{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5P7LY5ZVK566CEGT5LJIP5APPQ","short_pith_number":"pith:5P7LY5ZV","canonical_record":{"source":{"id":"2404.00419","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-30T16:54:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"177a71d9113904ef6b24c7342269d462057af4d08fd456b114a3598e75404635","abstract_canon_sha256":"bc3a420f6188d2618e3894717be2af779711e2a4be2125c3e615e7c3c2ad4bbc"},"schema_version":"1.0"},"canonical_sha256":"ebfebc7735577de110d3ead287f40f7c2545cf8335900b7af03db112144dbfd4","source":{"kind":"arxiv","id":"2404.00419","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00419","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00419v1","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00419","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"pith_short_12","alias_value":"5P7LY5ZVK566","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"pith_short_16","alias_value":"5P7LY5ZVK566CEGT","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"pith_short_8","alias_value":"5P7LY5ZV","created_at":"2026-07-05T08:02:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5P7LY5ZVK566CEGT5LJIP5APPQ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.00419","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-30T16:54:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"177a71d9113904ef6b24c7342269d462057af4d08fd456b114a3598e75404635","abstract_canon_sha256":"bc3a420f6188d2618e3894717be2af779711e2a4be2125c3e615e7c3c2ad4bbc"},"schema_version":"1.0"},"canonical_sha256":"ebfebc7735577de110d3ead287f40f7c2545cf8335900b7af03db112144dbfd4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:33.022465Z","signature_b64":"hXTK+PB7aQNZXtC4llEKnv6QYvwx4mOpkYQmNmS0MBlvOIYiULn6DwytsxU5Ge4tBQvQuf8L90MD7V1dSwKcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebfebc7735577de110d3ead287f40f7c2545cf8335900b7af03db112144dbfd4","last_reissued_at":"2026-07-05T08:02:33.021997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:33.021997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.00419","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":"2026-07-05T08:02:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"msOuwjsUv9oflHQYajcZO5ibkAj9wFWkm7/HBWUyjLPzW+3gZXdC47Zm8IRv8zkdFovJArt0zHfc3vM6z55dCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T12:52:59.231907Z"},"content_sha256":"2079b5ae0c153df90108ec678d8fb5e89e0b3d6090704fc6a4e6e2b204191922","schema_version":"1.0","event_id":"sha256:2079b5ae0c153df90108ec678d8fb5e89e0b3d6090704fc6a4e6e2b204191922"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5P7LY5ZVK566CEGT5LJIP5APPQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Vision-Language Models Understand Compound Nouns?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dinesh Manocha, Sonal Kumar, Sreyan Ghosh, S Sakshi, Utkarsh Tyagi","submitted_at":"2024-03-30T16:54:45Z","abstract_excerpt":"Open-vocabulary vision-language models (VLMs) like CLIP, trained using contrastive loss, have emerged as a promising new paradigm for text-to-image retrieval. However, do VLMs understand compound nouns (CNs) (e.g., lab coat) as well as they understand nouns (e.g., lab)? We curate Compun, a novel benchmark with 400 unique and commonly used CNs, to evaluate the effectiveness of VLMs in interpreting CNs. The Compun benchmark challenges a VLM for text-to-image retrieval where, given a text prompt with a CN, the task is to select the correct image that shows the CN among a pair of distractor images"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00419","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/2404.00419/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":"2026-07-05T08:02:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nkQckwmLo5ZUYVapJc1SO2suwyR0QA3dTE0CAI9JQg5TSc9cTcsKkZMpPIzp2/KBBGb+5qrXQn+ogcUP+UvWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T12:52:59.232633Z"},"content_sha256":"fc20593bc016aa9c5c6f4b8d6c97545c7b6efc9eec9fee162d6b872296f9d450","schema_version":"1.0","event_id":"sha256:fc20593bc016aa9c5c6f4b8d6c97545c7b6efc9eec9fee162d6b872296f9d450"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5P7LY5ZVK566CEGT5LJIP5APPQ/bundle.json","state_url":"https://pith.science/pith/5P7LY5ZVK566CEGT5LJIP5APPQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5P7LY5ZVK566CEGT5LJIP5APPQ/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":"2026-08-13T12:52:59Z","links":{"resolver":"https://pith.science/pith/5P7LY5ZVK566CEGT5LJIP5APPQ","bundle":"https://pith.science/pith/5P7LY5ZVK566CEGT5LJIP5APPQ/bundle.json","state":"https://pith.science/pith/5P7LY5ZVK566CEGT5LJIP5APPQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5P7LY5ZVK566CEGT5LJIP5APPQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5P7LY5ZVK566CEGT5LJIP5APPQ","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":"bc3a420f6188d2618e3894717be2af779711e2a4be2125c3e615e7c3c2ad4bbc","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-30T16:54:45Z","title_canon_sha256":"177a71d9113904ef6b24c7342269d462057af4d08fd456b114a3598e75404635"},"schema_version":"1.0","source":{"id":"2404.00419","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00419","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00419v1","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00419","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"pith_short_12","alias_value":"5P7LY5ZVK566","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"pith_short_16","alias_value":"5P7LY5ZVK566CEGT","created_at":"2026-07-05T08:02:33Z"},{"alias_kind":"pith_short_8","alias_value":"5P7LY5ZV","created_at":"2026-07-05T08:02:33Z"}],"graph_snapshots":[{"event_id":"sha256:fc20593bc016aa9c5c6f4b8d6c97545c7b6efc9eec9fee162d6b872296f9d450","target":"graph","created_at":"2026-07-05T08:02:33Z","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/2404.00419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-vocabulary vision-language models (VLMs) like CLIP, trained using contrastive loss, have emerged as a promising new paradigm for text-to-image retrieval. However, do VLMs understand compound nouns (CNs) (e.g., lab coat) as well as they understand nouns (e.g., lab)? We curate Compun, a novel benchmark with 400 unique and commonly used CNs, to evaluate the effectiveness of VLMs in interpreting CNs. The Compun benchmark challenges a VLM for text-to-image retrieval where, given a text prompt with a CN, the task is to select the correct image that shows the CN among a pair of distractor images","authors_text":"Dinesh Manocha, Sonal Kumar, Sreyan Ghosh, S Sakshi, Utkarsh Tyagi","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-30T16:54:45Z","title":"Do Vision-Language Models Understand Compound Nouns?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00419","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":"sha256:2079b5ae0c153df90108ec678d8fb5e89e0b3d6090704fc6a4e6e2b204191922","target":"record","created_at":"2026-07-05T08:02:33Z","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":"bc3a420f6188d2618e3894717be2af779711e2a4be2125c3e615e7c3c2ad4bbc","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-30T16:54:45Z","title_canon_sha256":"177a71d9113904ef6b24c7342269d462057af4d08fd456b114a3598e75404635"},"schema_version":"1.0","source":{"id":"2404.00419","kind":"arxiv","version":1}},"canonical_sha256":"ebfebc7735577de110d3ead287f40f7c2545cf8335900b7af03db112144dbfd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebfebc7735577de110d3ead287f40f7c2545cf8335900b7af03db112144dbfd4","first_computed_at":"2026-07-05T08:02:33.021997Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:33.021997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hXTK+PB7aQNZXtC4llEKnv6QYvwx4mOpkYQmNmS0MBlvOIYiULn6DwytsxU5Ge4tBQvQuf8L90MD7V1dSwKcBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:33.022465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.00419","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2079b5ae0c153df90108ec678d8fb5e89e0b3d6090704fc6a4e6e2b204191922","sha256:fc20593bc016aa9c5c6f4b8d6c97545c7b6efc9eec9fee162d6b872296f9d450"],"state_sha256":"9e2bf3a1722f407742ee9c263af1a70798f0b1ecb37a59afe2a2aac7a7b740f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LBndyUgbppwqNrLK32YIoCXzZ7LQsy9OibPpF5vOPm/PPeNxedDV+Ioo0xFVdIpjzbIILc0TyeXoFRlVps24Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T12:52:59.244413Z","bundle_sha256":"358709af5baf7f8114b7fbf60b39353836e9532fae6b1c5cb7c061b920e3e86f"}}