{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MGG3E3YEWDCGEXOC5GTO6DL2EO","short_pith_number":"pith:MGG3E3YE","schema_version":"1.0","canonical_sha256":"618db26f04b0c4625dc2e9a6ef0d7a238e074f2cd99b84df9d6c4be3b1ed00fe","source":{"kind":"arxiv","id":"2101.10281","version":1},"attestation_state":"computed","paper":{"title":"PAWLS: PDF Annotation With Labels and Structure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mark Neumann, Sam Skjonsberg, Zejiang Shen","submitted_at":"2021-01-25T18:02:43Z","abstract_excerpt":"Adobe's Portable Document Format (PDF) is a popular way of distributing view-only documents with a rich visual markup. This presents a challenge to NLP practitioners who wish to use the information contained within PDF documents for training models or data analysis, because annotating these documents is difficult. In this paper, we present PDF Annotation with Labels and Structure (PAWLS), a new annotation tool designed specifically for the PDF document format. PAWLS is particularly suited for mixed-mode annotation and scenarios in which annotators require extended context to annotate accuratel"},"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":"2101.10281","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-25T18:02:43Z","cross_cats_sorted":[],"title_canon_sha256":"9280c780b8fa74e03533d31477649e9a16976a9b541958fd905645099f8c5b82","abstract_canon_sha256":"257dbc23c123db3545ab3c5eee205973032c8767eae6abeec5c03c130e504d8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:09:27.488570Z","signature_b64":"LBrPZN3bjC7Of6q46qrjDYBj4ap8gSHEWzOW/1IT5FP2+Vx4hmnRZAV4dqWer/fV/95i4f2O/+ZSG2/yrDUcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"618db26f04b0c4625dc2e9a6ef0d7a238e074f2cd99b84df9d6c4be3b1ed00fe","last_reissued_at":"2026-07-05T02:09:27.488162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:09:27.488162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAWLS: PDF Annotation With Labels and Structure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mark Neumann, Sam Skjonsberg, Zejiang Shen","submitted_at":"2021-01-25T18:02:43Z","abstract_excerpt":"Adobe's Portable Document Format (PDF) is a popular way of distributing view-only documents with a rich visual markup. This presents a challenge to NLP practitioners who wish to use the information contained within PDF documents for training models or data analysis, because annotating these documents is difficult. In this paper, we present PDF Annotation with Labels and Structure (PAWLS), a new annotation tool designed specifically for the PDF document format. PAWLS is particularly suited for mixed-mode annotation and scenarios in which annotators require extended context to annotate accuratel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.10281","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/2101.10281/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":"2101.10281","created_at":"2026-07-05T02:09:27.488224+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.10281v1","created_at":"2026-07-05T02:09:27.488224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.10281","created_at":"2026-07-05T02:09:27.488224+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGG3E3YEWDCG","created_at":"2026-07-05T02:09:27.488224+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGG3E3YEWDCGEXOC","created_at":"2026-07-05T02:09:27.488224+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGG3E3YE","created_at":"2026-07-05T02:09:27.488224+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/MGG3E3YEWDCGEXOC5GTO6DL2EO","json":"https://pith.science/pith/MGG3E3YEWDCGEXOC5GTO6DL2EO.json","graph_json":"https://pith.science/api/pith-number/MGG3E3YEWDCGEXOC5GTO6DL2EO/graph.json","events_json":"https://pith.science/api/pith-number/MGG3E3YEWDCGEXOC5GTO6DL2EO/events.json","paper":"https://pith.science/paper/MGG3E3YE"},"agent_actions":{"view_html":"https://pith.science/pith/MGG3E3YEWDCGEXOC5GTO6DL2EO","download_json":"https://pith.science/pith/MGG3E3YEWDCGEXOC5GTO6DL2EO.json","view_paper":"https://pith.science/paper/MGG3E3YE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.10281&json=true","fetch_graph":"https://pith.science/api/pith-number/MGG3E3YEWDCGEXOC5GTO6DL2EO/graph.json","fetch_events":"https://pith.science/api/pith-number/MGG3E3YEWDCGEXOC5GTO6DL2EO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGG3E3YEWDCGEXOC5GTO6DL2EO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGG3E3YEWDCGEXOC5GTO6DL2EO/action/storage_attestation","attest_author":"https://pith.science/pith/MGG3E3YEWDCGEXOC5GTO6DL2EO/action/author_attestation","sign_citation":"https://pith.science/pith/MGG3E3YEWDCGEXOC5GTO6DL2EO/action/citation_signature","submit_replication":"https://pith.science/pith/MGG3E3YEWDCGEXOC5GTO6DL2EO/action/replication_record"}},"created_at":"2026-07-05T02:09:27.488224+00:00","updated_at":"2026-07-05T02:09:27.488224+00:00"}