{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:QFYOPNTEZ3JPPQBC3YFVKCL7GQ","short_pith_number":"pith:QFYOPNTE","canonical_record":{"source":{"id":"1710.03006","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-09T09:29:55Z","cross_cats_sorted":[],"title_canon_sha256":"e7d917040362b00540efb61ccdc647c51f65a030f48df47bcd8ba82f48e9bd60","abstract_canon_sha256":"2dffd7c59e447d3df5a658af44474d18c0039e04369ef61dd98b1e25abdf6a84"},"schema_version":"1.0"},"canonical_sha256":"8170e7b664ced2f7c022de0b55097f341f8a779042662eb321752b110118a77e","source":{"kind":"arxiv","id":"1710.03006","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.03006","created_at":"2026-05-17T23:50:34Z"},{"alias_kind":"arxiv_version","alias_value":"1710.03006v3","created_at":"2026-05-17T23:50:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.03006","created_at":"2026-05-17T23:50:34Z"},{"alias_kind":"pith_short_12","alias_value":"QFYOPNTEZ3JP","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"QFYOPNTEZ3JPPQBC","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"QFYOPNTE","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:QFYOPNTEZ3JPPQBC3YFVKCL7GQ","target":"record","payload":{"canonical_record":{"source":{"id":"1710.03006","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-09T09:29:55Z","cross_cats_sorted":[],"title_canon_sha256":"e7d917040362b00540efb61ccdc647c51f65a030f48df47bcd8ba82f48e9bd60","abstract_canon_sha256":"2dffd7c59e447d3df5a658af44474d18c0039e04369ef61dd98b1e25abdf6a84"},"schema_version":"1.0"},"canonical_sha256":"8170e7b664ced2f7c022de0b55097f341f8a779042662eb321752b110118a77e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:34.354776Z","signature_b64":"VAjfNhEsDs+AhBl3W9Bb9JqEMDj1Ua0pAsIVmDNNbxZOtYM8h6XyAxA1tHCyZMT/DWoQuqSjZtxnsUjSO/RJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8170e7b664ced2f7c022de0b55097f341f8a779042662eb321752b110118a77e","last_reissued_at":"2026-05-17T23:50:34.354099Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:34.354099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.03006","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:50:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AIqFn9M9sdng0SDNZ2ZcAb5RvONQnjbkgFToq57sECUF+E0/iAQG3vjJ5sYYL0eHNVm+wBIkKgBllg828r2kBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T10:06:30.873114Z"},"content_sha256":"5b5fe302b4458458c02be4d130252ed349c3fb072d9fd91fd0aa4b37f97d2962","schema_version":"1.0","event_id":"sha256:5b5fe302b4458458c02be4d130252ed349c3fb072d9fd91fd0aa4b37f97d2962"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:QFYOPNTEZ3JPPQBC3YFVKCL7GQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Page Stream Segmentation with Convolutional Neural Nets Combining Textual and Visual Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gerhard Heyer, Gregor Wiedemann","submitted_at":"2017-10-09T09:29:55Z","abstract_excerpt":"In recent years, (retro-)digitizing paper-based files became a major undertaking for private and public archives as well as an important task in electronic mailroom applications. As a first step, the workflow involves scanning and Optical Character Recognition (OCR) of documents. Preservation of document contexts of single page scans is a major requirement in this context. To facilitate workflows involving very large amounts of paper scans, page stream segmentation (PSS) is the task to automatically separate a stream of scanned images into multi-page documents. In a digitization project togeth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.03006","kind":"arxiv","version":3},"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":"2026-05-17T23:50:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7OQdE4lIY1Hwc+cQTtnHRGITyF5vmuQt4vJab2ULriLrT8bTRaT9lquhCHmsf++/iz/EmICyQxAJNCa0UyCKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T10:06:30.873469Z"},"content_sha256":"cf59300b01679fd361c430374414600fac94f041d979156908118ae0d2ad5433","schema_version":"1.0","event_id":"sha256:cf59300b01679fd361c430374414600fac94f041d979156908118ae0d2ad5433"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QFYOPNTEZ3JPPQBC3YFVKCL7GQ/bundle.json","state_url":"https://pith.science/pith/QFYOPNTEZ3JPPQBC3YFVKCL7GQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QFYOPNTEZ3JPPQBC3YFVKCL7GQ/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":"2026-06-01T10:06:30Z","links":{"resolver":"https://pith.science/pith/QFYOPNTEZ3JPPQBC3YFVKCL7GQ","bundle":"https://pith.science/pith/QFYOPNTEZ3JPPQBC3YFVKCL7GQ/bundle.json","state":"https://pith.science/pith/QFYOPNTEZ3JPPQBC3YFVKCL7GQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QFYOPNTEZ3JPPQBC3YFVKCL7GQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:QFYOPNTEZ3JPPQBC3YFVKCL7GQ","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":"2dffd7c59e447d3df5a658af44474d18c0039e04369ef61dd98b1e25abdf6a84","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-09T09:29:55Z","title_canon_sha256":"e7d917040362b00540efb61ccdc647c51f65a030f48df47bcd8ba82f48e9bd60"},"schema_version":"1.0","source":{"id":"1710.03006","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.03006","created_at":"2026-05-17T23:50:34Z"},{"alias_kind":"arxiv_version","alias_value":"1710.03006v3","created_at":"2026-05-17T23:50:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.03006","created_at":"2026-05-17T23:50:34Z"},{"alias_kind":"pith_short_12","alias_value":"QFYOPNTEZ3JP","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"QFYOPNTEZ3JPPQBC","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"QFYOPNTE","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:cf59300b01679fd361c430374414600fac94f041d979156908118ae0d2ad5433","target":"graph","created_at":"2026-05-17T23:50:34Z","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":"In recent years, (retro-)digitizing paper-based files became a major undertaking for private and public archives as well as an important task in electronic mailroom applications. As a first step, the workflow involves scanning and Optical Character Recognition (OCR) of documents. Preservation of document contexts of single page scans is a major requirement in this context. To facilitate workflows involving very large amounts of paper scans, page stream segmentation (PSS) is the task to automatically separate a stream of scanned images into multi-page documents. In a digitization project togeth","authors_text":"Gerhard Heyer, Gregor Wiedemann","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-09T09:29:55Z","title":"Page Stream Segmentation with Convolutional Neural Nets Combining Textual and Visual Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.03006","kind":"arxiv","version":3},"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":"sha256:5b5fe302b4458458c02be4d130252ed349c3fb072d9fd91fd0aa4b37f97d2962","target":"record","created_at":"2026-05-17T23:50:34Z","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":"2dffd7c59e447d3df5a658af44474d18c0039e04369ef61dd98b1e25abdf6a84","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-09T09:29:55Z","title_canon_sha256":"e7d917040362b00540efb61ccdc647c51f65a030f48df47bcd8ba82f48e9bd60"},"schema_version":"1.0","source":{"id":"1710.03006","kind":"arxiv","version":3}},"canonical_sha256":"8170e7b664ced2f7c022de0b55097f341f8a779042662eb321752b110118a77e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8170e7b664ced2f7c022de0b55097f341f8a779042662eb321752b110118a77e","first_computed_at":"2026-05-17T23:50:34.354099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:34.354099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VAjfNhEsDs+AhBl3W9Bb9JqEMDj1Ua0pAsIVmDNNbxZOtYM8h6XyAxA1tHCyZMT/DWoQuqSjZtxnsUjSO/RJAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:34.354776Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.03006","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b5fe302b4458458c02be4d130252ed349c3fb072d9fd91fd0aa4b37f97d2962","sha256:cf59300b01679fd361c430374414600fac94f041d979156908118ae0d2ad5433"],"state_sha256":"3725e5efda13a580d8e9da0a911a8f4414807b5fcd36a453f44b84010ad7fa2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5jow+FvpyfCNEDcJ7k0JUphbAKkC+KL5Ogfo7AmmA+/CJrF/xseG1uhIH+/rj3EXTGS2+ywxMbBsUP6utaXpAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T10:06:30.875356Z","bundle_sha256":"b9217ef5541e5d08bc162024a9d17e6f09bf517812235cfbd88963361d76dec0"}}