{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XSI5ZM54WH34JVWWVJZLVFJJJS","short_pith_number":"pith:XSI5ZM54","schema_version":"1.0","canonical_sha256":"bc91dcb3bcb1f7c4d6d6aa72ba95294ca4d8fadfe4429234234fb4822c594d18","source":{"kind":"arxiv","id":"2305.19402","version":2},"attestation_state":"computed","paper":{"title":"Contextual Vision Transformers for Robust Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Theofanis Karaletsos, Yujia Bao","submitted_at":"2023-05-30T20:31:26Z","abstract_excerpt":"We introduce Contextual Vision Transformers (ContextViT), a method designed to generate robust image representations for datasets experiencing shifts in latent factors across various groups. Derived from the concept of in-context learning, ContextViT incorporates an additional context token to encapsulate group-specific information. This integration allows the model to adjust the image representation in accordance with the group-specific context. Specifically, for a given input image, ContextViT maps images with identical group membership into this context token, which is appended to the input"},"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":"2305.19402","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-30T20:31:26Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"3c16ebe5b36a7f276386bac26cefe408ec31a411e12730f594301e00971fe5cf","abstract_canon_sha256":"acd975a4b632e0bb7b1c9e432c213c1edcdc2ebb81b54922c1796b7b9aabe28e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:23.648491Z","signature_b64":"V/3rqiX5UTwu/Cu3y3P+X3/fjK544vaYcVf8tU+UlbH1cvwt3OWWt+kWWApBHw4YjBi8YiNeJRZqRrlSiWZ4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc91dcb3bcb1f7c4d6d6aa72ba95294ca4d8fadfe4429234234fb4822c594d18","last_reissued_at":"2026-07-05T06:55:23.647986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:23.647986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextual Vision Transformers for Robust Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Theofanis Karaletsos, Yujia Bao","submitted_at":"2023-05-30T20:31:26Z","abstract_excerpt":"We introduce Contextual Vision Transformers (ContextViT), a method designed to generate robust image representations for datasets experiencing shifts in latent factors across various groups. Derived from the concept of in-context learning, ContextViT incorporates an additional context token to encapsulate group-specific information. This integration allows the model to adjust the image representation in accordance with the group-specific context. Specifically, for a given input image, ContextViT maps images with identical group membership into this context token, which is appended to the input"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19402","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/2305.19402/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":"2305.19402","created_at":"2026-07-05T06:55:23.648045+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.19402v2","created_at":"2026-07-05T06:55:23.648045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19402","created_at":"2026-07-05T06:55:23.648045+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSI5ZM54WH34","created_at":"2026-07-05T06:55:23.648045+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSI5ZM54WH34JVWW","created_at":"2026-07-05T06:55:23.648045+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSI5ZM54","created_at":"2026-07-05T06:55:23.648045+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/XSI5ZM54WH34JVWWVJZLVFJJJS","json":"https://pith.science/pith/XSI5ZM54WH34JVWWVJZLVFJJJS.json","graph_json":"https://pith.science/api/pith-number/XSI5ZM54WH34JVWWVJZLVFJJJS/graph.json","events_json":"https://pith.science/api/pith-number/XSI5ZM54WH34JVWWVJZLVFJJJS/events.json","paper":"https://pith.science/paper/XSI5ZM54"},"agent_actions":{"view_html":"https://pith.science/pith/XSI5ZM54WH34JVWWVJZLVFJJJS","download_json":"https://pith.science/pith/XSI5ZM54WH34JVWWVJZLVFJJJS.json","view_paper":"https://pith.science/paper/XSI5ZM54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.19402&json=true","fetch_graph":"https://pith.science/api/pith-number/XSI5ZM54WH34JVWWVJZLVFJJJS/graph.json","fetch_events":"https://pith.science/api/pith-number/XSI5ZM54WH34JVWWVJZLVFJJJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSI5ZM54WH34JVWWVJZLVFJJJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSI5ZM54WH34JVWWVJZLVFJJJS/action/storage_attestation","attest_author":"https://pith.science/pith/XSI5ZM54WH34JVWWVJZLVFJJJS/action/author_attestation","sign_citation":"https://pith.science/pith/XSI5ZM54WH34JVWWVJZLVFJJJS/action/citation_signature","submit_replication":"https://pith.science/pith/XSI5ZM54WH34JVWWVJZLVFJJJS/action/replication_record"}},"created_at":"2026-07-05T06:55:23.648045+00:00","updated_at":"2026-07-05T06:55:23.648045+00:00"}