{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:WLPAMJL3EQ3UBWDHLKAS4OCFZH","short_pith_number":"pith:WLPAMJL3","schema_version":"1.0","canonical_sha256":"b2de06257b243740d8675a812e3845c9d4c7872b5ab7342cb143e54f310995e7","source":{"kind":"arxiv","id":"1506.08891","version":6},"attestation_state":"computed","paper":{"title":"Detecting Table Region in PDF Documents Using Distant Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Doo Soon Kim, Miao Fan","submitted_at":"2015-06-29T22:54:17Z","abstract_excerpt":"Superior to state-of-the-art approaches which compete in table recognition with 67 annotated government reports in PDF format released by {\\it ICDAR 2013 Table Competition}, this paper contributes a novel paradigm leveraging large-scale unlabeled PDF documents to open-domain table detection. We integrate the paradigm into our latest developed system ({\\it PdfExtra}) to detect the region of tables by means of 9,466 academic articles from the entire repository of {\\it ACL Anthology}, where almost all papers are archived by PDF format without annotation for tables. The paradigm first designs heur"},"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":"1506.08891","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-29T22:54:17Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"eefc87e6717575ebbc17a436df2616c916c74ec5bdb15f3c305b6f9ac08b7104","abstract_canon_sha256":"c658079e1518ea1cd7eef65c0a9ccfcc5abb58d49a5d45451e073b32fc3d75be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:32:28.943763Z","signature_b64":"k0HzexQm/gknesKg8VwgTmIBlPZLaf5Dz7aO9lEuaz4f9MZ1msVYzaZmZY3GCh1SXNt3uaBioRlY0+jnwGhIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2de06257b243740d8675a812e3845c9d4c7872b5ab7342cb143e54f310995e7","last_reissued_at":"2026-05-18T01:32:28.943115Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:32:28.943115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting Table Region in PDF Documents Using Distant Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Doo Soon Kim, Miao Fan","submitted_at":"2015-06-29T22:54:17Z","abstract_excerpt":"Superior to state-of-the-art approaches which compete in table recognition with 67 annotated government reports in PDF format released by {\\it ICDAR 2013 Table Competition}, this paper contributes a novel paradigm leveraging large-scale unlabeled PDF documents to open-domain table detection. We integrate the paradigm into our latest developed system ({\\it PdfExtra}) to detect the region of tables by means of 9,466 academic articles from the entire repository of {\\it ACL Anthology}, where almost all papers are archived by PDF format without annotation for tables. The paradigm first designs heur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.08891","kind":"arxiv","version":6},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1506.08891","created_at":"2026-05-18T01:32:28.943194+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.08891v6","created_at":"2026-05-18T01:32:28.943194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.08891","created_at":"2026-05-18T01:32:28.943194+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLPAMJL3EQ3U","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLPAMJL3EQ3UBWDH","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLPAMJL3","created_at":"2026-05-18T12:29:47.479230+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/WLPAMJL3EQ3UBWDHLKAS4OCFZH","json":"https://pith.science/pith/WLPAMJL3EQ3UBWDHLKAS4OCFZH.json","graph_json":"https://pith.science/api/pith-number/WLPAMJL3EQ3UBWDHLKAS4OCFZH/graph.json","events_json":"https://pith.science/api/pith-number/WLPAMJL3EQ3UBWDHLKAS4OCFZH/events.json","paper":"https://pith.science/paper/WLPAMJL3"},"agent_actions":{"view_html":"https://pith.science/pith/WLPAMJL3EQ3UBWDHLKAS4OCFZH","download_json":"https://pith.science/pith/WLPAMJL3EQ3UBWDHLKAS4OCFZH.json","view_paper":"https://pith.science/paper/WLPAMJL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.08891&json=true","fetch_graph":"https://pith.science/api/pith-number/WLPAMJL3EQ3UBWDHLKAS4OCFZH/graph.json","fetch_events":"https://pith.science/api/pith-number/WLPAMJL3EQ3UBWDHLKAS4OCFZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLPAMJL3EQ3UBWDHLKAS4OCFZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLPAMJL3EQ3UBWDHLKAS4OCFZH/action/storage_attestation","attest_author":"https://pith.science/pith/WLPAMJL3EQ3UBWDHLKAS4OCFZH/action/author_attestation","sign_citation":"https://pith.science/pith/WLPAMJL3EQ3UBWDHLKAS4OCFZH/action/citation_signature","submit_replication":"https://pith.science/pith/WLPAMJL3EQ3UBWDHLKAS4OCFZH/action/replication_record"}},"created_at":"2026-05-18T01:32:28.943194+00:00","updated_at":"2026-05-18T01:32:28.943194+00:00"}