{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6EUX32BOWJDIXM77UPQXAKHUAC","short_pith_number":"pith:6EUX32BO","schema_version":"1.0","canonical_sha256":"f1297de82eb2468bb3ffa3e17028f400a7f552f4331aad3e1c1b0d72a963e029","source":{"kind":"arxiv","id":"2307.15640","version":2},"attestation_state":"computed","paper":{"title":"CLIP Brings Better Features to Visual Aesthetics Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Jinjin Xu, Liwu Xu, Xilu Wang, Yaqian Li, Yijie Huang, Yuzhe Yang","submitted_at":"2023-07-28T16:00:21Z","abstract_excerpt":"Image Aesthetics Assessment (IAA) is a challenging task due to its subjective nature and expensive manual annotations. Recent large-scale vision-language models, such as Contrastive Language-Image Pre-training (CLIP), have shown their promising representation capability for various downstream tasks. However, the application of CLIP to resource-constrained and low-data IAA tasks remains limited. While few attempts to leverage CLIP in IAA have mainly focused on carefully designed prompts, we extend beyond this by allowing models from different domains and with different model sizes to acquire kn"},"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":"2307.15640","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-28T16:00:21Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"bf64278c55f34a2b00448a17ca6ff99466d76768671f16ea008a0e4629faac8e","abstract_canon_sha256":"1c7eacff6bf383526cfad9279d47de006da1acc4391ce9ffb0280c8ccb7a26c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:09.738551Z","signature_b64":"ymxoWDfv9tc2Z5AIfsNevYShRpianJbYS5KqHizTM6dNVmxGBvVTVY3MH64E2vVDeGxMuhS0lk4LQuXWT6juBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1297de82eb2468bb3ffa3e17028f400a7f552f4331aad3e1c1b0d72a963e029","last_reissued_at":"2026-07-05T11:47:09.738027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:09.738027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP Brings Better Features to Visual Aesthetics Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Jinjin Xu, Liwu Xu, Xilu Wang, Yaqian Li, Yijie Huang, Yuzhe Yang","submitted_at":"2023-07-28T16:00:21Z","abstract_excerpt":"Image Aesthetics Assessment (IAA) is a challenging task due to its subjective nature and expensive manual annotations. Recent large-scale vision-language models, such as Contrastive Language-Image Pre-training (CLIP), have shown their promising representation capability for various downstream tasks. However, the application of CLIP to resource-constrained and low-data IAA tasks remains limited. While few attempts to leverage CLIP in IAA have mainly focused on carefully designed prompts, we extend beyond this by allowing models from different domains and with different model sizes to acquire kn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15640","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/2307.15640/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":"2307.15640","created_at":"2026-07-05T11:47:09.738089+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.15640v2","created_at":"2026-07-05T11:47:09.738089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15640","created_at":"2026-07-05T11:47:09.738089+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EUX32BOWJDI","created_at":"2026-07-05T11:47:09.738089+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EUX32BOWJDIXM77","created_at":"2026-07-05T11:47:09.738089+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EUX32BO","created_at":"2026-07-05T11:47:09.738089+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03683","citing_title":"On the rankability of visual embeddings","ref_index":62,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6EUX32BOWJDIXM77UPQXAKHUAC","json":"https://pith.science/pith/6EUX32BOWJDIXM77UPQXAKHUAC.json","graph_json":"https://pith.science/api/pith-number/6EUX32BOWJDIXM77UPQXAKHUAC/graph.json","events_json":"https://pith.science/api/pith-number/6EUX32BOWJDIXM77UPQXAKHUAC/events.json","paper":"https://pith.science/paper/6EUX32BO"},"agent_actions":{"view_html":"https://pith.science/pith/6EUX32BOWJDIXM77UPQXAKHUAC","download_json":"https://pith.science/pith/6EUX32BOWJDIXM77UPQXAKHUAC.json","view_paper":"https://pith.science/paper/6EUX32BO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.15640&json=true","fetch_graph":"https://pith.science/api/pith-number/6EUX32BOWJDIXM77UPQXAKHUAC/graph.json","fetch_events":"https://pith.science/api/pith-number/6EUX32BOWJDIXM77UPQXAKHUAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EUX32BOWJDIXM77UPQXAKHUAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EUX32BOWJDIXM77UPQXAKHUAC/action/storage_attestation","attest_author":"https://pith.science/pith/6EUX32BOWJDIXM77UPQXAKHUAC/action/author_attestation","sign_citation":"https://pith.science/pith/6EUX32BOWJDIXM77UPQXAKHUAC/action/citation_signature","submit_replication":"https://pith.science/pith/6EUX32BOWJDIXM77UPQXAKHUAC/action/replication_record"}},"created_at":"2026-07-05T11:47:09.738089+00:00","updated_at":"2026-07-05T11:47:09.738089+00:00"}