{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XA335AROSF6MCCZO6Z67CRGZTF","short_pith_number":"pith:XA335ARO","schema_version":"1.0","canonical_sha256":"b837be822e917cc10b2ef67df144d999655e3f0f4da9a56f5fa43325b68c40d7","source":{"kind":"arxiv","id":"2102.10717","version":2},"attestation_state":"computed","paper":{"title":"Abstraction and Analogy-Making in Artificial Intelligence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Melanie Mitchell","submitted_at":"2021-02-22T00:12:48Z","abstract_excerpt":"Conceptual abstraction and analogy-making are key abilities underlying humans' abilities to learn, reason, and robustly adapt their knowledge to new domains. Despite of a long history of research on constructing AI systems with these abilities, no current AI system is anywhere close to a capability of forming humanlike abstractions or analogies. This paper reviews the advantages and limitations of several approaches toward this goal, including symbolic methods, deep learning, and probabilistic program induction. The paper concludes with several proposals for designing challenge tasks and evalu"},"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":"2102.10717","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-02-22T00:12:48Z","cross_cats_sorted":[],"title_canon_sha256":"86a275ece4aa8bf7b27ffbbbcf74ecefe970e071ac085ae3989f51209d8033b0","abstract_canon_sha256":"e04eb63a7cf1a140d8dad79383bbfac5da0ca596d7ff8c37b0b613239484d1cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:49:09.043248Z","signature_b64":"B4HJCeKN71Iuh5LOAuuWl7iUnLNaxCeNWMEGFOK3pNvFGeLGntL1BZQYgpEJOdnIZnCYN9vWZa9p3wxbvEhwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b837be822e917cc10b2ef67df144d999655e3f0f4da9a56f5fa43325b68c40d7","last_reissued_at":"2026-07-05T03:49:09.042822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:49:09.042822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Abstraction and Analogy-Making in Artificial Intelligence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Melanie Mitchell","submitted_at":"2021-02-22T00:12:48Z","abstract_excerpt":"Conceptual abstraction and analogy-making are key abilities underlying humans' abilities to learn, reason, and robustly adapt their knowledge to new domains. Despite of a long history of research on constructing AI systems with these abilities, no current AI system is anywhere close to a capability of forming humanlike abstractions or analogies. This paper reviews the advantages and limitations of several approaches toward this goal, including symbolic methods, deep learning, and probabilistic program induction. The paper concludes with several proposals for designing challenge tasks and evalu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10717","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/2102.10717/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":"2102.10717","created_at":"2026-07-05T03:49:09.042881+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.10717v2","created_at":"2026-07-05T03:49:09.042881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10717","created_at":"2026-07-05T03:49:09.042881+00:00"},{"alias_kind":"pith_short_12","alias_value":"XA335AROSF6M","created_at":"2026-07-05T03:49:09.042881+00:00"},{"alias_kind":"pith_short_16","alias_value":"XA335AROSF6MCCZO","created_at":"2026-07-05T03:49:09.042881+00:00"},{"alias_kind":"pith_short_8","alias_value":"XA335ARO","created_at":"2026-07-05T03:49:09.042881+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15375","citing_title":"Automatic Extraction of Metaphoric Analogies from Literary Texts: Task Formulation, Dataset Construction, and Evaluation","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XA335AROSF6MCCZO6Z67CRGZTF","json":"https://pith.science/pith/XA335AROSF6MCCZO6Z67CRGZTF.json","graph_json":"https://pith.science/api/pith-number/XA335AROSF6MCCZO6Z67CRGZTF/graph.json","events_json":"https://pith.science/api/pith-number/XA335AROSF6MCCZO6Z67CRGZTF/events.json","paper":"https://pith.science/paper/XA335ARO"},"agent_actions":{"view_html":"https://pith.science/pith/XA335AROSF6MCCZO6Z67CRGZTF","download_json":"https://pith.science/pith/XA335AROSF6MCCZO6Z67CRGZTF.json","view_paper":"https://pith.science/paper/XA335ARO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.10717&json=true","fetch_graph":"https://pith.science/api/pith-number/XA335AROSF6MCCZO6Z67CRGZTF/graph.json","fetch_events":"https://pith.science/api/pith-number/XA335AROSF6MCCZO6Z67CRGZTF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XA335AROSF6MCCZO6Z67CRGZTF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XA335AROSF6MCCZO6Z67CRGZTF/action/storage_attestation","attest_author":"https://pith.science/pith/XA335AROSF6MCCZO6Z67CRGZTF/action/author_attestation","sign_citation":"https://pith.science/pith/XA335AROSF6MCCZO6Z67CRGZTF/action/citation_signature","submit_replication":"https://pith.science/pith/XA335AROSF6MCCZO6Z67CRGZTF/action/replication_record"}},"created_at":"2026-07-05T03:49:09.042881+00:00","updated_at":"2026-07-05T03:49:09.042881+00:00"}