{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MGG3E3YEWDCGEXOC5GTO6DL2EO","short_pith_number":"pith:MGG3E3YE","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"},"canonical_sha256":"618db26f04b0c4625dc2e9a6ef0d7a238e074f2cd99b84df9d6c4be3b1ed00fe","source":{"kind":"arxiv","id":"2101.10281","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.10281","created_at":"2026-07-05T02:09:27Z"},{"alias_kind":"arxiv_version","alias_value":"2101.10281v1","created_at":"2026-07-05T02:09:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.10281","created_at":"2026-07-05T02:09:27Z"},{"alias_kind":"pith_short_12","alias_value":"MGG3E3YEWDCG","created_at":"2026-07-05T02:09:27Z"},{"alias_kind":"pith_short_16","alias_value":"MGG3E3YEWDCGEXOC","created_at":"2026-07-05T02:09:27Z"},{"alias_kind":"pith_short_8","alias_value":"MGG3E3YE","created_at":"2026-07-05T02:09:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MGG3E3YEWDCGEXOC5GTO6DL2EO","target":"record","payload":{"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"},"canonical_sha256":"618db26f04b0c4625dc2e9a6ef0d7a238e074f2cd99b84df9d6c4be3b1ed00fe","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"},"source_kind":"arxiv","source_id":"2101.10281","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":"2026-07-05T02:09:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tV3a1S3HaKJGIJ2VSANr9yHokvM/L+A6HbdEZptrqwHiZmCQb42P9jUIcPjfVrm1cHAIWSIO8i0XHgZBpIxoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:32:21.784846Z"},"content_sha256":"cca690ce5a9ee801979ac0f9141d4c80be7fd3e310f74901739f629f4bec4d75","schema_version":"1.0","event_id":"sha256:cca690ce5a9ee801979ac0f9141d4c80be7fd3e310f74901739f629f4bec4d75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MGG3E3YEWDCGEXOC5GTO6DL2EO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:09:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cumy/Z6gyfUbCe0UXRcZkeNMQBn5vMXC6hFuuN6fo/m15Sj3/NyxsvOtow3GTxce5HGsR6kXpuAQVLKvO0zsCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:32:21.785235Z"},"content_sha256":"0faa33909f9711ffa7beee89b1b9bb56d8f7feda8177d3eea0342b901443d558","schema_version":"1.0","event_id":"sha256:0faa33909f9711ffa7beee89b1b9bb56d8f7feda8177d3eea0342b901443d558"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MGG3E3YEWDCGEXOC5GTO6DL2EO/bundle.json","state_url":"https://pith.science/pith/MGG3E3YEWDCGEXOC5GTO6DL2EO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MGG3E3YEWDCGEXOC5GTO6DL2EO/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":"2026-07-09T04:32:21Z","links":{"resolver":"https://pith.science/pith/MGG3E3YEWDCGEXOC5GTO6DL2EO","bundle":"https://pith.science/pith/MGG3E3YEWDCGEXOC5GTO6DL2EO/bundle.json","state":"https://pith.science/pith/MGG3E3YEWDCGEXOC5GTO6DL2EO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MGG3E3YEWDCGEXOC5GTO6DL2EO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MGG3E3YEWDCGEXOC5GTO6DL2EO","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":"257dbc23c123db3545ab3c5eee205973032c8767eae6abeec5c03c130e504d8c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-25T18:02:43Z","title_canon_sha256":"9280c780b8fa74e03533d31477649e9a16976a9b541958fd905645099f8c5b82"},"schema_version":"1.0","source":{"id":"2101.10281","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.10281","created_at":"2026-07-05T02:09:27Z"},{"alias_kind":"arxiv_version","alias_value":"2101.10281v1","created_at":"2026-07-05T02:09:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.10281","created_at":"2026-07-05T02:09:27Z"},{"alias_kind":"pith_short_12","alias_value":"MGG3E3YEWDCG","created_at":"2026-07-05T02:09:27Z"},{"alias_kind":"pith_short_16","alias_value":"MGG3E3YEWDCGEXOC","created_at":"2026-07-05T02:09:27Z"},{"alias_kind":"pith_short_8","alias_value":"MGG3E3YE","created_at":"2026-07-05T02:09:27Z"}],"graph_snapshots":[{"event_id":"sha256:0faa33909f9711ffa7beee89b1b9bb56d8f7feda8177d3eea0342b901443d558","target":"graph","created_at":"2026-07-05T02:09:27Z","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/2101.10281/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Mark Neumann, Sam Skjonsberg, Zejiang Shen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-25T18:02:43Z","title":"PAWLS: PDF Annotation With Labels and Structure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.10281","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:cca690ce5a9ee801979ac0f9141d4c80be7fd3e310f74901739f629f4bec4d75","target":"record","created_at":"2026-07-05T02:09:27Z","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":"257dbc23c123db3545ab3c5eee205973032c8767eae6abeec5c03c130e504d8c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-25T18:02:43Z","title_canon_sha256":"9280c780b8fa74e03533d31477649e9a16976a9b541958fd905645099f8c5b82"},"schema_version":"1.0","source":{"id":"2101.10281","kind":"arxiv","version":1}},"canonical_sha256":"618db26f04b0c4625dc2e9a6ef0d7a238e074f2cd99b84df9d6c4be3b1ed00fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"618db26f04b0c4625dc2e9a6ef0d7a238e074f2cd99b84df9d6c4be3b1ed00fe","first_computed_at":"2026-07-05T02:09:27.488162Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:09:27.488162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LBrPZN3bjC7Of6q46qrjDYBj4ap8gSHEWzOW/1IT5FP2+Vx4hmnRZAV4dqWer/fV/95i4f2O/+ZSG2/yrDUcAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:09:27.488570Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.10281","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cca690ce5a9ee801979ac0f9141d4c80be7fd3e310f74901739f629f4bec4d75","sha256:0faa33909f9711ffa7beee89b1b9bb56d8f7feda8177d3eea0342b901443d558"],"state_sha256":"2510385c44388b2c8c9033dad538673a54a673e4bef8b6a5bb059d76d5cdd23a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XFmkyZCq0E+652x6keu+kc/YvH2WPGCNQPnfqhShrvKWfO71g63o3pNU0SsR+Y5LJAlgyvJwAlNxvMifzb20DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T04:32:21.787156Z","bundle_sha256":"56f91fb5aaf0eebc26bca0bb9005bff9965aea2ba8f87b0f0ca9d58901016151"}}