{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:VJU7C2TDZT5O5HL4VDTMI2Q4D7","short_pith_number":"pith:VJU7C2TD","canonical_record":{"source":{"id":"2004.08686","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-18T18:38:25Z","cross_cats_sorted":[],"title_canon_sha256":"d79b9fda37de628d6f20d583d360e389166d67e34e3f459c7660c233ee034275","abstract_canon_sha256":"b8c47205f6b71014e69a787a0ef0efbf2250f34ae217cfcd7eb8ca5e310c7505"},"schema_version":"1.0"},"canonical_sha256":"aa69f16a63ccfaee9d7ca8e6c46a1c1fef33513767e57f3cd7981870107f0e02","source":{"kind":"arxiv","id":"2004.08686","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.08686","created_at":"2026-07-05T00:56:08Z"},{"alias_kind":"arxiv_version","alias_value":"2004.08686v1","created_at":"2026-07-05T00:56:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.08686","created_at":"2026-07-05T00:56:08Z"},{"alias_kind":"pith_short_12","alias_value":"VJU7C2TDZT5O","created_at":"2026-07-05T00:56:08Z"},{"alias_kind":"pith_short_16","alias_value":"VJU7C2TDZT5O5HL4","created_at":"2026-07-05T00:56:08Z"},{"alias_kind":"pith_short_8","alias_value":"VJU7C2TD","created_at":"2026-07-05T00:56:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:VJU7C2TDZT5O5HL4VDTMI2Q4D7","target":"record","payload":{"canonical_record":{"source":{"id":"2004.08686","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-18T18:38:25Z","cross_cats_sorted":[],"title_canon_sha256":"d79b9fda37de628d6f20d583d360e389166d67e34e3f459c7660c233ee034275","abstract_canon_sha256":"b8c47205f6b71014e69a787a0ef0efbf2250f34ae217cfcd7eb8ca5e310c7505"},"schema_version":"1.0"},"canonical_sha256":"aa69f16a63ccfaee9d7ca8e6c46a1c1fef33513767e57f3cd7981870107f0e02","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:56:08.557776Z","signature_b64":"LtUvEMkDhldGQmUoFCzVvVLMuuUEU56G0dSNvwn4PfXAixkmLPpGd7FyWUZtY0L7mUkMhqI5asJOXc7HRV4ECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa69f16a63ccfaee9d7ca8e6c46a1c1fef33513767e57f3cd7981870107f0e02","last_reissued_at":"2026-07-05T00:56:08.557311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:56:08.557311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.08686","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":"2026-07-05T00:56:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fxefYnoJw8gJD/ijyQo3fC5ZwaPoM4r1nhcXQmAs877ZQh6rgCleIINK2EVJZSRDoWF+xWl0isPNBoAxXiu+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:44:21.736146Z"},"content_sha256":"06853978dbec1c42c7c0278a463f6e480b86d6fa3e3407fbb25a638ddb87bbfe","schema_version":"1.0","event_id":"sha256:06853978dbec1c42c7c0278a463f6e480b86d6fa3e3407fbb25a638ddb87bbfe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:VJU7C2TDZT5O5HL4VDTMI2Q4D7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Large Dataset of Historical Japanese Documents with Complex Layouts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaixuan Zhang, Melissa Dell, Zejiang Shen","submitted_at":"2020-04-18T18:38:25Z","abstract_excerpt":"Deep learning-based approaches for automatic document layout analysis and content extraction have the potential to unlock rich information trapped in historical documents on a large scale. One major hurdle is the lack of large datasets for training robust models. In particular, little training data exist for Asian languages. To this end, we present HJDataset, a Large Dataset of Historical Japanese Documents with Complex Layouts. It contains over 250,000 layout element annotations of seven types. In addition to bounding boxes and masks of the content regions, it also includes the hierarchical s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.08686","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/2004.08686/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":"2026-07-05T00:56:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mwbGlpBExTexwGUVsiE9siA2pxR1JdBI34QLcEtu9WI8RRAQ5BrvbvUnqPVZ6KRYIYzj5n8NbpxPUjN4UsdPDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:44:21.736921Z"},"content_sha256":"dc67b7e5932ae305ee92e50cf9f26d1f08520e2d8af13a3c5082c2c94c11585f","schema_version":"1.0","event_id":"sha256:dc67b7e5932ae305ee92e50cf9f26d1f08520e2d8af13a3c5082c2c94c11585f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VJU7C2TDZT5O5HL4VDTMI2Q4D7/bundle.json","state_url":"https://pith.science/pith/VJU7C2TDZT5O5HL4VDTMI2Q4D7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VJU7C2TDZT5O5HL4VDTMI2Q4D7/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":"2026-08-18T20:44:21Z","links":{"resolver":"https://pith.science/pith/VJU7C2TDZT5O5HL4VDTMI2Q4D7","bundle":"https://pith.science/pith/VJU7C2TDZT5O5HL4VDTMI2Q4D7/bundle.json","state":"https://pith.science/pith/VJU7C2TDZT5O5HL4VDTMI2Q4D7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VJU7C2TDZT5O5HL4VDTMI2Q4D7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:VJU7C2TDZT5O5HL4VDTMI2Q4D7","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":"b8c47205f6b71014e69a787a0ef0efbf2250f34ae217cfcd7eb8ca5e310c7505","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-18T18:38:25Z","title_canon_sha256":"d79b9fda37de628d6f20d583d360e389166d67e34e3f459c7660c233ee034275"},"schema_version":"1.0","source":{"id":"2004.08686","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.08686","created_at":"2026-07-05T00:56:08Z"},{"alias_kind":"arxiv_version","alias_value":"2004.08686v1","created_at":"2026-07-05T00:56:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.08686","created_at":"2026-07-05T00:56:08Z"},{"alias_kind":"pith_short_12","alias_value":"VJU7C2TDZT5O","created_at":"2026-07-05T00:56:08Z"},{"alias_kind":"pith_short_16","alias_value":"VJU7C2TDZT5O5HL4","created_at":"2026-07-05T00:56:08Z"},{"alias_kind":"pith_short_8","alias_value":"VJU7C2TD","created_at":"2026-07-05T00:56:08Z"}],"graph_snapshots":[{"event_id":"sha256:dc67b7e5932ae305ee92e50cf9f26d1f08520e2d8af13a3c5082c2c94c11585f","target":"graph","created_at":"2026-07-05T00:56:08Z","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/2004.08686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning-based approaches for automatic document layout analysis and content extraction have the potential to unlock rich information trapped in historical documents on a large scale. One major hurdle is the lack of large datasets for training robust models. In particular, little training data exist for Asian languages. To this end, we present HJDataset, a Large Dataset of Historical Japanese Documents with Complex Layouts. It contains over 250,000 layout element annotations of seven types. In addition to bounding boxes and masks of the content regions, it also includes the hierarchical s","authors_text":"Kaixuan Zhang, Melissa Dell, Zejiang Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-18T18:38:25Z","title":"A Large Dataset of Historical Japanese Documents with Complex Layouts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.08686","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":"sha256:06853978dbec1c42c7c0278a463f6e480b86d6fa3e3407fbb25a638ddb87bbfe","target":"record","created_at":"2026-07-05T00:56:08Z","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":"b8c47205f6b71014e69a787a0ef0efbf2250f34ae217cfcd7eb8ca5e310c7505","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-18T18:38:25Z","title_canon_sha256":"d79b9fda37de628d6f20d583d360e389166d67e34e3f459c7660c233ee034275"},"schema_version":"1.0","source":{"id":"2004.08686","kind":"arxiv","version":1}},"canonical_sha256":"aa69f16a63ccfaee9d7ca8e6c46a1c1fef33513767e57f3cd7981870107f0e02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa69f16a63ccfaee9d7ca8e6c46a1c1fef33513767e57f3cd7981870107f0e02","first_computed_at":"2026-07-05T00:56:08.557311Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:56:08.557311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LtUvEMkDhldGQmUoFCzVvVLMuuUEU56G0dSNvwn4PfXAixkmLPpGd7FyWUZtY0L7mUkMhqI5asJOXc7HRV4ECA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:56:08.557776Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.08686","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06853978dbec1c42c7c0278a463f6e480b86d6fa3e3407fbb25a638ddb87bbfe","sha256:dc67b7e5932ae305ee92e50cf9f26d1f08520e2d8af13a3c5082c2c94c11585f"],"state_sha256":"8e7912518019f345538c44cfd48b79a9c29a0c99feed7e2d55dcc26a3a5a394e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BUBq+c+Zzh4c7aVTR0PpjY1WmSB5vJjxfJ0PJ4asjC7sR4HOSi/rcOSrEyGN4aegYDVAwa/sVSer8QakYfIFDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T20:44:21.741501Z","bundle_sha256":"94322fa486fd152352f9219a318cfdac1cb3134af96f85cdedf95233ae251afd"}}