{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NWLQYFQKYLKGXSH6R2UM4FCRYM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a14cb6b56ab11f5c6e77a9f1fe9e59af733d25afa79edda127b3ed5e0abb9db1","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2018-04-06T20:22:47Z","title_canon_sha256":"a9d96474a4c91e63b974d546257fb94ce3b770f970e51ac0450a72b19b432249"},"schema_version":"1.0","source":{"id":"1804.02445","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.02445","created_at":"2026-05-18T00:14:33Z"},{"alias_kind":"arxiv_version","alias_value":"1804.02445v2","created_at":"2026-05-18T00:14:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02445","created_at":"2026-05-18T00:14:33Z"},{"alias_kind":"pith_short_12","alias_value":"NWLQYFQKYLKG","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NWLQYFQKYLKGXSH6","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NWLQYFQK","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:dd0db65ddae7503e0c047c897b54e753cf3d49c5373b868b65a3a9ec924d6116","target":"graph","created_at":"2026-05-18T00:14:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Non-textual components such as charts, diagrams and tables provide key information in many scientific documents, but the lack of large labeled datasets has impeded the development of data-driven methods for scientific figure extraction. In this paper, we induce high-quality training labels for the task of figure extraction in a large number of scientific documents, with no human intervention. To accomplish this we leverage the auxiliary data provided in two large web collections of scientific documents (arXiv and PubMed) to locate figures and their associated captions in the rasterized PDF. We","authors_text":"Nicholas Lourie, Noah Siegel, Russell Power, Waleed Ammar","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2018-04-06T20:22:47Z","title":"Extracting Scientific Figures with Distantly Supervised Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02445","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:426820981b22a4671a2dd6cfd2e3fa7d9cd818dedeacad406eba14ab5cf439c8","target":"record","created_at":"2026-05-18T00:14:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a14cb6b56ab11f5c6e77a9f1fe9e59af733d25afa79edda127b3ed5e0abb9db1","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2018-04-06T20:22:47Z","title_canon_sha256":"a9d96474a4c91e63b974d546257fb94ce3b770f970e51ac0450a72b19b432249"},"schema_version":"1.0","source":{"id":"1804.02445","kind":"arxiv","version":2}},"canonical_sha256":"6d970c160ac2d46bc8fe8ea8ce1451c337905b154a51b47578c9b74ed66cc72e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d970c160ac2d46bc8fe8ea8ce1451c337905b154a51b47578c9b74ed66cc72e","first_computed_at":"2026-05-18T00:14:33.874434Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:33.874434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8iD5CMgzBlP3gM+XzBBOXIOvhkM89YJp4wgk3eZVETTbtvC9w19o6hReVsR4BRQCxA5fYG+9kmzFarbYknqCBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:33.875104Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.02445","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:426820981b22a4671a2dd6cfd2e3fa7d9cd818dedeacad406eba14ab5cf439c8","sha256:dd0db65ddae7503e0c047c897b54e753cf3d49c5373b868b65a3a9ec924d6116"],"state_sha256":"68cdfee3304e7d7e32ac40891c8f975b3b1a8e1db3cc3578d29c36b2ec1da32f"}