{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q7IDIH5AJTTPWVDVGCSSBI3KYE","short_pith_number":"pith:Q7IDIH5A","schema_version":"1.0","canonical_sha256":"87d0341fa04ce6fb547530a520a36ac134be92c14e212cadfa4dd3ba86fec25a","source":{"kind":"arxiv","id":"2501.09012","version":3},"attestation_state":"computed","paper":{"title":"Multimodal LLMs Can Reason about Aesthetics in Zero-Shot","license":"","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Changwen Chen, Ruixiang Jiang","submitted_at":"2025-01-15T18:56:22Z","abstract_excerpt":"The rapid technical progress of generative art (GenArt) has democratized the creation of visually appealing imagery. However, achieving genuine artistic impact - the kind that resonates with viewers on a deeper, more meaningful level - remains formidable as it requires a sophisticated aesthetic sensibility. This sensibility involves a multifaceted cognitive process extending beyond mere visual appeal, which is often overlooked by current computational methods. This paper pioneers an approach to capture this complex process by investigating how the reasoning capabilities of Multimodal LLMs (MLL"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":true,"weak_author_claims":0,"strong_author_claims":1,"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":"2501.09012","kind":"arxiv","version":3},"metadata":{"license":"","primary_cat":"cs.CV","submitted_at":"2025-01-15T18:56:22Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"e0c7371801c6dab1c7c579486b9277667a5b9abc5ead9162a14d652549dfecf9","abstract_canon_sha256":"a47dd607dfe67f4007226fc16c68cc4929f688b551cfddfebd0d392a1cba08a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-28T15:26:19.310919Z","signature_b64":"qcPQJp+q0V6nhyswoR+Bh2RAjibiuqkWTG5hzNWYSAqhQZLswy6WftEbe/nBOCeNeJNPemJqE/iKNaoAb+KhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87d0341fa04ce6fb547530a520a36ac134be92c14e212cadfa4dd3ba86fec25a","last_reissued_at":"2026-06-28T15:26:19.310436Z","signature_status":"signed_v1","first_computed_at":"2026-06-28T15:26:19.310436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal LLMs Can Reason about Aesthetics in Zero-Shot","license":"","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Changwen Chen, Ruixiang Jiang","submitted_at":"2025-01-15T18:56:22Z","abstract_excerpt":"The rapid technical progress of generative art (GenArt) has democratized the creation of visually appealing imagery. However, achieving genuine artistic impact - the kind that resonates with viewers on a deeper, more meaningful level - remains formidable as it requires a sophisticated aesthetic sensibility. This sensibility involves a multifaceted cognitive process extending beyond mere visual appeal, which is often overlooked by current computational methods. This paper pioneers an approach to capture this complex process by investigating how the reasoning capabilities of Multimodal LLMs (MLL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09012","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/2501.09012/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":"2501.09012","created_at":"2026-06-28T15:26:19.310491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09012v3","created_at":"2026-06-28T15:26:19.310491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09012","created_at":"2026-06-28T15:26:19.310491+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q7IDIH5AJTTP","created_at":"2026-06-28T15:26:19.310491+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q7IDIH5AJTTPWVDV","created_at":"2026-06-28T15:26:19.310491+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q7IDIH5A","created_at":"2026-06-28T15:26:19.310491+00:00"}],"events":[],"event_summary":{},"paper_claims":[{"claim_id":"c5dcec02-5345-4216-a504-8167aef888f9","handle":null,"display_name":"JIANG Ruixiang","verification":"orcid_verified","verification_note":"Auto-claimed from ORCID 0000-0001-8666-6767 at registration","role_label":null,"open_disputes":0}],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.12545","citing_title":"CROP: Expert-Aligned Image Cropping via Compositional Reasoning and Optimizing Preference","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05331","citing_title":"ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parameters","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q7IDIH5AJTTPWVDVGCSSBI3KYE","json":"https://pith.science/pith/Q7IDIH5AJTTPWVDVGCSSBI3KYE.json","graph_json":"https://pith.science/api/pith-number/Q7IDIH5AJTTPWVDVGCSSBI3KYE/graph.json","events_json":"https://pith.science/api/pith-number/Q7IDIH5AJTTPWVDVGCSSBI3KYE/events.json","paper":"https://pith.science/paper/Q7IDIH5A"},"agent_actions":{"view_html":"https://pith.science/pith/Q7IDIH5AJTTPWVDVGCSSBI3KYE","download_json":"https://pith.science/pith/Q7IDIH5AJTTPWVDVGCSSBI3KYE.json","view_paper":"https://pith.science/paper/Q7IDIH5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09012&json=true","fetch_graph":"https://pith.science/api/pith-number/Q7IDIH5AJTTPWVDVGCSSBI3KYE/graph.json","fetch_events":"https://pith.science/api/pith-number/Q7IDIH5AJTTPWVDVGCSSBI3KYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q7IDIH5AJTTPWVDVGCSSBI3KYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q7IDIH5AJTTPWVDVGCSSBI3KYE/action/storage_attestation","attest_author":"https://pith.science/pith/Q7IDIH5AJTTPWVDVGCSSBI3KYE/action/author_attestation","sign_citation":"https://pith.science/pith/Q7IDIH5AJTTPWVDVGCSSBI3KYE/action/citation_signature","submit_replication":"https://pith.science/pith/Q7IDIH5AJTTPWVDVGCSSBI3KYE/action/replication_record"}},"created_at":"2026-06-28T15:26:19.310491+00:00","updated_at":"2026-06-28T15:26:19.310491+00:00"}