDCNMLFN6UV5RP4Q","short_pith_number":"pith:P7RGUUIC","schema_version":"1.0","canonical_sha256":"7fe26a51028d9e31358b2b7d4af62fe416ede9d66f56e558eb1ce0dcc7b01ea5","source":{"kind":"arxiv","id":"2510.06288","version":4},"attestation_state":"computed","paper":{"title":"BuilderBench: The Building Blocks of Intelligent Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Benjamin Eysenbach, Catherine Ji, Jin Schofield, Karthik Narasimhan, Kathryn Wantlin, Raj Ghugare, Roger Creus Castanyer","submitted_at":"2025-10-07T04:23:48Z","abstract_excerpt":"Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set by existing data. To solve novel problems, agents should acquire skills by exploring and learning through experience. Finding a scalable learning mechanism for developing agents that learn through interaction remains a major open problem. In this work, we introduce BuilderBench, a benchmark to accelerate research into agent training that centers open-ended exploration. BuilderBench requires agents to learn how to build any structure using blocks. Bu"},"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":"2510.06288","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-07T04:23:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1cdf1e6e4ef7f48d7417e1fef1841f262c0372c04ffe29e9dd687be5178c4713","abstract_canon_sha256":"41adfe14b4d57a0905c79c0fa3614a2cc759f3c05180caf71b0cf8ff03b7417e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:13.521845Z","signature_b64":"aWfEO1D5OPgZnqR7q9hqWwc9JjqDfNsuHs0pRrr8qqjmj71paZgk6u8xjM1+jjTD24DQva5pMRCYXyeG8BAEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fe26a51028d9e31358b2b7d4af62fe416ede9d66f56e558eb1ce0dcc7b01ea5","last_reissued_at":"2026-07-03T01:17:13.521290Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:13.521290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BuilderBench: The Building Blocks of Intelligent Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Benjamin Eysenbach, Catherine Ji, Jin Schofield, Karthik Narasimhan, Kathryn Wantlin, Raj Ghugare, Roger Creus Castanyer","submitted_at":"2025-10-07T04:23:48Z","abstract_excerpt":"Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set by existing data. To solve novel problems, agents should acquire skills by exploring and learning through experience. Finding a scalable learning mechanism for developing agents that learn through interaction remains a major open problem. In this work, we introduce BuilderBench, a benchmark to accelerate research into agent training that centers open-ended exploration. BuilderBench requires agents to learn how to build any structure using blocks. Bu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.06288","kind":"arxiv","version":4},"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/2510.06288/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":"2510.06288","created_at":"2026-07-03T01:17:13.521370+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.06288v4","created_at":"2026-07-03T01:17:13.521370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.06288","created_at":"2026-07-03T01:17:13.521370+00:00"},{"alias_kind":"pith_short_12","alias_value":"P7RGUUICRWPD","created_at":"2026-07-03T01:17:13.521370+00:00"},{"alias_kind":"pith_short_16","alias_value":"P7RGUUICRWPDCNML","created_at":"2026-07-03T01:17:13.521370+00:00"},{"alias_kind":"pith_short_8","alias_value":"P7RGUUIC","created_at":"2026-07-03T01:17:13.521370+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":111,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23551","citing_title":"Goal-Conditioned Agents that Learn Everything All at Once","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17829","citing_title":"Interactive Evaluation Requires a Design Science","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":111,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P7RGUUICRWPDCNMLFN6UV5RP4Q","json":"https://pith.science/pith/P7RGUUICRWPDCNMLFN6UV5RP4Q.json","graph_json":"https://pith.science/api/pith-number/P7RGUUICRWPDCNMLFN6UV5RP4Q/graph.json","events_json":"https://pith.science/api/pith-number/P7RGUUICRWPDCNMLFN6UV5RP4Q/events.json","paper":"https://pith.science/paper/P7RGUUIC"},"agent_actions":{"view_html":"https://pith.science/pith/P7RGUUICRWPDCNMLFN6UV5RP4Q","download_json":"https://pith.science/pith/P7RGUUICRWPDCNMLFN6UV5RP4Q.json","view_paper":"https://pith.science/paper/P7RGUUIC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.06288&json=true","fetch_graph":"https://pith.science/api/pith-number/P7RGUUICRWPDCNMLFN6UV5RP4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/P7RGUUICRWPDCNMLFN6UV5RP4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P7RGUUICRWPDCNMLFN6UV5RP4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P7RGUUICRWPDCNMLFN6UV5RP4Q/action/storage_attestation","attest_author":"https://pith.science/pith/P7RGUUICRWPDCNMLFN6UV5RP4Q/action/author_attestation","sign_citation":"https://pith.science/pith/P7RGUUICRWPDCNMLFN6UV5RP4Q/action/citation_signature","submit_replication":"https://pith.science/pith/P7RGUUICRWPDCNMLFN6UV5RP4Q/action/replication_record"}},"created_at":"2026-07-03T01:17:13.521370+00:00","updated_at":"2026-07-03T01:17:13.521370+00:00"}