{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NA2VNYKFXL7IODALXBWOTRF2IU","short_pith_number":"pith:NA2VNYKF","schema_version":"1.0","canonical_sha256":"683556e145bafe870c0bb86ce9c4ba4522bb41bf23c6a8390be967795007af9d","source":{"kind":"arxiv","id":"2606.13275","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Captioning for Cultural Heritage: Automated Image Analysis of Traditional Indonesian Clothing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anugrah Aidin Yotolembah, Gembong Edhi Setyawan, Novanto Yudistira","submitted_at":"2026-06-11T12:29:39Z","abstract_excerpt":"This paper presents Custom ZeroCLIP, a retrieval-augmented vision-language framework for zero-shot captioning of Indonesian traditional garments. The dataset contains 3,800 expert-annotated images from all 38 Indonesian provinces. Using a province-level inductive zero-shot protocol, the model is trained on 24 seen provinces, validated on 6 seen provinces, and evaluated on 8 unseen provinces. The framework combines a frozen CLIP ViT-B/32 image encoder, a CLIP text encoder, a BERT text encoder, and an LSTM caption decoder. During inference, unseen-province labels and captions are unavailable, an"},"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":"2606.13275","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T12:29:39Z","cross_cats_sorted":[],"title_canon_sha256":"6bd8364519fffa278cf2b6f8e03485176b385d200c75bc7ee154020147a91027","abstract_canon_sha256":"5d6d06cc6fa50fa4233b112b395631ddfe8ecca231d919535e22d129a029efa2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:50.074943Z","signature_b64":"Dn63D4PpMM1tNY/7cpIFmLpvJ9lu/lu2igfHEV0nyzaeDWsuAI5LvIrDzWmwYoXrM0w84G7KYKiurSbHosA8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"683556e145bafe870c0bb86ce9c4ba4522bb41bf23c6a8390be967795007af9d","last_reissued_at":"2026-06-12T01:09:50.073999Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:50.073999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Captioning for Cultural Heritage: Automated Image Analysis of Traditional Indonesian Clothing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anugrah Aidin Yotolembah, Gembong Edhi Setyawan, Novanto Yudistira","submitted_at":"2026-06-11T12:29:39Z","abstract_excerpt":"This paper presents Custom ZeroCLIP, a retrieval-augmented vision-language framework for zero-shot captioning of Indonesian traditional garments. The dataset contains 3,800 expert-annotated images from all 38 Indonesian provinces. Using a province-level inductive zero-shot protocol, the model is trained on 24 seen provinces, validated on 6 seen provinces, and evaluated on 8 unseen provinces. The framework combines a frozen CLIP ViT-B/32 image encoder, a CLIP text encoder, a BERT text encoder, and an LSTM caption decoder. During inference, unseen-province labels and captions are unavailable, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13275","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/2606.13275/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":"2606.13275","created_at":"2026-06-12T01:09:50.074175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13275v1","created_at":"2026-06-12T01:09:50.074175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13275","created_at":"2026-06-12T01:09:50.074175+00:00"},{"alias_kind":"pith_short_12","alias_value":"NA2VNYKFXL7I","created_at":"2026-06-12T01:09:50.074175+00:00"},{"alias_kind":"pith_short_16","alias_value":"NA2VNYKFXL7IODAL","created_at":"2026-06-12T01:09:50.074175+00:00"},{"alias_kind":"pith_short_8","alias_value":"NA2VNYKF","created_at":"2026-06-12T01:09:50.074175+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/NA2VNYKFXL7IODALXBWOTRF2IU","json":"https://pith.science/pith/NA2VNYKFXL7IODALXBWOTRF2IU.json","graph_json":"https://pith.science/api/pith-number/NA2VNYKFXL7IODALXBWOTRF2IU/graph.json","events_json":"https://pith.science/api/pith-number/NA2VNYKFXL7IODALXBWOTRF2IU/events.json","paper":"https://pith.science/paper/NA2VNYKF"},"agent_actions":{"view_html":"https://pith.science/pith/NA2VNYKFXL7IODALXBWOTRF2IU","download_json":"https://pith.science/pith/NA2VNYKFXL7IODALXBWOTRF2IU.json","view_paper":"https://pith.science/paper/NA2VNYKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13275&json=true","fetch_graph":"https://pith.science/api/pith-number/NA2VNYKFXL7IODALXBWOTRF2IU/graph.json","fetch_events":"https://pith.science/api/pith-number/NA2VNYKFXL7IODALXBWOTRF2IU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NA2VNYKFXL7IODALXBWOTRF2IU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NA2VNYKFXL7IODALXBWOTRF2IU/action/storage_attestation","attest_author":"https://pith.science/pith/NA2VNYKFXL7IODALXBWOTRF2IU/action/author_attestation","sign_citation":"https://pith.science/pith/NA2VNYKFXL7IODALXBWOTRF2IU/action/citation_signature","submit_replication":"https://pith.science/pith/NA2VNYKFXL7IODALXBWOTRF2IU/action/replication_record"}},"created_at":"2026-06-12T01:09:50.074175+00:00","updated_at":"2026-06-12T01:09:50.074175+00:00"}