{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KS3TKDW7TZHUECKUCDAW4IS7I6","short_pith_number":"pith:KS3TKDW7","schema_version":"1.0","canonical_sha256":"54b7350edf9e4f42095410c16e225f478445c9bfae8cb31c6cb9e40579986722","source":{"kind":"arxiv","id":"2308.11788","version":1},"attestation_state":"computed","paper":{"title":"An extensible point-based method for data chart value detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carlos Soto, Shinjae Yoo","submitted_at":"2023-08-22T21:03:58Z","abstract_excerpt":"We present an extensible method for identifying semantic points to reverse engineer (i.e. extract the values of) data charts, particularly those in scientific articles. Our method uses a point proposal network (akin to region proposal networks for object detection) to directly predict the position of points of interest in a chart, and it is readily extensible to multiple chart types and chart elements. We focus on complex bar charts in the scientific literature, on which our model is able to detect salient points with an accuracy of 0.8705 F1 (@1.5-cell max deviation); it achieves 0.9810 F1 on"},"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":"2308.11788","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-22T21:03:58Z","cross_cats_sorted":[],"title_canon_sha256":"75e5375ae86d1c9d4c581eda872b40b789eca05ecdab35302b01a251d0728011","abstract_canon_sha256":"713b2fafb9110788da7dea01e6b49258e5399bf3b88adba7e5c9a87176eac0da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:54.933127Z","signature_b64":"8ctw8eiOgyLgYXbzWv6Jczo8htdbOaUXgoKbX4skqac8PvttO8rk7nZ4BCvqhbZtjbXvFjy/p47XpR4R30dKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54b7350edf9e4f42095410c16e225f478445c9bfae8cb31c6cb9e40579986722","last_reissued_at":"2026-07-05T06:43:54.932686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:54.932686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An extensible point-based method for data chart value detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carlos Soto, Shinjae Yoo","submitted_at":"2023-08-22T21:03:58Z","abstract_excerpt":"We present an extensible method for identifying semantic points to reverse engineer (i.e. extract the values of) data charts, particularly those in scientific articles. Our method uses a point proposal network (akin to region proposal networks for object detection) to directly predict the position of points of interest in a chart, and it is readily extensible to multiple chart types and chart elements. We focus on complex bar charts in the scientific literature, on which our model is able to detect salient points with an accuracy of 0.8705 F1 (@1.5-cell max deviation); it achieves 0.9810 F1 on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11788","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/2308.11788/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":"2308.11788","created_at":"2026-07-05T06:43:54.932742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.11788v1","created_at":"2026-07-05T06:43:54.932742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11788","created_at":"2026-07-05T06:43:54.932742+00:00"},{"alias_kind":"pith_short_12","alias_value":"KS3TKDW7TZHU","created_at":"2026-07-05T06:43:54.932742+00:00"},{"alias_kind":"pith_short_16","alias_value":"KS3TKDW7TZHUECKU","created_at":"2026-07-05T06:43:54.932742+00:00"},{"alias_kind":"pith_short_8","alias_value":"KS3TKDW7","created_at":"2026-07-05T06:43:54.932742+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.06062","citing_title":"Bar-JEPA: Extracting Values from Bar Chart with Joint-Embedding Predictive Architecture","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KS3TKDW7TZHUECKUCDAW4IS7I6","json":"https://pith.science/pith/KS3TKDW7TZHUECKUCDAW4IS7I6.json","graph_json":"https://pith.science/api/pith-number/KS3TKDW7TZHUECKUCDAW4IS7I6/graph.json","events_json":"https://pith.science/api/pith-number/KS3TKDW7TZHUECKUCDAW4IS7I6/events.json","paper":"https://pith.science/paper/KS3TKDW7"},"agent_actions":{"view_html":"https://pith.science/pith/KS3TKDW7TZHUECKUCDAW4IS7I6","download_json":"https://pith.science/pith/KS3TKDW7TZHUECKUCDAW4IS7I6.json","view_paper":"https://pith.science/paper/KS3TKDW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.11788&json=true","fetch_graph":"https://pith.science/api/pith-number/KS3TKDW7TZHUECKUCDAW4IS7I6/graph.json","fetch_events":"https://pith.science/api/pith-number/KS3TKDW7TZHUECKUCDAW4IS7I6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KS3TKDW7TZHUECKUCDAW4IS7I6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KS3TKDW7TZHUECKUCDAW4IS7I6/action/storage_attestation","attest_author":"https://pith.science/pith/KS3TKDW7TZHUECKUCDAW4IS7I6/action/author_attestation","sign_citation":"https://pith.science/pith/KS3TKDW7TZHUECKUCDAW4IS7I6/action/citation_signature","submit_replication":"https://pith.science/pith/KS3TKDW7TZHUECKUCDAW4IS7I6/action/replication_record"}},"created_at":"2026-07-05T06:43:54.932742+00:00","updated_at":"2026-07-05T06:43:54.932742+00:00"}