{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TSYTGCFFX466FEO7GIKM6CDYIV","short_pith_number":"pith:TSYTGCFF","schema_version":"1.0","canonical_sha256":"9cb13308a5bf3de291df3214cf0878455dbd50a48b4e117bb886de6dacf63b52","source":{"kind":"arxiv","id":"2401.04575","version":2},"attestation_state":"computed","paper":{"title":"Let's Go Shopping (LGS) -- Web-Scale Image-Text Dataset for Visual Concept Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","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","submitted_at":"2024-01-09T14:24:29Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.04575","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-09T14:24:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"79aed92ff03f183cbb3752e6427823f5aa4a4df6a5216f6801ca14094f3f2eb1","abstract_canon_sha256":"fbac65fd50d7eebc6a3d095968b5bb1e170cb601439154a6e6d78059ff8bd683"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:43.816620Z","signature_b64":"NPwbwkjTdVZyIL/QxKNMFGfK2Vow7XOOrG97/iqgflO9hUcUF4XRuHMYedxxWJH/KsulqnZQqcs0c5mtbp+3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cb13308a5bf3de291df3214cf0878455dbd50a48b4e117bb886de6dacf63b52","last_reissued_at":"2026-07-05T07:52:43.816004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:43.816004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Let's Go Shopping (LGS) -- Web-Scale Image-Text Dataset for Visual Concept Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","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","submitted_at":"2024-01-09T14:24:29Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04575","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/2401.04575/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.04575","created_at":"2026-07-05T07:52:43.816089+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04575v2","created_at":"2026-07-05T07:52:43.816089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04575","created_at":"2026-07-05T07:52:43.816089+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSYTGCFFX466","created_at":"2026-07-05T07:52:43.816089+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSYTGCFFX466FEO7","created_at":"2026-07-05T07:52:43.816089+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSYTGCFF","created_at":"2026-07-05T07:52:43.816089+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSYTGCFFX466FEO7GIKM6CDYIV","json":"https://pith.science/pith/TSYTGCFFX466FEO7GIKM6CDYIV.json","graph_json":"https://pith.science/api/pith-number/TSYTGCFFX466FEO7GIKM6CDYIV/graph.json","events_json":"https://pith.science/api/pith-number/TSYTGCFFX466FEO7GIKM6CDYIV/events.json","paper":"https://pith.science/paper/TSYTGCFF"},"agent_actions":{"view_html":"https://pith.science/pith/TSYTGCFFX466FEO7GIKM6CDYIV","download_json":"https://pith.science/pith/TSYTGCFFX466FEO7GIKM6CDYIV.json","view_paper":"https://pith.science/paper/TSYTGCFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04575&json=true","fetch_graph":"https://pith.science/api/pith-number/TSYTGCFFX466FEO7GIKM6CDYIV/graph.json","fetch_events":"https://pith.science/api/pith-number/TSYTGCFFX466FEO7GIKM6CDYIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSYTGCFFX466FEO7GIKM6CDYIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSYTGCFFX466FEO7GIKM6CDYIV/action/storage_attestation","attest_author":"https://pith.science/pith/TSYTGCFFX466FEO7GIKM6CDYIV/action/author_attestation","sign_citation":"https://pith.science/pith/TSYTGCFFX466FEO7GIKM6CDYIV/action/citation_signature","submit_replication":"https://pith.science/pith/TSYTGCFFX466FEO7GIKM6CDYIV/action/replication_record"}},"created_at":"2026-07-05T07:52:43.816089+00:00","updated_at":"2026-07-05T07:52:43.816089+00:00"}