{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:WLPAMJL3EQ3UBWDHLKAS4OCFZH","short_pith_number":"pith:WLPAMJL3","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"},"canonical_sha256":"b2de06257b243740d8675a812e3845c9d4c7872b5ab7342cb143e54f310995e7","source":{"kind":"arxiv","id":"1506.08891","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.08891","created_at":"2026-05-18T01:32:28Z"},{"alias_kind":"arxiv_version","alias_value":"1506.08891v6","created_at":"2026-05-18T01:32:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.08891","created_at":"2026-05-18T01:32:28Z"},{"alias_kind":"pith_short_12","alias_value":"WLPAMJL3EQ3U","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"WLPAMJL3EQ3UBWDH","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"WLPAMJL3","created_at":"2026-05-18T12:29:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:WLPAMJL3EQ3UBWDHLKAS4OCFZH","target":"record","payload":{"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"},"canonical_sha256":"b2de06257b243740d8675a812e3845c9d4c7872b5ab7342cb143e54f310995e7","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"},"source_kind":"arxiv","source_id":"1506.08891","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:32:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AlZRfGvUH6zFNiin5JkJl8bkp12CHAnnDb6jsEzrRtjr5kaL2/KUnCWL3VfiakoLfbs8YwvIRO2PYqm0JIRBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:22:32.542545Z"},"content_sha256":"04c9692c88dc64565cf4a1cdf7bb11f58f7559c2732c81a183be59861c1cf5c8","schema_version":"1.0","event_id":"sha256:04c9692c88dc64565cf4a1cdf7bb11f58f7559c2732c81a183be59861c1cf5c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:WLPAMJL3EQ3UBWDHLKAS4OCFZH","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:32:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TZTB2p35Yght1TpFj7CyVt9qESO7rFjI8tXhBHb71JNepZ6BVK9AnzSIWHaidPAF69jWHsaxEt80WanW/Ax7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:22:32.542907Z"},"content_sha256":"b6b1ab5f7b7514ce548a153c7e832bed2c7cf026688d5a9368d783b4fe728d18","schema_version":"1.0","event_id":"sha256:b6b1ab5f7b7514ce548a153c7e832bed2c7cf026688d5a9368d783b4fe728d18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WLPAMJL3EQ3UBWDHLKAS4OCFZH/bundle.json","state_url":"https://pith.science/pith/WLPAMJL3EQ3UBWDHLKAS4OCFZH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WLPAMJL3EQ3UBWDHLKAS4OCFZH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T07:22:32Z","links":{"resolver":"https://pith.science/pith/WLPAMJL3EQ3UBWDHLKAS4OCFZH","bundle":"https://pith.science/pith/WLPAMJL3EQ3UBWDHLKAS4OCFZH/bundle.json","state":"https://pith.science/pith/WLPAMJL3EQ3UBWDHLKAS4OCFZH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WLPAMJL3EQ3UBWDHLKAS4OCFZH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:WLPAMJL3EQ3UBWDHLKAS4OCFZH","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":"c658079e1518ea1cd7eef65c0a9ccfcc5abb58d49a5d45451e073b32fc3d75be","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-29T22:54:17Z","title_canon_sha256":"eefc87e6717575ebbc17a436df2616c916c74ec5bdb15f3c305b6f9ac08b7104"},"schema_version":"1.0","source":{"id":"1506.08891","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.08891","created_at":"2026-05-18T01:32:28Z"},{"alias_kind":"arxiv_version","alias_value":"1506.08891v6","created_at":"2026-05-18T01:32:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.08891","created_at":"2026-05-18T01:32:28Z"},{"alias_kind":"pith_short_12","alias_value":"WLPAMJL3EQ3U","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"WLPAMJL3EQ3UBWDH","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"WLPAMJL3","created_at":"2026-05-18T12:29:47Z"}],"graph_snapshots":[{"event_id":"sha256:b6b1ab5f7b7514ce548a153c7e832bed2c7cf026688d5a9368d783b4fe728d18","target":"graph","created_at":"2026-05-18T01:32:28Z","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":"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","authors_text":"Doo Soon Kim, Miao Fan","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-29T22:54:17Z","title":"Detecting Table Region in PDF Documents Using Distant Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.08891","kind":"arxiv","version":6},"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":"sha256:04c9692c88dc64565cf4a1cdf7bb11f58f7559c2732c81a183be59861c1cf5c8","target":"record","created_at":"2026-05-18T01:32:28Z","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":"c658079e1518ea1cd7eef65c0a9ccfcc5abb58d49a5d45451e073b32fc3d75be","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-29T22:54:17Z","title_canon_sha256":"eefc87e6717575ebbc17a436df2616c916c74ec5bdb15f3c305b6f9ac08b7104"},"schema_version":"1.0","source":{"id":"1506.08891","kind":"arxiv","version":6}},"canonical_sha256":"b2de06257b243740d8675a812e3845c9d4c7872b5ab7342cb143e54f310995e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2de06257b243740d8675a812e3845c9d4c7872b5ab7342cb143e54f310995e7","first_computed_at":"2026-05-18T01:32:28.943115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:32:28.943115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k0HzexQm/gknesKg8VwgTmIBlPZLaf5Dz7aO9lEuaz4f9MZ1msVYzaZmZY3GCh1SXNt3uaBioRlY0+jnwGhIDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:32:28.943763Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.08891","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04c9692c88dc64565cf4a1cdf7bb11f58f7559c2732c81a183be59861c1cf5c8","sha256:b6b1ab5f7b7514ce548a153c7e832bed2c7cf026688d5a9368d783b4fe728d18"],"state_sha256":"2cd8b678a9732cc7b9239b2d0088fea500e3644c0547024b981b0023748abc37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PDzRVqpuP2glwGInnT7bjxLmgKeHtlhO2u6oX7euC4eDX4P2ZCdrbgSNNAVy14LRDsVimzO7KWewE5Y3U7ryDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T07:22:32.544873Z","bundle_sha256":"3f29df52b93a055e38a21482f6256215841fdac1153ec15ed779d04b080a49e3"}}