{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ROFCW5GECIPCIQODEFDWD4BZG4","short_pith_number":"pith:ROFCW5GE","schema_version":"1.0","canonical_sha256":"8b8a2b74c4121e2441c3214761f0393708d6404fb2e4c1241c085b28006bf7f3","source":{"kind":"arxiv","id":"2201.10963","version":2},"attestation_state":"computed","paper":{"title":"Learning to Compose Diversified Prompts for Image Emotion Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Ge Shi, Lehao Xing, Lifang Wu, Meng Jian, Sinuo Deng, Ye Xiang","submitted_at":"2022-01-26T14:31:55Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) represents the latest incarnation of pre-trained vision-language models. Although CLIP has recently shown its superior power on a wide range of downstream vision-language tasks like Visual Question Answering, it is still underexplored for Image Emotion Classification (IEC). Adapting CLIP to the IEC task has three significant challenges, tremendous training objective gap between pretraining and IEC, shared suboptimal and invariant prompts for all instances. In this paper, we propose a general framework that shows how CLIP can be effectively applied"},"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":"2201.10963","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-26T14:31:55Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"d408ace60d6c1119436dcb95ab25c37d06683ba40fb8e5602cb1e415bad33893","abstract_canon_sha256":"959e07d1c4e515a49cf8d962cb5dbf413520b68e364b406690e348f023b67d33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:10.972625Z","signature_b64":"eLcC2uKQ8FAZwS9ebz8LMteLTZpma6Ko0PYd2/PFYC+6Ekm9anWjHt66PB6cb6ZCAiaLdxy//xpmx/DKsMIFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b8a2b74c4121e2441c3214761f0393708d6404fb2e4c1241c085b28006bf7f3","last_reissued_at":"2026-07-05T04:27:10.972046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:10.972046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Compose Diversified Prompts for Image Emotion Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Ge Shi, Lehao Xing, Lifang Wu, Meng Jian, Sinuo Deng, Ye Xiang","submitted_at":"2022-01-26T14:31:55Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) represents the latest incarnation of pre-trained vision-language models. Although CLIP has recently shown its superior power on a wide range of downstream vision-language tasks like Visual Question Answering, it is still underexplored for Image Emotion Classification (IEC). Adapting CLIP to the IEC task has three significant challenges, tremendous training objective gap between pretraining and IEC, shared suboptimal and invariant prompts for all instances. In this paper, we propose a general framework that shows how CLIP can be effectively applied"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10963","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/2201.10963/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":"2201.10963","created_at":"2026-07-05T04:27:10.972115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.10963v2","created_at":"2026-07-05T04:27:10.972115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10963","created_at":"2026-07-05T04:27:10.972115+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROFCW5GECIPC","created_at":"2026-07-05T04:27:10.972115+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROFCW5GECIPCIQOD","created_at":"2026-07-05T04:27:10.972115+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROFCW5GE","created_at":"2026-07-05T04:27:10.972115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10448","citing_title":"Unlocking Visual Secrets: Inverting Features with Diffusion Priors for Image Reconstruction","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROFCW5GECIPCIQODEFDWD4BZG4","json":"https://pith.science/pith/ROFCW5GECIPCIQODEFDWD4BZG4.json","graph_json":"https://pith.science/api/pith-number/ROFCW5GECIPCIQODEFDWD4BZG4/graph.json","events_json":"https://pith.science/api/pith-number/ROFCW5GECIPCIQODEFDWD4BZG4/events.json","paper":"https://pith.science/paper/ROFCW5GE"},"agent_actions":{"view_html":"https://pith.science/pith/ROFCW5GECIPCIQODEFDWD4BZG4","download_json":"https://pith.science/pith/ROFCW5GECIPCIQODEFDWD4BZG4.json","view_paper":"https://pith.science/paper/ROFCW5GE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.10963&json=true","fetch_graph":"https://pith.science/api/pith-number/ROFCW5GECIPCIQODEFDWD4BZG4/graph.json","fetch_events":"https://pith.science/api/pith-number/ROFCW5GECIPCIQODEFDWD4BZG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROFCW5GECIPCIQODEFDWD4BZG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROFCW5GECIPCIQODEFDWD4BZG4/action/storage_attestation","attest_author":"https://pith.science/pith/ROFCW5GECIPCIQODEFDWD4BZG4/action/author_attestation","sign_citation":"https://pith.science/pith/ROFCW5GECIPCIQODEFDWD4BZG4/action/citation_signature","submit_replication":"https://pith.science/pith/ROFCW5GECIPCIQODEFDWD4BZG4/action/replication_record"}},"created_at":"2026-07-05T04:27:10.972115+00:00","updated_at":"2026-07-05T04:27:10.972115+00:00"}