{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2DZXOW77GICPZ7GCCOH3ZHNPKB","short_pith_number":"pith:2DZXOW77","schema_version":"1.0","canonical_sha256":"d0f3775bff3204fcfcc2138fbc9daf5058a8ab37bfb17d04b8bc5d3b22f5ab9b","source":{"kind":"arxiv","id":"2301.12293","version":1},"attestation_state":"computed","paper":{"title":"ACL-Fig: A Dataset for Scientific Figure Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.DL"],"primary_cat":"cs.AI","authors_text":"C. Lee Giles, Jian Wu, Kavya Shrinivas Puranik, Shaurya Rohatgi, Zeba Karishma","submitted_at":"2023-01-28T20:27:35Z","abstract_excerpt":"Most existing large-scale academic search engines are built to retrieve text-based information. However, there are no large-scale retrieval services for scientific figures and tables. One challenge for such services is understanding scientific figures' semantics, such as their types and purposes. A key obstacle is the need for datasets containing annotated scientific figures and tables, which can then be used for classification, question-answering, and auto-captioning. Here, we develop a pipeline that extracts figures and tables from the scientific literature and a deep-learning-based framewor"},"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":"2301.12293","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-01-28T20:27:35Z","cross_cats_sorted":["cs.CV","cs.DL"],"title_canon_sha256":"f672a79d41c06e5f69b0b4e433d8f14f0c8c10646687ca9c39f98e2c8ae6ed6e","abstract_canon_sha256":"b2db36b0d0b8e9b143bdf5dfc1e3b6749cc2a65cdc7b9892e39efe7b43008183"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:37.575529Z","signature_b64":"aygjv2EeX0+An+QrmFe+pvMC648NZrEP/+ITbfDxveDcwF8hAlx1/jjK/l33h8gpz6zrdBxWzpR6344Olok4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0f3775bff3204fcfcc2138fbc9daf5058a8ab37bfb17d04b8bc5d3b22f5ab9b","last_reissued_at":"2026-07-05T05:36:37.575198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:37.575198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ACL-Fig: A Dataset for Scientific Figure Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.DL"],"primary_cat":"cs.AI","authors_text":"C. Lee Giles, Jian Wu, Kavya Shrinivas Puranik, Shaurya Rohatgi, Zeba Karishma","submitted_at":"2023-01-28T20:27:35Z","abstract_excerpt":"Most existing large-scale academic search engines are built to retrieve text-based information. However, there are no large-scale retrieval services for scientific figures and tables. One challenge for such services is understanding scientific figures' semantics, such as their types and purposes. A key obstacle is the need for datasets containing annotated scientific figures and tables, which can then be used for classification, question-answering, and auto-captioning. Here, we develop a pipeline that extracts figures and tables from the scientific literature and a deep-learning-based framewor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12293","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/2301.12293/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":"2301.12293","created_at":"2026-07-05T05:36:37.575252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12293v1","created_at":"2026-07-05T05:36:37.575252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12293","created_at":"2026-07-05T05:36:37.575252+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DZXOW77GICP","created_at":"2026-07-05T05:36:37.575252+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DZXOW77GICPZ7GC","created_at":"2026-07-05T05:36:37.575252+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DZXOW77","created_at":"2026-07-05T05:36:37.575252+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20857","citing_title":"DiagramBank: A Large-scale Dataset of Diagram Design Exemplars with Paper Metadata for Retrieval-Augmented Generation","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DZXOW77GICPZ7GCCOH3ZHNPKB","json":"https://pith.science/pith/2DZXOW77GICPZ7GCCOH3ZHNPKB.json","graph_json":"https://pith.science/api/pith-number/2DZXOW77GICPZ7GCCOH3ZHNPKB/graph.json","events_json":"https://pith.science/api/pith-number/2DZXOW77GICPZ7GCCOH3ZHNPKB/events.json","paper":"https://pith.science/paper/2DZXOW77"},"agent_actions":{"view_html":"https://pith.science/pith/2DZXOW77GICPZ7GCCOH3ZHNPKB","download_json":"https://pith.science/pith/2DZXOW77GICPZ7GCCOH3ZHNPKB.json","view_paper":"https://pith.science/paper/2DZXOW77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12293&json=true","fetch_graph":"https://pith.science/api/pith-number/2DZXOW77GICPZ7GCCOH3ZHNPKB/graph.json","fetch_events":"https://pith.science/api/pith-number/2DZXOW77GICPZ7GCCOH3ZHNPKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DZXOW77GICPZ7GCCOH3ZHNPKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DZXOW77GICPZ7GCCOH3ZHNPKB/action/storage_attestation","attest_author":"https://pith.science/pith/2DZXOW77GICPZ7GCCOH3ZHNPKB/action/author_attestation","sign_citation":"https://pith.science/pith/2DZXOW77GICPZ7GCCOH3ZHNPKB/action/citation_signature","submit_replication":"https://pith.science/pith/2DZXOW77GICPZ7GCCOH3ZHNPKB/action/replication_record"}},"created_at":"2026-07-05T05:36:37.575252+00:00","updated_at":"2026-07-05T05:36:37.575252+00:00"}