{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HA37AHUQOGYOCQ2IADBEKFNU6P","short_pith_number":"pith:HA37AHUQ","schema_version":"1.0","canonical_sha256":"3837f01e9071b0e1434800c24515b4f3e35a6fa50b58ce289afad5d494f13292","source":{"kind":"arxiv","id":"2503.23631","version":2},"attestation_state":"computed","paper":{"title":"Intrinsically-Motivated Humans and Agents in Open-World Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alison Gopnik, Aly Lidayan, Eliza Kosoy, Maria Rufova, Pieter Abbeel, Yuqing Du","submitted_at":"2025-03-31T00:09:00Z","abstract_excerpt":"What drives exploration? Understanding intrinsic motivation is a long-standing challenge in both cognitive science and artificial intelligence; numerous objectives have been proposed and used to train agents, yet there remains a gap between human and agent exploration. We directly compare adults, children, and AI agents in a complex open-ended environment, Crafter, and study how common intrinsic objectives: Entropy, Information Gain, and Empowerment, relate to their behavior. We find that only Entropy and Empowerment are consistently positively correlated with human exploration progress, indic"},"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":"2503.23631","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-31T00:09:00Z","cross_cats_sorted":[],"title_canon_sha256":"ca0364082ebf13b0aabc4bde7c7b0a7843629d77ffeab72515da238ce666589c","abstract_canon_sha256":"543134fb09023ee7e306704cdeec13ae1af240430e9c632674f9472ba50bc3d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:55.058050Z","signature_b64":"VGFx7nbLIKvF0darMALw/+61V2jG7NYULMN8lor6N8M/rujTzkm5CcIseQrexGt8zjKAhX/VUTfaFuR1PHh2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3837f01e9071b0e1434800c24515b4f3e35a6fa50b58ce289afad5d494f13292","last_reissued_at":"2026-07-05T11:10:55.057503Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:55.057503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intrinsically-Motivated Humans and Agents in Open-World Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alison Gopnik, Aly Lidayan, Eliza Kosoy, Maria Rufova, Pieter Abbeel, Yuqing Du","submitted_at":"2025-03-31T00:09:00Z","abstract_excerpt":"What drives exploration? Understanding intrinsic motivation is a long-standing challenge in both cognitive science and artificial intelligence; numerous objectives have been proposed and used to train agents, yet there remains a gap between human and agent exploration. We directly compare adults, children, and AI agents in a complex open-ended environment, Crafter, and study how common intrinsic objectives: Entropy, Information Gain, and Empowerment, relate to their behavior. We find that only Entropy and Empowerment are consistently positively correlated with human exploration progress, indic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23631","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/2503.23631/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":"2503.23631","created_at":"2026-07-05T11:10:55.057566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23631v2","created_at":"2026-07-05T11:10:55.057566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23631","created_at":"2026-07-05T11:10:55.057566+00:00"},{"alias_kind":"pith_short_12","alias_value":"HA37AHUQOGYO","created_at":"2026-07-05T11:10:55.057566+00:00"},{"alias_kind":"pith_short_16","alias_value":"HA37AHUQOGYOCQ2I","created_at":"2026-07-05T11:10:55.057566+00:00"},{"alias_kind":"pith_short_8","alias_value":"HA37AHUQ","created_at":"2026-07-05T11:10:55.057566+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22255","citing_title":"Agent-centric learning: from external reward maximization to internal knowledge curation","ref_index":2015,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HA37AHUQOGYOCQ2IADBEKFNU6P","json":"https://pith.science/pith/HA37AHUQOGYOCQ2IADBEKFNU6P.json","graph_json":"https://pith.science/api/pith-number/HA37AHUQOGYOCQ2IADBEKFNU6P/graph.json","events_json":"https://pith.science/api/pith-number/HA37AHUQOGYOCQ2IADBEKFNU6P/events.json","paper":"https://pith.science/paper/HA37AHUQ"},"agent_actions":{"view_html":"https://pith.science/pith/HA37AHUQOGYOCQ2IADBEKFNU6P","download_json":"https://pith.science/pith/HA37AHUQOGYOCQ2IADBEKFNU6P.json","view_paper":"https://pith.science/paper/HA37AHUQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23631&json=true","fetch_graph":"https://pith.science/api/pith-number/HA37AHUQOGYOCQ2IADBEKFNU6P/graph.json","fetch_events":"https://pith.science/api/pith-number/HA37AHUQOGYOCQ2IADBEKFNU6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HA37AHUQOGYOCQ2IADBEKFNU6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HA37AHUQOGYOCQ2IADBEKFNU6P/action/storage_attestation","attest_author":"https://pith.science/pith/HA37AHUQOGYOCQ2IADBEKFNU6P/action/author_attestation","sign_citation":"https://pith.science/pith/HA37AHUQOGYOCQ2IADBEKFNU6P/action/citation_signature","submit_replication":"https://pith.science/pith/HA37AHUQOGYOCQ2IADBEKFNU6P/action/replication_record"}},"created_at":"2026-07-05T11:10:55.057566+00:00","updated_at":"2026-07-05T11:10:55.057566+00:00"}