{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TRIQMZGBVGA6VC5ZBQDE5HNP6W","short_pith_number":"pith:TRIQMZGB","canonical_record":{"source":{"id":"2205.00716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-02T08:11:32Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"71d4a00c2564b8571218dc97b23789845da7d464ab77a57458178b309807b219","abstract_canon_sha256":"4494f031e3cd38b74ab689da594a02a47d7c1bff2030a0738afbd8ec7e0f335b"},"schema_version":"1.0"},"canonical_sha256":"9c510664c1a981ea8bb90c064e9daff5a95efe57985fe333374dc47b0014fa9e","source":{"kind":"arxiv","id":"2205.00716","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.00716","created_at":"2026-07-05T04:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"2205.00716v1","created_at":"2026-07-05T04:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.00716","created_at":"2026-07-05T04:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"TRIQMZGBVGA6","created_at":"2026-07-05T04:19:15Z"},{"alias_kind":"pith_short_16","alias_value":"TRIQMZGBVGA6VC5Z","created_at":"2026-07-05T04:19:15Z"},{"alias_kind":"pith_short_8","alias_value":"TRIQMZGB","created_at":"2026-07-05T04:19:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TRIQMZGBVGA6VC5ZBQDE5HNP6W","target":"record","payload":{"canonical_record":{"source":{"id":"2205.00716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-02T08:11:32Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"71d4a00c2564b8571218dc97b23789845da7d464ab77a57458178b309807b219","abstract_canon_sha256":"4494f031e3cd38b74ab689da594a02a47d7c1bff2030a0738afbd8ec7e0f335b"},"schema_version":"1.0"},"canonical_sha256":"9c510664c1a981ea8bb90c064e9daff5a95efe57985fe333374dc47b0014fa9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:15.872196Z","signature_b64":"ioUzNi5kXLv2sG2jO3tDmRproZmI/E4tkKhKRdUz/De8hKltNoaNNOoLgKawjof3/vJ/4D8S9+Vfm0LY/c1eCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c510664c1a981ea8bb90c064e9daff5a95efe57985fe333374dc47b0014fa9e","last_reissued_at":"2026-07-05T04:19:15.871710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:15.871710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.00716","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":"2026-07-05T04:19:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gpnSetTh/QPv6vabKCkYs3O8q/Z8JIHhvcFkokHeJvycG8ehipQalOTg7hZuMg5yU4bFxhO6qP4w0KVLLYunDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T03:25:24.418182Z"},"content_sha256":"792b15c5cd9a3a976c460c31e413202bdf5b24926a4ba9be0e110fe87d78087a","schema_version":"1.0","event_id":"sha256:792b15c5cd9a3a976c460c31e413202bdf5b24926a4ba9be0e110fe87d78087a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TRIQMZGBVGA6VC5ZBQDE5HNP6W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Library Perspective on Nearly-Unsupervised Information Extraction Workflows in Digital Libraries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.CL","authors_text":"Florian Pl\\\"otzky, Hermann Kroll, Jan Pirklbauer, Wolf-Tilo Balke","submitted_at":"2022-05-02T08:11:32Z","abstract_excerpt":"Information extraction can support novel and effective access paths for digital libraries. Nevertheless, designing reliable extraction workflows can be cost-intensive in practice. On the one hand, suitable extraction methods rely on domain-specific training data. On the other hand, unsupervised and open extraction methods usually produce not-canonicalized extraction results. This paper tackles the question how digital libraries can handle such extractions and if their quality is sufficient in practice. We focus on unsupervised extraction workflows by analyzing them in case studies in the domai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.00716","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/2205.00716/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":"2026-07-05T04:19:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0oQ0w16JbevdAwTpP383sQlIkPt4cg9Lor0ziMHfrrJWr8z2QRAT62ShyXirzbqhQBC8Wq4t0LicYO12VMb7Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T03:25:24.418957Z"},"content_sha256":"f3b95c26c0008f94cdac50b63b2e96321b0d074cef91e677c0afaa0b889ae478","schema_version":"1.0","event_id":"sha256:f3b95c26c0008f94cdac50b63b2e96321b0d074cef91e677c0afaa0b889ae478"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TRIQMZGBVGA6VC5ZBQDE5HNP6W/bundle.json","state_url":"https://pith.science/pith/TRIQMZGBVGA6VC5ZBQDE5HNP6W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TRIQMZGBVGA6VC5ZBQDE5HNP6W/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":"2026-08-24T03:25:24Z","links":{"resolver":"https://pith.science/pith/TRIQMZGBVGA6VC5ZBQDE5HNP6W","bundle":"https://pith.science/pith/TRIQMZGBVGA6VC5ZBQDE5HNP6W/bundle.json","state":"https://pith.science/pith/TRIQMZGBVGA6VC5ZBQDE5HNP6W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TRIQMZGBVGA6VC5ZBQDE5HNP6W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TRIQMZGBVGA6VC5ZBQDE5HNP6W","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":"4494f031e3cd38b74ab689da594a02a47d7c1bff2030a0738afbd8ec7e0f335b","cross_cats_sorted":["cs.DL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-02T08:11:32Z","title_canon_sha256":"71d4a00c2564b8571218dc97b23789845da7d464ab77a57458178b309807b219"},"schema_version":"1.0","source":{"id":"2205.00716","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.00716","created_at":"2026-07-05T04:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"2205.00716v1","created_at":"2026-07-05T04:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.00716","created_at":"2026-07-05T04:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"TRIQMZGBVGA6","created_at":"2026-07-05T04:19:15Z"},{"alias_kind":"pith_short_16","alias_value":"TRIQMZGBVGA6VC5Z","created_at":"2026-07-05T04:19:15Z"},{"alias_kind":"pith_short_8","alias_value":"TRIQMZGB","created_at":"2026-07-05T04:19:15Z"}],"graph_snapshots":[{"event_id":"sha256:f3b95c26c0008f94cdac50b63b2e96321b0d074cef91e677c0afaa0b889ae478","target":"graph","created_at":"2026-07-05T04:19:15Z","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/2205.00716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Information extraction can support novel and effective access paths for digital libraries. Nevertheless, designing reliable extraction workflows can be cost-intensive in practice. On the one hand, suitable extraction methods rely on domain-specific training data. On the other hand, unsupervised and open extraction methods usually produce not-canonicalized extraction results. This paper tackles the question how digital libraries can handle such extractions and if their quality is sufficient in practice. We focus on unsupervised extraction workflows by analyzing them in case studies in the domai","authors_text":"Florian Pl\\\"otzky, Hermann Kroll, Jan Pirklbauer, Wolf-Tilo Balke","cross_cats":["cs.DL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-02T08:11:32Z","title":"A Library Perspective on Nearly-Unsupervised Information Extraction Workflows in Digital Libraries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.00716","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":"sha256:792b15c5cd9a3a976c460c31e413202bdf5b24926a4ba9be0e110fe87d78087a","target":"record","created_at":"2026-07-05T04:19:15Z","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":"4494f031e3cd38b74ab689da594a02a47d7c1bff2030a0738afbd8ec7e0f335b","cross_cats_sorted":["cs.DL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-02T08:11:32Z","title_canon_sha256":"71d4a00c2564b8571218dc97b23789845da7d464ab77a57458178b309807b219"},"schema_version":"1.0","source":{"id":"2205.00716","kind":"arxiv","version":1}},"canonical_sha256":"9c510664c1a981ea8bb90c064e9daff5a95efe57985fe333374dc47b0014fa9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c510664c1a981ea8bb90c064e9daff5a95efe57985fe333374dc47b0014fa9e","first_computed_at":"2026-07-05T04:19:15.871710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:19:15.871710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ioUzNi5kXLv2sG2jO3tDmRproZmI/E4tkKhKRdUz/De8hKltNoaNNOoLgKawjof3/vJ/4D8S9+Vfm0LY/c1eCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:19:15.872196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.00716","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:792b15c5cd9a3a976c460c31e413202bdf5b24926a4ba9be0e110fe87d78087a","sha256:f3b95c26c0008f94cdac50b63b2e96321b0d074cef91e677c0afaa0b889ae478"],"state_sha256":"ed0a021353a64b4b40cba77366e4a36d04c6b38f832ff69da3630bcc3b496441"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SDsZMw8hN3JyPD+FGNMyMUfUlc48lKe3yj4zvHPcdGVetn3BrX9PlInqesLk77eZrElp64mCm9efPBhe2DiuDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T03:25:24.425425Z","bundle_sha256":"3835af9bd28fc43346437af19bc7f6fd12bf49227fd8dd852444cbce6b5f7842"}}