{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NX47OMOVQLSTCXCHNFR6PACLCZ","short_pith_number":"pith:NX47OMOV","schema_version":"1.0","canonical_sha256":"6df9f731d582e5315c476963e7804b1653d677af4fedc226c710c7513cd42a0a","source":{"kind":"arxiv","id":"2201.01819","version":1},"attestation_state":"computed","paper":{"title":"Formal Analysis of Art: Proxy Learning of Visual Concepts from Style Through Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Ahmed Elgammal, Diana Kim, Marian Mazzone","submitted_at":"2022-01-05T21:03:29Z","abstract_excerpt":"We present a machine learning system that can quantify fine art paintings with a set of visual elements and principles of art. This formal analysis is fundamental for understanding art, but developing such a system is challenging. Paintings have high visual complexities, but it is also difficult to collect enough training data with direct labels. To resolve these practical limitations, we introduce a novel mechanism, called proxy learning, which learns visual concepts in paintings though their general relation to styles. This framework does not require any visual annotation, but only uses styl"},"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":"2201.01819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-05T21:03:29Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"5b5c237a469e598a49a484ac5396a4eb523b55010ad754d7fc88ffe25258a0fa","abstract_canon_sha256":"ba5003c3170472e726025a31ff8b2ab1a7405cef43c482201fa320ec4c137a5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:10.625417Z","signature_b64":"A4mdWwIjGJimNbBiDDacGWXNxGaGsyK7bVYcy9oRu+IFbG1KDCENPn6hTBHp3zw1Ia4Qj19j2Grcs3LKd20uDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6df9f731d582e5315c476963e7804b1653d677af4fedc226c710c7513cd42a0a","last_reissued_at":"2026-07-05T03:48:10.624996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:10.624996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Formal Analysis of Art: Proxy Learning of Visual Concepts from Style Through Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Ahmed Elgammal, Diana Kim, Marian Mazzone","submitted_at":"2022-01-05T21:03:29Z","abstract_excerpt":"We present a machine learning system that can quantify fine art paintings with a set of visual elements and principles of art. This formal analysis is fundamental for understanding art, but developing such a system is challenging. Paintings have high visual complexities, but it is also difficult to collect enough training data with direct labels. To resolve these practical limitations, we introduce a novel mechanism, called proxy learning, which learns visual concepts in paintings though their general relation to styles. This framework does not require any visual annotation, but only uses styl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01819","kind":"arxiv","version":1},"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/2201.01819/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":"2201.01819","created_at":"2026-07-05T03:48:10.625053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.01819v1","created_at":"2026-07-05T03:48:10.625053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01819","created_at":"2026-07-05T03:48:10.625053+00:00"},{"alias_kind":"pith_short_12","alias_value":"NX47OMOVQLST","created_at":"2026-07-05T03:48:10.625053+00:00"},{"alias_kind":"pith_short_16","alias_value":"NX47OMOVQLSTCXCH","created_at":"2026-07-05T03:48:10.625053+00:00"},{"alias_kind":"pith_short_8","alias_value":"NX47OMOV","created_at":"2026-07-05T03:48:10.625053+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09012","citing_title":"Multimodal LLMs Can Reason about Aesthetics in Zero-Shot","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NX47OMOVQLSTCXCHNFR6PACLCZ","json":"https://pith.science/pith/NX47OMOVQLSTCXCHNFR6PACLCZ.json","graph_json":"https://pith.science/api/pith-number/NX47OMOVQLSTCXCHNFR6PACLCZ/graph.json","events_json":"https://pith.science/api/pith-number/NX47OMOVQLSTCXCHNFR6PACLCZ/events.json","paper":"https://pith.science/paper/NX47OMOV"},"agent_actions":{"view_html":"https://pith.science/pith/NX47OMOVQLSTCXCHNFR6PACLCZ","download_json":"https://pith.science/pith/NX47OMOVQLSTCXCHNFR6PACLCZ.json","view_paper":"https://pith.science/paper/NX47OMOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.01819&json=true","fetch_graph":"https://pith.science/api/pith-number/NX47OMOVQLSTCXCHNFR6PACLCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/NX47OMOVQLSTCXCHNFR6PACLCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NX47OMOVQLSTCXCHNFR6PACLCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NX47OMOVQLSTCXCHNFR6PACLCZ/action/storage_attestation","attest_author":"https://pith.science/pith/NX47OMOVQLSTCXCHNFR6PACLCZ/action/author_attestation","sign_citation":"https://pith.science/pith/NX47OMOVQLSTCXCHNFR6PACLCZ/action/citation_signature","submit_replication":"https://pith.science/pith/NX47OMOVQLSTCXCHNFR6PACLCZ/action/replication_record"}},"created_at":"2026-07-05T03:48:10.625053+00:00","updated_at":"2026-07-05T03:48:10.625053+00:00"}