{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KGTJDBCW6JID3MMLLWYYEUUQZE","short_pith_number":"pith:KGTJDBCW","schema_version":"1.0","canonical_sha256":"51a6918456f2503db18b5db1825290c9232c6c669781eb566859826abc3ba73a","source":{"kind":"arxiv","id":"2404.09624","version":3},"attestation_state":"computed","paper":{"title":"AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangming Shi, Leida Li, Pengfei Chen, Quan Yuan, Weisi Lin, Xiangfei Sheng, Yipo Huang, Zhichao Duan, Zhichao Yang","submitted_at":"2024-04-15T09:56:20Z","abstract_excerpt":"The highly abstract nature of image aesthetics perception (IAP) poses significant challenge for current multimodal large language models (MLLMs). The lack of human-annotated multi-modality aesthetic data further exacerbates this dilemma, resulting in MLLMs falling short of aesthetics perception capabilities. To address the above challenge, we first introduce a comprehensively annotated Aesthetic Multi-Modality Instruction Tuning (AesMMIT) dataset, which serves as the footstone for building multi-modality aesthetics foundation models. Specifically, to align MLLMs with human aesthetics perceptio"},"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":"2404.09624","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T09:56:20Z","cross_cats_sorted":[],"title_canon_sha256":"be4b582b280c7ad621005443c5df33a10803526ec875cfbd589e0e22825009cb","abstract_canon_sha256":"b64262ec19a3d1e56355bd1e63c6005cedab8b8d2faaef4dfbb1550840fef00c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:51.437614Z","signature_b64":"o8HweiWItl5/ZbOESlYaoSf7tUD8r3PNISghzkZCBlTD7Rg8ERlh0yX4W95vL+lWU1UTurvFDbZSKQ37jFJtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51a6918456f2503db18b5db1825290c9232c6c669781eb566859826abc3ba73a","last_reissued_at":"2026-07-05T08:47:51.437196Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:51.437196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangming Shi, Leida Li, Pengfei Chen, Quan Yuan, Weisi Lin, Xiangfei Sheng, Yipo Huang, Zhichao Duan, Zhichao Yang","submitted_at":"2024-04-15T09:56:20Z","abstract_excerpt":"The highly abstract nature of image aesthetics perception (IAP) poses significant challenge for current multimodal large language models (MLLMs). The lack of human-annotated multi-modality aesthetic data further exacerbates this dilemma, resulting in MLLMs falling short of aesthetics perception capabilities. To address the above challenge, we first introduce a comprehensively annotated Aesthetic Multi-Modality Instruction Tuning (AesMMIT) dataset, which serves as the footstone for building multi-modality aesthetics foundation models. Specifically, to align MLLMs with human aesthetics perceptio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09624","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/2404.09624/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":"2404.09624","created_at":"2026-07-05T08:47:51.437248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09624v3","created_at":"2026-07-05T08:47:51.437248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09624","created_at":"2026-07-05T08:47:51.437248+00:00"},{"alias_kind":"pith_short_12","alias_value":"KGTJDBCW6JID","created_at":"2026-07-05T08:47:51.437248+00:00"},{"alias_kind":"pith_short_16","alias_value":"KGTJDBCW6JID3MML","created_at":"2026-07-05T08:47:51.437248+00:00"},{"alias_kind":"pith_short_8","alias_value":"KGTJDBCW","created_at":"2026-07-05T08:47:51.437248+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14533","citing_title":"ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KGTJDBCW6JID3MMLLWYYEUUQZE","json":"https://pith.science/pith/KGTJDBCW6JID3MMLLWYYEUUQZE.json","graph_json":"https://pith.science/api/pith-number/KGTJDBCW6JID3MMLLWYYEUUQZE/graph.json","events_json":"https://pith.science/api/pith-number/KGTJDBCW6JID3MMLLWYYEUUQZE/events.json","paper":"https://pith.science/paper/KGTJDBCW"},"agent_actions":{"view_html":"https://pith.science/pith/KGTJDBCW6JID3MMLLWYYEUUQZE","download_json":"https://pith.science/pith/KGTJDBCW6JID3MMLLWYYEUUQZE.json","view_paper":"https://pith.science/paper/KGTJDBCW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09624&json=true","fetch_graph":"https://pith.science/api/pith-number/KGTJDBCW6JID3MMLLWYYEUUQZE/graph.json","fetch_events":"https://pith.science/api/pith-number/KGTJDBCW6JID3MMLLWYYEUUQZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KGTJDBCW6JID3MMLLWYYEUUQZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KGTJDBCW6JID3MMLLWYYEUUQZE/action/storage_attestation","attest_author":"https://pith.science/pith/KGTJDBCW6JID3MMLLWYYEUUQZE/action/author_attestation","sign_citation":"https://pith.science/pith/KGTJDBCW6JID3MMLLWYYEUUQZE/action/citation_signature","submit_replication":"https://pith.science/pith/KGTJDBCW6JID3MMLLWYYEUUQZE/action/replication_record"}},"created_at":"2026-07-05T08:47:51.437248+00:00","updated_at":"2026-07-05T08:47:51.437248+00:00"}