{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DET5S3VD5MXM5I2IIDOM2LEW3P","short_pith_number":"pith:DET5S3VD","schema_version":"1.0","canonical_sha256":"1927d96ea3eb2ecea34840dccd2c96dbe1b98182cd2bb0db91d3acd934aab620","source":{"kind":"arxiv","id":"2102.03942","version":1},"attestation_state":"computed","paper":{"title":"Iconographic Image Captioning for Artworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eva Cetinic","submitted_at":"2021-02-07T23:11:33Z","abstract_excerpt":"Image captioning implies automatically generating textual descriptions of images based only on the visual input. Although this has been an extensively addressed research topic in recent years, not many contributions have been made in the domain of art historical data. In this particular context, the task of image captioning is confronted with various challenges such as the lack of large-scale datasets of image-text pairs, the complexity of meaning associated with describing artworks and the need for expert-level annotations. This work aims to address some of those challenges by utilizing a nov"},"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":"2102.03942","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-07T23:11:33Z","cross_cats_sorted":[],"title_canon_sha256":"cc51d04167456c393a57bfa7c410b67a5424528da28e5008a150fedda90c8e2d","abstract_canon_sha256":"224cb3b1ae7aad6dd19af103b66adcdff4d4a8de446f753d69f90ce518ad389d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:28.357359Z","signature_b64":"w1Cl77c5RWHNjgOZyWlzJ6uQB6N1VxhIZSW9MEA9+1/QccXmUXu7swsXzG8QhebmmlMT2A5J7rn3ylSIDFExDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1927d96ea3eb2ecea34840dccd2c96dbe1b98182cd2bb0db91d3acd934aab620","last_reissued_at":"2026-07-05T02:13:28.356943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:28.356943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Iconographic Image Captioning for Artworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eva Cetinic","submitted_at":"2021-02-07T23:11:33Z","abstract_excerpt":"Image captioning implies automatically generating textual descriptions of images based only on the visual input. Although this has been an extensively addressed research topic in recent years, not many contributions have been made in the domain of art historical data. In this particular context, the task of image captioning is confronted with various challenges such as the lack of large-scale datasets of image-text pairs, the complexity of meaning associated with describing artworks and the need for expert-level annotations. This work aims to address some of those challenges by utilizing a nov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.03942","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/2102.03942/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":"2102.03942","created_at":"2026-07-05T02:13:28.356996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.03942v1","created_at":"2026-07-05T02:13:28.356996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.03942","created_at":"2026-07-05T02:13:28.356996+00:00"},{"alias_kind":"pith_short_12","alias_value":"DET5S3VD5MXM","created_at":"2026-07-05T02:13:28.356996+00:00"},{"alias_kind":"pith_short_16","alias_value":"DET5S3VD5MXM5I2I","created_at":"2026-07-05T02:13:28.356996+00:00"},{"alias_kind":"pith_short_8","alias_value":"DET5S3VD","created_at":"2026-07-05T02:13:28.356996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.19986","citing_title":"Automating Iconclass: LLMs and RAG for Large-Scale Classification of Religious Woodcuts","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DET5S3VD5MXM5I2IIDOM2LEW3P","json":"https://pith.science/pith/DET5S3VD5MXM5I2IIDOM2LEW3P.json","graph_json":"https://pith.science/api/pith-number/DET5S3VD5MXM5I2IIDOM2LEW3P/graph.json","events_json":"https://pith.science/api/pith-number/DET5S3VD5MXM5I2IIDOM2LEW3P/events.json","paper":"https://pith.science/paper/DET5S3VD"},"agent_actions":{"view_html":"https://pith.science/pith/DET5S3VD5MXM5I2IIDOM2LEW3P","download_json":"https://pith.science/pith/DET5S3VD5MXM5I2IIDOM2LEW3P.json","view_paper":"https://pith.science/paper/DET5S3VD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.03942&json=true","fetch_graph":"https://pith.science/api/pith-number/DET5S3VD5MXM5I2IIDOM2LEW3P/graph.json","fetch_events":"https://pith.science/api/pith-number/DET5S3VD5MXM5I2IIDOM2LEW3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DET5S3VD5MXM5I2IIDOM2LEW3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DET5S3VD5MXM5I2IIDOM2LEW3P/action/storage_attestation","attest_author":"https://pith.science/pith/DET5S3VD5MXM5I2IIDOM2LEW3P/action/author_attestation","sign_citation":"https://pith.science/pith/DET5S3VD5MXM5I2IIDOM2LEW3P/action/citation_signature","submit_replication":"https://pith.science/pith/DET5S3VD5MXM5I2IIDOM2LEW3P/action/replication_record"}},"created_at":"2026-07-05T02:13:28.356996+00:00","updated_at":"2026-07-05T02:13:28.356996+00:00"}