{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KGTJDBCW6JID3MMLLWYYEUUQZE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b64262ec19a3d1e56355bd1e63c6005cedab8b8d2faaef4dfbb1550840fef00c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T09:56:20Z","title_canon_sha256":"be4b582b280c7ad621005443c5df33a10803526ec875cfbd589e0e22825009cb"},"schema_version":"1.0","source":{"id":"2404.09624","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09624","created_at":"2026-07-05T08:47:51Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09624v3","created_at":"2026-07-05T08:47:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09624","created_at":"2026-07-05T08:47:51Z"},{"alias_kind":"pith_short_12","alias_value":"KGTJDBCW6JID","created_at":"2026-07-05T08:47:51Z"},{"alias_kind":"pith_short_16","alias_value":"KGTJDBCW6JID3MML","created_at":"2026-07-05T08:47:51Z"},{"alias_kind":"pith_short_8","alias_value":"KGTJDBCW","created_at":"2026-07-05T08:47:51Z"}],"graph_snapshots":[{"event_id":"sha256:d1f9c9643592482f9f928eb10334805bf679adeed00836770c295b5e414edd21","target":"graph","created_at":"2026-07-05T08:47:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.09624/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guangming Shi, Leida Li, Pengfei Chen, Quan Yuan, Weisi Lin, Xiangfei Sheng, Yipo Huang, Zhichao Duan, Zhichao Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T09:56:20Z","title":"AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09624","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8985c7a793461c6ccbeda0ba919b390eebae2c14d7eaeba899842de6f49bfdcd","target":"record","created_at":"2026-07-05T08:47:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b64262ec19a3d1e56355bd1e63c6005cedab8b8d2faaef4dfbb1550840fef00c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T09:56:20Z","title_canon_sha256":"be4b582b280c7ad621005443c5df33a10803526ec875cfbd589e0e22825009cb"},"schema_version":"1.0","source":{"id":"2404.09624","kind":"arxiv","version":3}},"canonical_sha256":"51a6918456f2503db18b5db1825290c9232c6c669781eb566859826abc3ba73a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51a6918456f2503db18b5db1825290c9232c6c669781eb566859826abc3ba73a","first_computed_at":"2026-07-05T08:47:51.437196Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:47:51.437196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o8HweiWItl5/ZbOESlYaoSf7tUD8r3PNISghzkZCBlTD7Rg8ERlh0yX4W95vL+lWU1UTurvFDbZSKQ37jFJtCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:47:51.437614Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.09624","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8985c7a793461c6ccbeda0ba919b390eebae2c14d7eaeba899842de6f49bfdcd","sha256:d1f9c9643592482f9f928eb10334805bf679adeed00836770c295b5e414edd21"],"state_sha256":"41d9273f94b43b96718b4ab4cb8dcf3119e6270faae9ba9dd4e264a599a4597f"}