{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P7UFQAN57MCVOL6D3573RSHKMB","short_pith_number":"pith:P7UFQAN5","schema_version":"1.0","canonical_sha256":"7fe85801bdfb05572fc3df7fb8c8ea6075a68140feea4afb9bf68d6f0741ae83","source":{"kind":"arxiv","id":"2507.04735","version":1},"attestation_state":"computed","paper":{"title":"An analysis of vision-language models for fabric retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Asif Khan Pattan, Fabio Poiesi, Francesco Giuliari, Mohamed Lamine Mekhalfi","submitted_at":"2025-07-07T08:00:18Z","abstract_excerpt":"Effective cross-modal retrieval is essential for applications like information retrieval and recommendation systems, particularly in specialized domains such as manufacturing, where product information often consists of visual samples paired with a textual description. This paper investigates the use of Vision Language Models(VLMs) for zero-shot text-to-image retrieval on fabric samples. We address the lack of publicly available datasets by introducing an automated annotation pipeline that uses Multimodal Large Language Models (MLLMs) to generate two types of textual descriptions: freeform nat"},"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":"2507.04735","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T08:00:18Z","cross_cats_sorted":[],"title_canon_sha256":"e54535e09145ccbeed909a1537ce05cf34dfecc5a6053dc65613a530142f9f03","abstract_canon_sha256":"d02dab70d8acaa25ab93c37a9013f5ed1a096b4645fc56fbace106f8a0c420c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:53.138367Z","signature_b64":"QNxVX8ELu5zk3/ucXTEZuSG2xsUzb/bUJMQoRG0vRNikiLvfSg5thDPtCzC096LPG7V7oDv+veWg/CPmItLIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fe85801bdfb05572fc3df7fb8c8ea6075a68140feea4afb9bf68d6f0741ae83","last_reissued_at":"2026-07-05T11:32:53.137831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:53.137831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An analysis of vision-language models for fabric retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Asif Khan Pattan, Fabio Poiesi, Francesco Giuliari, Mohamed Lamine Mekhalfi","submitted_at":"2025-07-07T08:00:18Z","abstract_excerpt":"Effective cross-modal retrieval is essential for applications like information retrieval and recommendation systems, particularly in specialized domains such as manufacturing, where product information often consists of visual samples paired with a textual description. This paper investigates the use of Vision Language Models(VLMs) for zero-shot text-to-image retrieval on fabric samples. We address the lack of publicly available datasets by introducing an automated annotation pipeline that uses Multimodal Large Language Models (MLLMs) to generate two types of textual descriptions: freeform nat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04735","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/2507.04735/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":"2507.04735","created_at":"2026-07-05T11:32:53.137896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04735v1","created_at":"2026-07-05T11:32:53.137896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04735","created_at":"2026-07-05T11:32:53.137896+00:00"},{"alias_kind":"pith_short_12","alias_value":"P7UFQAN57MCV","created_at":"2026-07-05T11:32:53.137896+00:00"},{"alias_kind":"pith_short_16","alias_value":"P7UFQAN57MCVOL6D","created_at":"2026-07-05T11:32:53.137896+00:00"},{"alias_kind":"pith_short_8","alias_value":"P7UFQAN5","created_at":"2026-07-05T11:32:53.137896+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/P7UFQAN57MCVOL6D3573RSHKMB","json":"https://pith.science/pith/P7UFQAN57MCVOL6D3573RSHKMB.json","graph_json":"https://pith.science/api/pith-number/P7UFQAN57MCVOL6D3573RSHKMB/graph.json","events_json":"https://pith.science/api/pith-number/P7UFQAN57MCVOL6D3573RSHKMB/events.json","paper":"https://pith.science/paper/P7UFQAN5"},"agent_actions":{"view_html":"https://pith.science/pith/P7UFQAN57MCVOL6D3573RSHKMB","download_json":"https://pith.science/pith/P7UFQAN57MCVOL6D3573RSHKMB.json","view_paper":"https://pith.science/paper/P7UFQAN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04735&json=true","fetch_graph":"https://pith.science/api/pith-number/P7UFQAN57MCVOL6D3573RSHKMB/graph.json","fetch_events":"https://pith.science/api/pith-number/P7UFQAN57MCVOL6D3573RSHKMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P7UFQAN57MCVOL6D3573RSHKMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P7UFQAN57MCVOL6D3573RSHKMB/action/storage_attestation","attest_author":"https://pith.science/pith/P7UFQAN57MCVOL6D3573RSHKMB/action/author_attestation","sign_citation":"https://pith.science/pith/P7UFQAN57MCVOL6D3573RSHKMB/action/citation_signature","submit_replication":"https://pith.science/pith/P7UFQAN57MCVOL6D3573RSHKMB/action/replication_record"}},"created_at":"2026-07-05T11:32:53.137896+00:00","updated_at":"2026-07-05T11:32:53.137896+00:00"}