{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:P7EM5H6M6DA6DNHYQ7WDEUGDVP","short_pith_number":"pith:P7EM5H6M","canonical_record":{"source":{"id":"2304.04399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T05:54:03Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"3e5719dcc3944b9efe684139ca71e06b9a21d7ec21b57367120c8915ef910e4a","abstract_canon_sha256":"1635a53222c5e9d012895387e98b62de71d17602cd9e987623586960cb2bd54b"},"schema_version":"1.0"},"canonical_sha256":"7fc8ce9fccf0c1e1b4f887ec3250c3abfe3504e73d28d3a2c5ddddf70166bdf1","source":{"kind":"arxiv","id":"2304.04399","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.04399","created_at":"2026-07-05T05:59:25Z"},{"alias_kind":"arxiv_version","alias_value":"2304.04399v1","created_at":"2026-07-05T05:59:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04399","created_at":"2026-07-05T05:59:25Z"},{"alias_kind":"pith_short_12","alias_value":"P7EM5H6M6DA6","created_at":"2026-07-05T05:59:25Z"},{"alias_kind":"pith_short_16","alias_value":"P7EM5H6M6DA6DNHY","created_at":"2026-07-05T05:59:25Z"},{"alias_kind":"pith_short_8","alias_value":"P7EM5H6M","created_at":"2026-07-05T05:59:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:P7EM5H6M6DA6DNHYQ7WDEUGDVP","target":"record","payload":{"canonical_record":{"source":{"id":"2304.04399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T05:54:03Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"3e5719dcc3944b9efe684139ca71e06b9a21d7ec21b57367120c8915ef910e4a","abstract_canon_sha256":"1635a53222c5e9d012895387e98b62de71d17602cd9e987623586960cb2bd54b"},"schema_version":"1.0"},"canonical_sha256":"7fc8ce9fccf0c1e1b4f887ec3250c3abfe3504e73d28d3a2c5ddddf70166bdf1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:25.806766Z","signature_b64":"ruY7ZH11tHr0FPm8FfEF5qJcoBQkw5Q8ST8Lps0Fdt8lY0gR8rdJQeMUmSrmJAhRHVuvoWvZdsMnUOQWYRafAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fc8ce9fccf0c1e1b4f887ec3250c3abfe3504e73d28d3a2c5ddddf70166bdf1","last_reissued_at":"2026-07-05T05:59:25.806356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:25.806356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.04399","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:59:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4A4rg1nwHsUB3CzHCtsHS6GbYTuWA2IY6hw9o96WTcHW/iQVozXuQw8yDvCgRwGDFT8c/hOSUGcyT1tFUBJ3Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:12:26.696063Z"},"content_sha256":"735f7b74fe2c29fbccce057fb5c3235e16e18e7672581067785e34df5dd5afaa","schema_version":"1.0","event_id":"sha256:735f7b74fe2c29fbccce057fb5c3235e16e18e7672581067785e34df5dd5afaa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:P7EM5H6M6DA6DNHYQ7WDEUGDVP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CAVL: Learning Contrastive and Adaptive Representations of Vision and Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Ihor Markevych, Jingfei Xia, Shentong Mo","submitted_at":"2023-04-10T05:54:03Z","abstract_excerpt":"Visual and linguistic pre-training aims to learn vision and language representations together, which can be transferred to visual-linguistic downstream tasks. However, there exists semantic confusion between language and vision during the pre-training stage. Moreover, current pre-trained models tend to take lots of computation resources for fine-tuning when transferred to downstream tasks. In this work, we present a simple but effective approach for learning Contrastive and Adaptive representations of Vision and Language, namely CAVL. Specifically, we introduce a pair-wise contrastive loss to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04399","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/2304.04399/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:59:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UaDRCtjvhcL67KpelSJz1GrKpisC4vmk4v5hqJKDsd34D5ecSUdxr0FyCQcJsaafzI7OApMRpMu9jzhPvA5fAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:12:26.696452Z"},"content_sha256":"bb877aaf3850c45e4eba7f63b36b517979e934af0255e85906fa98377c8b91a0","schema_version":"1.0","event_id":"sha256:bb877aaf3850c45e4eba7f63b36b517979e934af0255e85906fa98377c8b91a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P7EM5H6M6DA6DNHYQ7WDEUGDVP/bundle.json","state_url":"https://pith.science/pith/P7EM5H6M6DA6DNHYQ7WDEUGDVP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P7EM5H6M6DA6DNHYQ7WDEUGDVP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T11:12:26Z","links":{"resolver":"https://pith.science/pith/P7EM5H6M6DA6DNHYQ7WDEUGDVP","bundle":"https://pith.science/pith/P7EM5H6M6DA6DNHYQ7WDEUGDVP/bundle.json","state":"https://pith.science/pith/P7EM5H6M6DA6DNHYQ7WDEUGDVP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P7EM5H6M6DA6DNHYQ7WDEUGDVP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:P7EM5H6M6DA6DNHYQ7WDEUGDVP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1635a53222c5e9d012895387e98b62de71d17602cd9e987623586960cb2bd54b","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T05:54:03Z","title_canon_sha256":"3e5719dcc3944b9efe684139ca71e06b9a21d7ec21b57367120c8915ef910e4a"},"schema_version":"1.0","source":{"id":"2304.04399","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.04399","created_at":"2026-07-05T05:59:25Z"},{"alias_kind":"arxiv_version","alias_value":"2304.04399v1","created_at":"2026-07-05T05:59:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04399","created_at":"2026-07-05T05:59:25Z"},{"alias_kind":"pith_short_12","alias_value":"P7EM5H6M6DA6","created_at":"2026-07-05T05:59:25Z"},{"alias_kind":"pith_short_16","alias_value":"P7EM5H6M6DA6DNHY","created_at":"2026-07-05T05:59:25Z"},{"alias_kind":"pith_short_8","alias_value":"P7EM5H6M","created_at":"2026-07-05T05:59:25Z"}],"graph_snapshots":[{"event_id":"sha256:bb877aaf3850c45e4eba7f63b36b517979e934af0255e85906fa98377c8b91a0","target":"graph","created_at":"2026-07-05T05:59:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2304.04399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual and linguistic pre-training aims to learn vision and language representations together, which can be transferred to visual-linguistic downstream tasks. However, there exists semantic confusion between language and vision during the pre-training stage. Moreover, current pre-trained models tend to take lots of computation resources for fine-tuning when transferred to downstream tasks. In this work, we present a simple but effective approach for learning Contrastive and Adaptive representations of Vision and Language, namely CAVL. Specifically, we introduce a pair-wise contrastive loss to ","authors_text":"Ihor Markevych, Jingfei Xia, Shentong Mo","cross_cats":["cs.AI","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T05:54:03Z","title":"CAVL: Learning Contrastive and Adaptive Representations of Vision and Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04399","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:735f7b74fe2c29fbccce057fb5c3235e16e18e7672581067785e34df5dd5afaa","target":"record","created_at":"2026-07-05T05:59:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1635a53222c5e9d012895387e98b62de71d17602cd9e987623586960cb2bd54b","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T05:54:03Z","title_canon_sha256":"3e5719dcc3944b9efe684139ca71e06b9a21d7ec21b57367120c8915ef910e4a"},"schema_version":"1.0","source":{"id":"2304.04399","kind":"arxiv","version":1}},"canonical_sha256":"7fc8ce9fccf0c1e1b4f887ec3250c3abfe3504e73d28d3a2c5ddddf70166bdf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fc8ce9fccf0c1e1b4f887ec3250c3abfe3504e73d28d3a2c5ddddf70166bdf1","first_computed_at":"2026-07-05T05:59:25.806356Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:59:25.806356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ruY7ZH11tHr0FPm8FfEF5qJcoBQkw5Q8ST8Lps0Fdt8lY0gR8rdJQeMUmSrmJAhRHVuvoWvZdsMnUOQWYRafAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:59:25.806766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.04399","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:735f7b74fe2c29fbccce057fb5c3235e16e18e7672581067785e34df5dd5afaa","sha256:bb877aaf3850c45e4eba7f63b36b517979e934af0255e85906fa98377c8b91a0"],"state_sha256":"ebe725edccdc55d4994811695ef1ea331d010514a3ee562bdd17c637ec829da7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u57RkrPx7bmhsnYa9WNBAhey2KcOJ/CKpymoEfiCZ4xY88xCtCR62+Sn02oleBw8rVGB8iLlqCQxMKrZYrZADw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:12:26.698431Z","bundle_sha256":"3a1603448b8763668babd932a795bafa8b67621ec2fd67cdd243b2771025a69b"}}