{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:X6WA5JJIMKVJ3WVMPS6JKSHVWN","short_pith_number":"pith:X6WA5JJI","schema_version":"1.0","canonical_sha256":"bfac0ea52862aa9ddaac7cbc9548f5b375d91127eb0aa37a583ef0cb711da20e","source":{"kind":"arxiv","id":"2108.01454","version":2},"attestation_state":"computed","paper":{"title":"Inscriptis -- A Python-based HTML to text conversion library optimized for knowledge extraction from the Web","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Albert Weichselbraun","submitted_at":"2021-07-12T12:40:43Z","abstract_excerpt":"Inscriptis provides a library, command line client and Web service for converting HTML to plain text. Its development has been triggered by the need to obtain accurate text representations for knowledge extraction tasks that preserve the spatial alignment of text without drawing upon heavyweight, browser-based solutions such as Selenium. In contrast to related software packages, Inscriptis (i) provides a layout-aware conversion of HTML that more closely resembles the rendering obtained from standard Web browsers; and (ii) supports annotation rules, i.e., user-provided mappings that allow for a"},"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":"2108.01454","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2021-07-12T12:40:43Z","cross_cats_sorted":[],"title_canon_sha256":"79f3550f2a3d430c04ca033eaabe3684500271d702ef7bc539016c69145158db","abstract_canon_sha256":"ad97ece5d69a864e5a56100e54987f5a732a623349bdbaa2739ec19caee8dcf5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:44.638617Z","signature_b64":"wpN3trDrSW54SEpDYUswGdiZG9gw0VQkKTwU9Q2BZ/CZ2il+ozftaqsVx68erBdq1zR+AwfphRLV+oTq+BlgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfac0ea52862aa9ddaac7cbc9548f5b375d91127eb0aa37a583ef0cb711da20e","last_reissued_at":"2026-07-05T03:24:44.638066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:44.638066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inscriptis -- A Python-based HTML to text conversion library optimized for knowledge extraction from the Web","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Albert Weichselbraun","submitted_at":"2021-07-12T12:40:43Z","abstract_excerpt":"Inscriptis provides a library, command line client and Web service for converting HTML to plain text. Its development has been triggered by the need to obtain accurate text representations for knowledge extraction tasks that preserve the spatial alignment of text without drawing upon heavyweight, browser-based solutions such as Selenium. In contrast to related software packages, Inscriptis (i) provides a layout-aware conversion of HTML that more closely resembles the rendering obtained from standard Web browsers; and (ii) supports annotation rules, i.e., user-provided mappings that allow for a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01454","kind":"arxiv","version":2},"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/2108.01454/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2108.01454","created_at":"2026-07-05T03:24:44.638142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.01454v2","created_at":"2026-07-05T03:24:44.638142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01454","created_at":"2026-07-05T03:24:44.638142+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6WA5JJIMKVJ","created_at":"2026-07-05T03:24:44.638142+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6WA5JJIMKVJ3WVM","created_at":"2026-07-05T03:24:44.638142+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6WA5JJI","created_at":"2026-07-05T03:24:44.638142+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/X6WA5JJIMKVJ3WVMPS6JKSHVWN","json":"https://pith.science/pith/X6WA5JJIMKVJ3WVMPS6JKSHVWN.json","graph_json":"https://pith.science/api/pith-number/X6WA5JJIMKVJ3WVMPS6JKSHVWN/graph.json","events_json":"https://pith.science/api/pith-number/X6WA5JJIMKVJ3WVMPS6JKSHVWN/events.json","paper":"https://pith.science/paper/X6WA5JJI"},"agent_actions":{"view_html":"https://pith.science/pith/X6WA5JJIMKVJ3WVMPS6JKSHVWN","download_json":"https://pith.science/pith/X6WA5JJIMKVJ3WVMPS6JKSHVWN.json","view_paper":"https://pith.science/paper/X6WA5JJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.01454&json=true","fetch_graph":"https://pith.science/api/pith-number/X6WA5JJIMKVJ3WVMPS6JKSHVWN/graph.json","fetch_events":"https://pith.science/api/pith-number/X6WA5JJIMKVJ3WVMPS6JKSHVWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6WA5JJIMKVJ3WVMPS6JKSHVWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6WA5JJIMKVJ3WVMPS6JKSHVWN/action/storage_attestation","attest_author":"https://pith.science/pith/X6WA5JJIMKVJ3WVMPS6JKSHVWN/action/author_attestation","sign_citation":"https://pith.science/pith/X6WA5JJIMKVJ3WVMPS6JKSHVWN/action/citation_signature","submit_replication":"https://pith.science/pith/X6WA5JJIMKVJ3WVMPS6JKSHVWN/action/replication_record"}},"created_at":"2026-07-05T03:24:44.638142+00:00","updated_at":"2026-07-05T03:24:44.638142+00:00"}