{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7HRRZJLMPRQ4JHAF6DF3KZHWWS","short_pith_number":"pith:7HRRZJLM","canonical_record":{"source":{"id":"1908.07836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-16T00:40:08Z","cross_cats_sorted":[],"title_canon_sha256":"94dae323df3132a93f3521c92740adffa572806ba573ee31c4078624eaf12aa6","abstract_canon_sha256":"0dd734c897f16b04b7ee69ec4de432c48b5535f2ff11fd6a4a78dfe8d1ad6ac2"},"schema_version":"1.0"},"canonical_sha256":"f9e31ca56c7c61c49c05f0cbb564f6b4a2e824ad40af13fa9c9416639958796b","source":{"kind":"arxiv","id":"1908.07836","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.07836","created_at":"2026-07-04T23:59:01Z"},{"alias_kind":"arxiv_version","alias_value":"1908.07836v1","created_at":"2026-07-04T23:59:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07836","created_at":"2026-07-04T23:59:01Z"},{"alias_kind":"pith_short_12","alias_value":"7HRRZJLMPRQ4","created_at":"2026-07-04T23:59:01Z"},{"alias_kind":"pith_short_16","alias_value":"7HRRZJLMPRQ4JHAF","created_at":"2026-07-04T23:59:01Z"},{"alias_kind":"pith_short_8","alias_value":"7HRRZJLM","created_at":"2026-07-04T23:59:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7HRRZJLMPRQ4JHAF6DF3KZHWWS","target":"record","payload":{"canonical_record":{"source":{"id":"1908.07836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-16T00:40:08Z","cross_cats_sorted":[],"title_canon_sha256":"94dae323df3132a93f3521c92740adffa572806ba573ee31c4078624eaf12aa6","abstract_canon_sha256":"0dd734c897f16b04b7ee69ec4de432c48b5535f2ff11fd6a4a78dfe8d1ad6ac2"},"schema_version":"1.0"},"canonical_sha256":"f9e31ca56c7c61c49c05f0cbb564f6b4a2e824ad40af13fa9c9416639958796b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:01.572699Z","signature_b64":"UUrEKI0OPAib1UeSbHSeNyvAikuJfotUhNX6zXLlBKKx0O3D5ZJc15egMRouk0dtCrqnDiJLNvaeq7kYKJjRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9e31ca56c7c61c49c05f0cbb564f6b4a2e824ad40af13fa9c9416639958796b","last_reissued_at":"2026-07-04T23:59:01.572327Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:01.572327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.07836","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:59:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W80c9DVSP49XP9X94m5O+ndvJat6oPrSZNlWKUQr86GxprALg91vxcPwsRsy/3cq0eyv1pELnodd8Su8z9QNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:08:14.533772Z"},"content_sha256":"38432d6a7936992374c9e8440e7c395f5eeb480e41b2ed6f9e8fe8890d316a84","schema_version":"1.0","event_id":"sha256:38432d6a7936992374c9e8440e7c395f5eeb480e41b2ed6f9e8fe8890d316a84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7HRRZJLMPRQ4JHAF6DF3KZHWWS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PubLayNet: largest dataset ever for document layout analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonio Jimeno Yepes, Jianbin Tang, Xu Zhong","submitted_at":"2019-08-16T00:40:08Z","abstract_excerpt":"Recognizing the layout of unstructured digital documents is an important step when parsing the documents into structured machine-readable format for downstream applications. Deep neural networks that are developed for computer vision have been proven to be an effective method to analyze layout of document images. However, document layout datasets that are currently publicly available are several magnitudes smaller than established computing vision datasets. Models have to be trained by transfer learning from a base model that is pre-trained on a traditional computer vision dataset. In this pap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07836","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/1908.07836/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:59:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aKL3c+hIDDKNJ5FIDGCUh/u+acDopiXsaxAeFyKXSVxcZlHjFsJkW3XRe1gqOL7k8FJcuczmScQ5Jp3QDZQUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:08:14.534148Z"},"content_sha256":"96a19cb6b2910858b0c48e62bdd02d24bab539be4a89a8928a107d536f299cd2","schema_version":"1.0","event_id":"sha256:96a19cb6b2910858b0c48e62bdd02d24bab539be4a89a8928a107d536f299cd2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7HRRZJLMPRQ4JHAF6DF3KZHWWS/bundle.json","state_url":"https://pith.science/pith/7HRRZJLMPRQ4JHAF6DF3KZHWWS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7HRRZJLMPRQ4JHAF6DF3KZHWWS/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":"2026-07-06T18:08:14Z","links":{"resolver":"https://pith.science/pith/7HRRZJLMPRQ4JHAF6DF3KZHWWS","bundle":"https://pith.science/pith/7HRRZJLMPRQ4JHAF6DF3KZHWWS/bundle.json","state":"https://pith.science/pith/7HRRZJLMPRQ4JHAF6DF3KZHWWS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7HRRZJLMPRQ4JHAF6DF3KZHWWS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7HRRZJLMPRQ4JHAF6DF3KZHWWS","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":"0dd734c897f16b04b7ee69ec4de432c48b5535f2ff11fd6a4a78dfe8d1ad6ac2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-16T00:40:08Z","title_canon_sha256":"94dae323df3132a93f3521c92740adffa572806ba573ee31c4078624eaf12aa6"},"schema_version":"1.0","source":{"id":"1908.07836","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.07836","created_at":"2026-07-04T23:59:01Z"},{"alias_kind":"arxiv_version","alias_value":"1908.07836v1","created_at":"2026-07-04T23:59:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07836","created_at":"2026-07-04T23:59:01Z"},{"alias_kind":"pith_short_12","alias_value":"7HRRZJLMPRQ4","created_at":"2026-07-04T23:59:01Z"},{"alias_kind":"pith_short_16","alias_value":"7HRRZJLMPRQ4JHAF","created_at":"2026-07-04T23:59:01Z"},{"alias_kind":"pith_short_8","alias_value":"7HRRZJLM","created_at":"2026-07-04T23:59:01Z"}],"graph_snapshots":[{"event_id":"sha256:96a19cb6b2910858b0c48e62bdd02d24bab539be4a89a8928a107d536f299cd2","target":"graph","created_at":"2026-07-04T23:59:01Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.07836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recognizing the layout of unstructured digital documents is an important step when parsing the documents into structured machine-readable format for downstream applications. Deep neural networks that are developed for computer vision have been proven to be an effective method to analyze layout of document images. However, document layout datasets that are currently publicly available are several magnitudes smaller than established computing vision datasets. Models have to be trained by transfer learning from a base model that is pre-trained on a traditional computer vision dataset. In this pap","authors_text":"Antonio Jimeno Yepes, Jianbin Tang, Xu Zhong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-16T00:40:08Z","title":"PubLayNet: largest dataset ever for document layout analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07836","kind":"arxiv","version":1},"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":"sha256:38432d6a7936992374c9e8440e7c395f5eeb480e41b2ed6f9e8fe8890d316a84","target":"record","created_at":"2026-07-04T23:59:01Z","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":"0dd734c897f16b04b7ee69ec4de432c48b5535f2ff11fd6a4a78dfe8d1ad6ac2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-16T00:40:08Z","title_canon_sha256":"94dae323df3132a93f3521c92740adffa572806ba573ee31c4078624eaf12aa6"},"schema_version":"1.0","source":{"id":"1908.07836","kind":"arxiv","version":1}},"canonical_sha256":"f9e31ca56c7c61c49c05f0cbb564f6b4a2e824ad40af13fa9c9416639958796b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9e31ca56c7c61c49c05f0cbb564f6b4a2e824ad40af13fa9c9416639958796b","first_computed_at":"2026-07-04T23:59:01.572327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:59:01.572327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UUrEKI0OPAib1UeSbHSeNyvAikuJfotUhNX6zXLlBKKx0O3D5ZJc15egMRouk0dtCrqnDiJLNvaeq7kYKJjRDA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:59:01.572699Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.07836","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38432d6a7936992374c9e8440e7c395f5eeb480e41b2ed6f9e8fe8890d316a84","sha256:96a19cb6b2910858b0c48e62bdd02d24bab539be4a89a8928a107d536f299cd2"],"state_sha256":"df031cd34ffa6982ea07b40ef740d7a88b7b7680a4386b1b48e520b15abc9ed0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Qk+9n8iDgQuD8hM6uQ+YseYsbbY+m76edPi5LtfGPOJJG3oKLevucBmcZhBov7+p57Svy1ZyCPtrXCe2knjAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:08:14.536261Z","bundle_sha256":"7c49a396be547cb3600c5dc6361be91790d58dfacc57d3bf32ce63afb9dc315f"}}