{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R6CQDXLSIJQI3MNBSFXMLBVEB7","short_pith_number":"pith:R6CQDXLS","schema_version":"1.0","canonical_sha256":"8f8501dd7242608db1a1916ec586a40ffd38cdb80ff7e7c883e8901b11b24c91","source":{"kind":"arxiv","id":"2307.07742","version":2},"attestation_state":"computed","paper":{"title":"SINC: Self-Supervised In-Context Learning for Vision-Language Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bei Liu, Cheng Yu Yeo, Hong-Han Shuai, Jianlong Fu, Yi-Syuan Chen, Yun-Zhu Song","submitted_at":"2023-07-15T08:33:08Z","abstract_excerpt":"Large Pre-trained Transformers exhibit an intriguing capacity for in-context learning. Without gradient updates, these models can rapidly construct new predictors from demonstrations presented in the inputs. Recent works promote this ability in the vision-language domain by incorporating visual information into large language models that can already make in-context predictions. However, these methods could inherit issues in the language domain, such as template sensitivity and hallucination. Also, the scale of these language models raises a significant demand for computations, making learning "},"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":"2307.07742","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-15T08:33:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed3ac69eee3b4bc24058ea3f352f5f89de24c8faf84204f61bd413e4c850f446","abstract_canon_sha256":"4facede646557ffb604702ae1930be5b67ffb223b30b086793573a2fc63c2ffa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:44.422510Z","signature_b64":"cpDhV9AzhhcC0wYP/oGz2+SUh2B1tHXBMLq2AZ3pFAzBufcwmNsWDmLtoj/GPKXDq24L68jhPXRPfhxydkDVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f8501dd7242608db1a1916ec586a40ffd38cdb80ff7e7c883e8901b11b24c91","last_reissued_at":"2026-07-05T06:42:44.422042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:44.422042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SINC: Self-Supervised In-Context Learning for Vision-Language Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bei Liu, Cheng Yu Yeo, Hong-Han Shuai, Jianlong Fu, Yi-Syuan Chen, Yun-Zhu Song","submitted_at":"2023-07-15T08:33:08Z","abstract_excerpt":"Large Pre-trained Transformers exhibit an intriguing capacity for in-context learning. Without gradient updates, these models can rapidly construct new predictors from demonstrations presented in the inputs. Recent works promote this ability in the vision-language domain by incorporating visual information into large language models that can already make in-context predictions. However, these methods could inherit issues in the language domain, such as template sensitivity and hallucination. Also, the scale of these language models raises a significant demand for computations, making learning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07742","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/2307.07742/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":"2307.07742","created_at":"2026-07-05T06:42:44.422096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.07742v2","created_at":"2026-07-05T06:42:44.422096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07742","created_at":"2026-07-05T06:42:44.422096+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6CQDXLSIJQI","created_at":"2026-07-05T06:42:44.422096+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6CQDXLSIJQI3MNB","created_at":"2026-07-05T06:42:44.422096+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6CQDXLS","created_at":"2026-07-05T06:42:44.422096+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R6CQDXLSIJQI3MNBSFXMLBVEB7","json":"https://pith.science/pith/R6CQDXLSIJQI3MNBSFXMLBVEB7.json","graph_json":"https://pith.science/api/pith-number/R6CQDXLSIJQI3MNBSFXMLBVEB7/graph.json","events_json":"https://pith.science/api/pith-number/R6CQDXLSIJQI3MNBSFXMLBVEB7/events.json","paper":"https://pith.science/paper/R6CQDXLS"},"agent_actions":{"view_html":"https://pith.science/pith/R6CQDXLSIJQI3MNBSFXMLBVEB7","download_json":"https://pith.science/pith/R6CQDXLSIJQI3MNBSFXMLBVEB7.json","view_paper":"https://pith.science/paper/R6CQDXLS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.07742&json=true","fetch_graph":"https://pith.science/api/pith-number/R6CQDXLSIJQI3MNBSFXMLBVEB7/graph.json","fetch_events":"https://pith.science/api/pith-number/R6CQDXLSIJQI3MNBSFXMLBVEB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6CQDXLSIJQI3MNBSFXMLBVEB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6CQDXLSIJQI3MNBSFXMLBVEB7/action/storage_attestation","attest_author":"https://pith.science/pith/R6CQDXLSIJQI3MNBSFXMLBVEB7/action/author_attestation","sign_citation":"https://pith.science/pith/R6CQDXLSIJQI3MNBSFXMLBVEB7/action/citation_signature","submit_replication":"https://pith.science/pith/R6CQDXLSIJQI3MNBSFXMLBVEB7/action/replication_record"}},"created_at":"2026-07-05T06:42:44.422096+00:00","updated_at":"2026-07-05T06:42:44.422096+00:00"}