{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KLTCSYDM5DX3NPCDASAHRLDOGE","short_pith_number":"pith:KLTCSYDM","schema_version":"1.0","canonical_sha256":"52e629606ce8efb6bc43048078ac6e31194048cbb2e141ad313cadb91264a27c","source":{"kind":"arxiv","id":"2108.08688","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Language-Image Pre-training for the Italian Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Federico Bianchi, Gabriele Sarti, Giuseppe Attanasio, Raphael Pisoni, Silvia Terragni, Sri Lakshmi","submitted_at":"2021-08-19T13:53:47Z","abstract_excerpt":"CLIP (Contrastive Language-Image Pre-training) is a very recent multi-modal model that jointly learns representations of images and texts. The model is trained on a massive amount of English data and shows impressive performance on zero-shot classification tasks. Training the same model on a different language is not trivial, since data in other languages might be not enough and the model needs high-quality translations of the texts to guarantee a good performance. In this paper, we present the first CLIP model for the Italian Language (CLIP-Italian), trained on more than 1.4 million image-tex"},"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":"2108.08688","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-19T13:53:47Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"bc9eecfaab19d89ea253b0e15ba03aa46964c00a002d095ab02f2769ea441ee0","abstract_canon_sha256":"07e779c475db3b3d94adad8de12182820d391cd43a4fa98311bb722821e32fef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:12.529191Z","signature_b64":"MS2KXvuK0EybAHlApZcRQp20KRO/YbBHeHE74YHtmw9jTvRKP3GG8SIe3TyD8BXk3VbpeoGqV/dKJrQxMMRqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52e629606ce8efb6bc43048078ac6e31194048cbb2e141ad313cadb91264a27c","last_reissued_at":"2026-07-05T03:07:12.528782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:12.528782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Language-Image Pre-training for the Italian Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Federico Bianchi, Gabriele Sarti, Giuseppe Attanasio, Raphael Pisoni, Silvia Terragni, Sri Lakshmi","submitted_at":"2021-08-19T13:53:47Z","abstract_excerpt":"CLIP (Contrastive Language-Image Pre-training) is a very recent multi-modal model that jointly learns representations of images and texts. The model is trained on a massive amount of English data and shows impressive performance on zero-shot classification tasks. Training the same model on a different language is not trivial, since data in other languages might be not enough and the model needs high-quality translations of the texts to guarantee a good performance. In this paper, we present the first CLIP model for the Italian Language (CLIP-Italian), trained on more than 1.4 million image-tex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08688","kind":"arxiv","version":1},"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/2108.08688/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":"2108.08688","created_at":"2026-07-05T03:07:12.528838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.08688v1","created_at":"2026-07-05T03:07:12.528838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08688","created_at":"2026-07-05T03:07:12.528838+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLTCSYDM5DX3","created_at":"2026-07-05T03:07:12.528838+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLTCSYDM5DX3NPCD","created_at":"2026-07-05T03:07:12.528838+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLTCSYDM","created_at":"2026-07-05T03:07:12.528838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.14238","citing_title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KLTCSYDM5DX3NPCDASAHRLDOGE","json":"https://pith.science/pith/KLTCSYDM5DX3NPCDASAHRLDOGE.json","graph_json":"https://pith.science/api/pith-number/KLTCSYDM5DX3NPCDASAHRLDOGE/graph.json","events_json":"https://pith.science/api/pith-number/KLTCSYDM5DX3NPCDASAHRLDOGE/events.json","paper":"https://pith.science/paper/KLTCSYDM"},"agent_actions":{"view_html":"https://pith.science/pith/KLTCSYDM5DX3NPCDASAHRLDOGE","download_json":"https://pith.science/pith/KLTCSYDM5DX3NPCDASAHRLDOGE.json","view_paper":"https://pith.science/paper/KLTCSYDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.08688&json=true","fetch_graph":"https://pith.science/api/pith-number/KLTCSYDM5DX3NPCDASAHRLDOGE/graph.json","fetch_events":"https://pith.science/api/pith-number/KLTCSYDM5DX3NPCDASAHRLDOGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLTCSYDM5DX3NPCDASAHRLDOGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLTCSYDM5DX3NPCDASAHRLDOGE/action/storage_attestation","attest_author":"https://pith.science/pith/KLTCSYDM5DX3NPCDASAHRLDOGE/action/author_attestation","sign_citation":"https://pith.science/pith/KLTCSYDM5DX3NPCDASAHRLDOGE/action/citation_signature","submit_replication":"https://pith.science/pith/KLTCSYDM5DX3NPCDASAHRLDOGE/action/replication_record"}},"created_at":"2026-07-05T03:07:12.528838+00:00","updated_at":"2026-07-05T03:07:12.528838+00:00"}