{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CIDSTTLMY7Q7LFKK6VJ7PABI24","short_pith_number":"pith:CIDSTTLM","canonical_record":{"source":{"id":"2211.00768","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-01T22:16:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"348acb51f6e8e1dc24d624f02b2bc75cd2c56b37854821526082c0cb7338055e","abstract_canon_sha256":"b04b1bd55faf902988372ab62657c7453cfafdad7b0523ef652f4e8900b731b0"},"schema_version":"1.0"},"canonical_sha256":"120729cd6cc7e1f5954af553f78028d73f355169defbbd1d01813d6781e0420f","source":{"kind":"arxiv","id":"2211.00768","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.00768","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"arxiv_version","alias_value":"2211.00768v4","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00768","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"pith_short_12","alias_value":"CIDSTTLMY7Q7","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"pith_short_16","alias_value":"CIDSTTLMY7Q7LFKK","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"pith_short_8","alias_value":"CIDSTTLM","created_at":"2026-07-05T05:22:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CIDSTTLMY7Q7LFKK6VJ7PABI24","target":"record","payload":{"canonical_record":{"source":{"id":"2211.00768","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-01T22:16:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"348acb51f6e8e1dc24d624f02b2bc75cd2c56b37854821526082c0cb7338055e","abstract_canon_sha256":"b04b1bd55faf902988372ab62657c7453cfafdad7b0523ef652f4e8900b731b0"},"schema_version":"1.0"},"canonical_sha256":"120729cd6cc7e1f5954af553f78028d73f355169defbbd1d01813d6781e0420f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:12.078082Z","signature_b64":"hFgjYE/XJ77G5tdrqzYxeIr72IexkdmK0Ot5/oiOdeulbmHuuGxze7tZ8RAN7GBSjdsRRBD7G6tslL5j+QlkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"120729cd6cc7e1f5954af553f78028d73f355169defbbd1d01813d6781e0420f","last_reissued_at":"2026-07-05T05:22:12.077627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:12.077627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.00768","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:22:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v7PRoSakMqC9+W/TX5BfOMMyj0a6swYdVzW9FMasYrGMBellKUDq3POrNP9qbFba/EdUYdnB2GpZdJlOP7jmCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:40:57.446580Z"},"content_sha256":"3cc010e67d90d45c2af09612fecfa2502a9bc8fc71eb25854d6d261deb3b406b","schema_version":"1.0","event_id":"sha256:3cc010e67d90d45c2af09612fecfa2502a9bc8fc71eb25854d6d261deb3b406b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CIDSTTLMY7Q7LFKK6VJ7PABI24","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Anuj Diwan, David Harwath, Eunsol Choi, Kyle Mahowald, Layne Berry","submitted_at":"2022-11-01T22:16:58Z","abstract_excerpt":"Recent visuolinguistic pre-trained models show promising progress on various end tasks such as image retrieval and video captioning. Yet, they fail miserably on the recently proposed Winoground dataset, which challenges models to match paired images and English captions, with items constructed to overlap lexically but differ in meaning (e.g., \"there is a mug in some grass\" vs. \"there is some grass in a mug\"). By annotating the dataset using new fine-grained tags, we show that solving the Winoground task requires not just compositional language understanding, but a host of other abilities like "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00768","kind":"arxiv","version":4},"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/2211.00768/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":"2026-07-05T05:22:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GmDOk2RTBgwtOo9yMyOEqtbFYKHSbp+CFeHLg8hAtbVZbdWGawMRLDIzbI1qtSB9HvvoIukHjpBgayHP9+JyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:40:57.447252Z"},"content_sha256":"3817754ea14abb6282ca3a8568f880e2c023c7c4b5d71b0762e9d291997f4abb","schema_version":"1.0","event_id":"sha256:3817754ea14abb6282ca3a8568f880e2c023c7c4b5d71b0762e9d291997f4abb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CIDSTTLMY7Q7LFKK6VJ7PABI24/bundle.json","state_url":"https://pith.science/pith/CIDSTTLMY7Q7LFKK6VJ7PABI24/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CIDSTTLMY7Q7LFKK6VJ7PABI24/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":"2026-07-07T02:40:57Z","links":{"resolver":"https://pith.science/pith/CIDSTTLMY7Q7LFKK6VJ7PABI24","bundle":"https://pith.science/pith/CIDSTTLMY7Q7LFKK6VJ7PABI24/bundle.json","state":"https://pith.science/pith/CIDSTTLMY7Q7LFKK6VJ7PABI24/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CIDSTTLMY7Q7LFKK6VJ7PABI24/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CIDSTTLMY7Q7LFKK6VJ7PABI24","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":"b04b1bd55faf902988372ab62657c7453cfafdad7b0523ef652f4e8900b731b0","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-01T22:16:58Z","title_canon_sha256":"348acb51f6e8e1dc24d624f02b2bc75cd2c56b37854821526082c0cb7338055e"},"schema_version":"1.0","source":{"id":"2211.00768","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.00768","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"arxiv_version","alias_value":"2211.00768v4","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00768","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"pith_short_12","alias_value":"CIDSTTLMY7Q7","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"pith_short_16","alias_value":"CIDSTTLMY7Q7LFKK","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"pith_short_8","alias_value":"CIDSTTLM","created_at":"2026-07-05T05:22:12Z"}],"graph_snapshots":[{"event_id":"sha256:3817754ea14abb6282ca3a8568f880e2c023c7c4b5d71b0762e9d291997f4abb","target":"graph","created_at":"2026-07-05T05:22:12Z","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/2211.00768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent visuolinguistic pre-trained models show promising progress on various end tasks such as image retrieval and video captioning. Yet, they fail miserably on the recently proposed Winoground dataset, which challenges models to match paired images and English captions, with items constructed to overlap lexically but differ in meaning (e.g., \"there is a mug in some grass\" vs. \"there is some grass in a mug\"). By annotating the dataset using new fine-grained tags, we show that solving the Winoground task requires not just compositional language understanding, but a host of other abilities like ","authors_text":"Anuj Diwan, David Harwath, Eunsol Choi, Kyle Mahowald, Layne Berry","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-01T22:16:58Z","title":"Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00768","kind":"arxiv","version":4},"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":"sha256:3cc010e67d90d45c2af09612fecfa2502a9bc8fc71eb25854d6d261deb3b406b","target":"record","created_at":"2026-07-05T05:22:12Z","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":"b04b1bd55faf902988372ab62657c7453cfafdad7b0523ef652f4e8900b731b0","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-01T22:16:58Z","title_canon_sha256":"348acb51f6e8e1dc24d624f02b2bc75cd2c56b37854821526082c0cb7338055e"},"schema_version":"1.0","source":{"id":"2211.00768","kind":"arxiv","version":4}},"canonical_sha256":"120729cd6cc7e1f5954af553f78028d73f355169defbbd1d01813d6781e0420f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"120729cd6cc7e1f5954af553f78028d73f355169defbbd1d01813d6781e0420f","first_computed_at":"2026-07-05T05:22:12.077627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:22:12.077627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hFgjYE/XJ77G5tdrqzYxeIr72IexkdmK0Ot5/oiOdeulbmHuuGxze7tZ8RAN7GBSjdsRRBD7G6tslL5j+QlkDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:22:12.078082Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.00768","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cc010e67d90d45c2af09612fecfa2502a9bc8fc71eb25854d6d261deb3b406b","sha256:3817754ea14abb6282ca3a8568f880e2c023c7c4b5d71b0762e9d291997f4abb"],"state_sha256":"e02b652b7bd13f390cdbef676dda6a52031ed99a43adcee36072f35bb34da8aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IVBv7UiE1PtfOc8pnQ8q5TDtQ9NnBAsN60Mugc/iy9tVqgYmkMbXx6Uy2kiHMRQDo6SZwB8LgmGl96iXfKIqCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T02:40:57.451468Z","bundle_sha256":"e29e54376369c74fcced3bfb66d930689b14b17da5e29a3e13a1d639647a69ec"}}