{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TSYTGCFFX466FEO7GIKM6CDYIV","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":"fbac65fd50d7eebc6a3d095968b5bb1e170cb601439154a6e6d78059ff8bd683","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-09T14:24:29Z","title_canon_sha256":"79aed92ff03f183cbb3752e6427823f5aa4a4df6a5216f6801ca14094f3f2eb1"},"schema_version":"1.0","source":{"id":"2401.04575","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.04575","created_at":"2026-07-05T07:52:43Z"},{"alias_kind":"arxiv_version","alias_value":"2401.04575v2","created_at":"2026-07-05T07:52:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04575","created_at":"2026-07-05T07:52:43Z"},{"alias_kind":"pith_short_12","alias_value":"TSYTGCFFX466","created_at":"2026-07-05T07:52:43Z"},{"alias_kind":"pith_short_16","alias_value":"TSYTGCFFX466FEO7","created_at":"2026-07-05T07:52:43Z"},{"alias_kind":"pith_short_8","alias_value":"TSYTGCFF","created_at":"2026-07-05T07:52:43Z"}],"graph_snapshots":[{"event_id":"sha256:e69257f951e8ddfd99ce67389edac954610d0742bfc7d266c215a366b45c9068","target":"graph","created_at":"2026-07-05T07:52:43Z","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/2401.04575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision and vision-language applications of neural networks, such as image classification and captioning, rely on large-scale annotated datasets that require non-trivial data-collecting processes. This time-consuming endeavor hinders the emergence of large-scale datasets, limiting researchers and practitioners to a small number of choices. Therefore, we seek more efficient ways to collect and annotate images. Previous initiatives have gathered captions from HTML alt-texts and crawled social media postings, but these data sources suffer from noise, sparsity, or subjectivity. For this reason, we ","authors_text":"Aerin Kim, Amelia N. Chu, Apaar Shanker, Elliot Branson, Erhan Bas, Eugenia D Fomitcheva, Haoming Zhang, Isidora Filipovic, Kyunghyun Cho, Samyak Parajuli, Somayeh Sojoudi, Utsav Garg, Yatong Bai","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-09T14:24:29Z","title":"Let's Go Shopping (LGS) -- Web-Scale Image-Text Dataset for Visual Concept Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04575","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":"sha256:2c1d28455a415e30608e6cb701f5e3c80054f12f07848232d632a33cdde8cd62","target":"record","created_at":"2026-07-05T07:52:43Z","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":"fbac65fd50d7eebc6a3d095968b5bb1e170cb601439154a6e6d78059ff8bd683","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-09T14:24:29Z","title_canon_sha256":"79aed92ff03f183cbb3752e6427823f5aa4a4df6a5216f6801ca14094f3f2eb1"},"schema_version":"1.0","source":{"id":"2401.04575","kind":"arxiv","version":2}},"canonical_sha256":"9cb13308a5bf3de291df3214cf0878455dbd50a48b4e117bb886de6dacf63b52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cb13308a5bf3de291df3214cf0878455dbd50a48b4e117bb886de6dacf63b52","first_computed_at":"2026-07-05T07:52:43.816004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:43.816004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NPwbwkjTdVZyIL/QxKNMFGfK2Vow7XOOrG97/iqgflO9hUcUF4XRuHMYedxxWJH/KsulqnZQqcs0c5mtbp+3Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:43.816620Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.04575","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c1d28455a415e30608e6cb701f5e3c80054f12f07848232d632a33cdde8cd62","sha256:e69257f951e8ddfd99ce67389edac954610d0742bfc7d266c215a366b45c9068"],"state_sha256":"83b85ee41ac72ee8d5551014700927ebc3c7220ddbd3509c3a849eefda1b0f4d"}