{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TSNYWDL3RRDH5KVPRCY7KT7MKC","short_pith_number":"pith:TSNYWDL3","schema_version":"1.0","canonical_sha256":"9c9b8b0d7b8c467eaaaf88b1f54fec50aa7ba2a3c5f03c772cb94721fb8e0a9d","source":{"kind":"arxiv","id":"2304.01961","version":1},"attestation_state":"computed","paper":{"title":"AToMiC: An Image/Text Retrieval Test Collection to Support Multimedia Content Creation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.IR","authors_text":"Carlos Lassance, Jheng-Hong Yang, Jimmy Lin, Krishna Srinivasan, Miriam Redi, Rafael Sampaio de Rezende, St\\'ephane Clinchant","submitted_at":"2023-04-04T17:11:34Z","abstract_excerpt":"This paper presents the AToMiC (Authoring Tools for Multimedia Content) dataset, designed to advance research in image/text cross-modal retrieval. While vision-language pretrained transformers have led to significant improvements in retrieval effectiveness, existing research has relied on image-caption datasets that feature only simplistic image-text relationships and underspecified user models of retrieval tasks. To address the gap between these oversimplified settings and real-world applications for multimedia content creation, we introduce a new approach for building retrieval test collecti"},"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":"2304.01961","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-04-04T17:11:34Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"56de0980b2aad4234e27b4b855b0ff4c427a93a42ef2612b59c715d4d807ea3e","abstract_canon_sha256":"223763090103a7679a61ef5ad57d862698a70da179aed658ecc1f05e728d96a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:46.859852Z","signature_b64":"SnYSNJnb0X+LYeRGe60dZl4ERGSQ7bvCtnbbVsV3EKvZYhCdzr4gHAw5NtSkxVdArqOwC3lyfh1j6whHV7QXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c9b8b0d7b8c467eaaaf88b1f54fec50aa7ba2a3c5f03c772cb94721fb8e0a9d","last_reissued_at":"2026-07-05T05:57:46.859360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:46.859360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AToMiC: An Image/Text Retrieval Test Collection to Support Multimedia Content Creation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.IR","authors_text":"Carlos Lassance, Jheng-Hong Yang, Jimmy Lin, Krishna Srinivasan, Miriam Redi, Rafael Sampaio de Rezende, St\\'ephane Clinchant","submitted_at":"2023-04-04T17:11:34Z","abstract_excerpt":"This paper presents the AToMiC (Authoring Tools for Multimedia Content) dataset, designed to advance research in image/text cross-modal retrieval. While vision-language pretrained transformers have led to significant improvements in retrieval effectiveness, existing research has relied on image-caption datasets that feature only simplistic image-text relationships and underspecified user models of retrieval tasks. To address the gap between these oversimplified settings and real-world applications for multimedia content creation, we introduce a new approach for building retrieval test collecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.01961","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/2304.01961/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":"2304.01961","created_at":"2026-07-05T05:57:46.859419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.01961v1","created_at":"2026-07-05T05:57:46.859419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.01961","created_at":"2026-07-05T05:57:46.859419+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSNYWDL3RRDH","created_at":"2026-07-05T05:57:46.859419+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSNYWDL3RRDH5KVP","created_at":"2026-07-05T05:57:46.859419+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSNYWDL3","created_at":"2026-07-05T05:57:46.859419+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/TSNYWDL3RRDH5KVPRCY7KT7MKC","json":"https://pith.science/pith/TSNYWDL3RRDH5KVPRCY7KT7MKC.json","graph_json":"https://pith.science/api/pith-number/TSNYWDL3RRDH5KVPRCY7KT7MKC/graph.json","events_json":"https://pith.science/api/pith-number/TSNYWDL3RRDH5KVPRCY7KT7MKC/events.json","paper":"https://pith.science/paper/TSNYWDL3"},"agent_actions":{"view_html":"https://pith.science/pith/TSNYWDL3RRDH5KVPRCY7KT7MKC","download_json":"https://pith.science/pith/TSNYWDL3RRDH5KVPRCY7KT7MKC.json","view_paper":"https://pith.science/paper/TSNYWDL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.01961&json=true","fetch_graph":"https://pith.science/api/pith-number/TSNYWDL3RRDH5KVPRCY7KT7MKC/graph.json","fetch_events":"https://pith.science/api/pith-number/TSNYWDL3RRDH5KVPRCY7KT7MKC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSNYWDL3RRDH5KVPRCY7KT7MKC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSNYWDL3RRDH5KVPRCY7KT7MKC/action/storage_attestation","attest_author":"https://pith.science/pith/TSNYWDL3RRDH5KVPRCY7KT7MKC/action/author_attestation","sign_citation":"https://pith.science/pith/TSNYWDL3RRDH5KVPRCY7KT7MKC/action/citation_signature","submit_replication":"https://pith.science/pith/TSNYWDL3RRDH5KVPRCY7KT7MKC/action/replication_record"}},"created_at":"2026-07-05T05:57:46.859419+00:00","updated_at":"2026-07-05T05:57:46.859419+00:00"}