{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NKQROKZ4DH7FIFJ56U6OAU5SD2","short_pith_number":"pith:NKQROKZ4","schema_version":"1.0","canonical_sha256":"6aa1172b3c19fe54153df53ce053b21e87b12a0095b36b35887aa7e1073e9796","source":{"kind":"arxiv","id":"2507.20188","version":1},"attestation_state":"computed","paper":{"title":"SAViL-Det: Semantic-Aware Vision-Language Model for Multi-Script Text Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdenour Hadid, Mohammed-En-Nadhir Zighem","submitted_at":"2025-07-27T09:16:39Z","abstract_excerpt":"Detecting text in natural scenes remains challenging, particularly for diverse scripts and arbitrarily shaped instances where visual cues alone are often insufficient. Existing methods do not fully leverage semantic context. This paper introduces SAViL-Det, a novel semantic-aware vision-language model that enhances multi-script text detection by effectively integrating textual prompts with visual features. SAViL-Det utilizes a pre-trained CLIP model combined with an Asymptotic Feature Pyramid Network (AFPN) for multi-scale visual feature fusion. The core of the proposed framework is a novel la"},"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":"2507.20188","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-27T09:16:39Z","cross_cats_sorted":[],"title_canon_sha256":"e9f4abc8a9f0de6f387e5f13d83d8c7aa2d58c9f9da13eb953219e4c2bf7f007","abstract_canon_sha256":"a4338cba13911c941527b1a4c42935f80c4db3e88d467d22b6bf95314c2bb2f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:14.858389Z","signature_b64":"XUEn7SBppdyrXafHppTntb9/1H+ZOYK9vTHt4DPpYeiyOvt5l64X8EZpJmjlXLsHtVEMaTVyS97cBavN9vtzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6aa1172b3c19fe54153df53ce053b21e87b12a0095b36b35887aa7e1073e9796","last_reissued_at":"2026-07-05T11:44:14.857927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:14.857927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAViL-Det: Semantic-Aware Vision-Language Model for Multi-Script Text Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdenour Hadid, Mohammed-En-Nadhir Zighem","submitted_at":"2025-07-27T09:16:39Z","abstract_excerpt":"Detecting text in natural scenes remains challenging, particularly for diverse scripts and arbitrarily shaped instances where visual cues alone are often insufficient. Existing methods do not fully leverage semantic context. This paper introduces SAViL-Det, a novel semantic-aware vision-language model that enhances multi-script text detection by effectively integrating textual prompts with visual features. SAViL-Det utilizes a pre-trained CLIP model combined with an Asymptotic Feature Pyramid Network (AFPN) for multi-scale visual feature fusion. The core of the proposed framework is a novel la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20188","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/2507.20188/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":"2507.20188","created_at":"2026-07-05T11:44:14.857993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20188v1","created_at":"2026-07-05T11:44:14.857993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20188","created_at":"2026-07-05T11:44:14.857993+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKQROKZ4DH7F","created_at":"2026-07-05T11:44:14.857993+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKQROKZ4DH7FIFJ5","created_at":"2026-07-05T11:44:14.857993+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKQROKZ4","created_at":"2026-07-05T11:44:14.857993+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/NKQROKZ4DH7FIFJ56U6OAU5SD2","json":"https://pith.science/pith/NKQROKZ4DH7FIFJ56U6OAU5SD2.json","graph_json":"https://pith.science/api/pith-number/NKQROKZ4DH7FIFJ56U6OAU5SD2/graph.json","events_json":"https://pith.science/api/pith-number/NKQROKZ4DH7FIFJ56U6OAU5SD2/events.json","paper":"https://pith.science/paper/NKQROKZ4"},"agent_actions":{"view_html":"https://pith.science/pith/NKQROKZ4DH7FIFJ56U6OAU5SD2","download_json":"https://pith.science/pith/NKQROKZ4DH7FIFJ56U6OAU5SD2.json","view_paper":"https://pith.science/paper/NKQROKZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20188&json=true","fetch_graph":"https://pith.science/api/pith-number/NKQROKZ4DH7FIFJ56U6OAU5SD2/graph.json","fetch_events":"https://pith.science/api/pith-number/NKQROKZ4DH7FIFJ56U6OAU5SD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKQROKZ4DH7FIFJ56U6OAU5SD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKQROKZ4DH7FIFJ56U6OAU5SD2/action/storage_attestation","attest_author":"https://pith.science/pith/NKQROKZ4DH7FIFJ56U6OAU5SD2/action/author_attestation","sign_citation":"https://pith.science/pith/NKQROKZ4DH7FIFJ56U6OAU5SD2/action/citation_signature","submit_replication":"https://pith.science/pith/NKQROKZ4DH7FIFJ56U6OAU5SD2/action/replication_record"}},"created_at":"2026-07-05T11:44:14.857993+00:00","updated_at":"2026-07-05T11:44:14.857993+00:00"}