{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TUGJQA3ILEARTXS3FF5EGONQFF","short_pith_number":"pith:TUGJQA3I","canonical_record":{"source":{"id":"2204.03162","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T02:17:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"42db550c621101dec0af33adaedd8745bf8b0133d58240dc122824b6a0941b7c","abstract_canon_sha256":"8802403c62e87647ee3c48887296a29219a9efab635f16ddd5f2abcacb270640"},"schema_version":"1.0"},"canonical_sha256":"9d0c980368590119de5b297a4339b02961fdea66a2471422f42f3a3808994aa0","source":{"kind":"arxiv","id":"2204.03162","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03162","created_at":"2026-07-05T04:17:04Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03162v2","created_at":"2026-07-05T04:17:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03162","created_at":"2026-07-05T04:17:04Z"},{"alias_kind":"pith_short_12","alias_value":"TUGJQA3ILEAR","created_at":"2026-07-05T04:17:04Z"},{"alias_kind":"pith_short_16","alias_value":"TUGJQA3ILEARTXS3","created_at":"2026-07-05T04:17:04Z"},{"alias_kind":"pith_short_8","alias_value":"TUGJQA3I","created_at":"2026-07-05T04:17:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TUGJQA3ILEARTXS3FF5EGONQFF","target":"record","payload":{"canonical_record":{"source":{"id":"2204.03162","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T02:17:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"42db550c621101dec0af33adaedd8745bf8b0133d58240dc122824b6a0941b7c","abstract_canon_sha256":"8802403c62e87647ee3c48887296a29219a9efab635f16ddd5f2abcacb270640"},"schema_version":"1.0"},"canonical_sha256":"9d0c980368590119de5b297a4339b02961fdea66a2471422f42f3a3808994aa0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:04.464895Z","signature_b64":"7DKmbEPJCupmzKXKmSoGAfFx2N3qfeEr5p5uJy+ExwDPeYX1a0szlR2dzLXeMc+ePvJaP33hVqcaZ6skrTwNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d0c980368590119de5b297a4339b02961fdea66a2471422f42f3a3808994aa0","last_reissued_at":"2026-07-05T04:17:04.464374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:04.464374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.03162","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:17:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lJ53NacCxjxK1vsw+CRwmY6sDrhzHGa+R1mdKhiBc6YinaAF8oGrb5GLqqKuHzYi4TAW70xyIfCzlsM0q6lRDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:05:21.719233Z"},"content_sha256":"2036665f0a38f911327005ad46c56025b29f991f186f3fbbc8d97509153589bb","schema_version":"1.0","event_id":"sha256:2036665f0a38f911327005ad46c56025b29f991f186f3fbbc8d97509153589bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TUGJQA3ILEARTXS3FF5EGONQFF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Adina Williams, Amanpreet Singh, Candace Ross, Douwe Kiela, Max Bartolo, Ryan Jiang, Tristan Thrush","submitted_at":"2022-04-07T02:17:05Z","abstract_excerpt":"We present a novel task and dataset for evaluating the ability of vision and language models to conduct visio-linguistic compositional reasoning, which we call Winoground. Given two images and two captions, the goal is to match them correctly - but crucially, both captions contain a completely identical set of words, only in a different order. The dataset was carefully hand-curated by expert annotators and is labeled with a rich set of fine-grained tags to assist in analyzing model performance. We probe a diverse range of state-of-the-art vision and language models and find that, surprisingly,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03162","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/2204.03162/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":"2026-07-05T04:17:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n8tZxE40lW5+AFouoocLLACOnLvWP65xk/R0v/e4AJPspLStMB3ufY/T+ckfIy4pe/Ml1tCptUeuqJfMEYLMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:05:21.719749Z"},"content_sha256":"34ede5dd5f9c3bdf55f207b5e92ea34f12c329c4d86c589737c850b874c1c098","schema_version":"1.0","event_id":"sha256:34ede5dd5f9c3bdf55f207b5e92ea34f12c329c4d86c589737c850b874c1c098"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUGJQA3ILEARTXS3FF5EGONQFF/bundle.json","state_url":"https://pith.science/pith/TUGJQA3ILEARTXS3FF5EGONQFF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUGJQA3ILEARTXS3FF5EGONQFF/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":"2026-08-07T17:05:21Z","links":{"resolver":"https://pith.science/pith/TUGJQA3ILEARTXS3FF5EGONQFF","bundle":"https://pith.science/pith/TUGJQA3ILEARTXS3FF5EGONQFF/bundle.json","state":"https://pith.science/pith/TUGJQA3ILEARTXS3FF5EGONQFF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUGJQA3ILEARTXS3FF5EGONQFF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TUGJQA3ILEARTXS3FF5EGONQFF","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":"8802403c62e87647ee3c48887296a29219a9efab635f16ddd5f2abcacb270640","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T02:17:05Z","title_canon_sha256":"42db550c621101dec0af33adaedd8745bf8b0133d58240dc122824b6a0941b7c"},"schema_version":"1.0","source":{"id":"2204.03162","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03162","created_at":"2026-07-05T04:17:04Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03162v2","created_at":"2026-07-05T04:17:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03162","created_at":"2026-07-05T04:17:04Z"},{"alias_kind":"pith_short_12","alias_value":"TUGJQA3ILEAR","created_at":"2026-07-05T04:17:04Z"},{"alias_kind":"pith_short_16","alias_value":"TUGJQA3ILEARTXS3","created_at":"2026-07-05T04:17:04Z"},{"alias_kind":"pith_short_8","alias_value":"TUGJQA3I","created_at":"2026-07-05T04:17:04Z"}],"graph_snapshots":[{"event_id":"sha256:34ede5dd5f9c3bdf55f207b5e92ea34f12c329c4d86c589737c850b874c1c098","target":"graph","created_at":"2026-07-05T04:17:04Z","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/2204.03162/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel task and dataset for evaluating the ability of vision and language models to conduct visio-linguistic compositional reasoning, which we call Winoground. Given two images and two captions, the goal is to match them correctly - but crucially, both captions contain a completely identical set of words, only in a different order. The dataset was carefully hand-curated by expert annotators and is labeled with a rich set of fine-grained tags to assist in analyzing model performance. We probe a diverse range of state-of-the-art vision and language models and find that, surprisingly,","authors_text":"Adina Williams, Amanpreet Singh, Candace Ross, Douwe Kiela, Max Bartolo, Ryan Jiang, Tristan Thrush","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T02:17:05Z","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03162","kind":"arxiv","version":2},"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":"sha256:2036665f0a38f911327005ad46c56025b29f991f186f3fbbc8d97509153589bb","target":"record","created_at":"2026-07-05T04:17:04Z","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":"8802403c62e87647ee3c48887296a29219a9efab635f16ddd5f2abcacb270640","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T02:17:05Z","title_canon_sha256":"42db550c621101dec0af33adaedd8745bf8b0133d58240dc122824b6a0941b7c"},"schema_version":"1.0","source":{"id":"2204.03162","kind":"arxiv","version":2}},"canonical_sha256":"9d0c980368590119de5b297a4339b02961fdea66a2471422f42f3a3808994aa0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d0c980368590119de5b297a4339b02961fdea66a2471422f42f3a3808994aa0","first_computed_at":"2026-07-05T04:17:04.464374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:04.464374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7DKmbEPJCupmzKXKmSoGAfFx2N3qfeEr5p5uJy+ExwDPeYX1a0szlR2dzLXeMc+ePvJaP33hVqcaZ6skrTwNBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:04.464895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.03162","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2036665f0a38f911327005ad46c56025b29f991f186f3fbbc8d97509153589bb","sha256:34ede5dd5f9c3bdf55f207b5e92ea34f12c329c4d86c589737c850b874c1c098"],"state_sha256":"175b4613c0bad0740359365e0e65a02a0901ff81c1ce555bea04a7be7ba1cf86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HqGTiHXaCybX/k6xm8nCfrJxUPoRS3zpx6DuGi7scZ2BmlVRlAwEml5O+RfMH7ZtwFO79yZz6Ym4a+Sxs62+Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:05:21.725280Z","bundle_sha256":"d6943c002f818b58afb35582fbf9544e3fcb865443ed52f8025790c75579a9ff"}}