{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QFYOPNTEZ3JPPQBC3YFVKCL7GQ","short_pith_number":"pith:QFYOPNTE","schema_version":"1.0","canonical_sha256":"8170e7b664ced2f7c022de0b55097f341f8a779042662eb321752b110118a77e","source":{"kind":"arxiv","id":"1710.03006","version":3},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1710.03006","created_at":"2026-05-17T23:50:34.354202+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.03006v3","created_at":"2026-05-17T23:50:34.354202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.03006","created_at":"2026-05-17T23:50:34.354202+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFYOPNTEZ3JP","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFYOPNTEZ3JPPQBC","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFYOPNTE","created_at":"2026-05-18T12:31:37.085036+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/QFYOPNTEZ3JPPQBC3YFVKCL7GQ","json":"https://pith.science/pith/QFYOPNTEZ3JPPQBC3YFVKCL7GQ.json","graph_json":"https://pith.science/api/pith-number/QFYOPNTEZ3JPPQBC3YFVKCL7GQ/graph.json","events_json":"https://pith.science/api/pith-number/QFYOPNTEZ3JPPQBC3YFVKCL7GQ/events.json","paper":"https://pith.science/paper/QFYOPNTE"},"agent_actions":{"view_html":"https://pith.science/pith/QFYOPNTEZ3JPPQBC3YFVKCL7GQ","download_json":"https://pith.science/pith/QFYOPNTEZ3JPPQBC3YFVKCL7GQ.json","view_paper":"https://pith.science/paper/QFYOPNTE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.03006&json=true","fetch_graph":"https://pith.science/api/pith-number/QFYOPNTEZ3JPPQBC3YFVKCL7GQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QFYOPNTEZ3JPPQBC3YFVKCL7GQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFYOPNTEZ3JPPQBC3YFVKCL7GQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFYOPNTEZ3JPPQBC3YFVKCL7GQ/action/storage_attestation","attest_author":"https://pith.science/pith/QFYOPNTEZ3JPPQBC3YFVKCL7GQ/action/author_attestation","sign_citation":"https://pith.science/pith/QFYOPNTEZ3JPPQBC3YFVKCL7GQ/action/citation_signature","submit_replication":"https://pith.science/pith/QFYOPNTEZ3JPPQBC3YFVKCL7GQ/action/replication_record"}},"created_at":"2026-05-17T23:50:34.354202+00:00","updated_at":"2026-05-17T23:50:34.354202+00:00"}