{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XO5SOW6FOVCU3JEQ7JSNYCU3FO","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":"17382764c7af7eab321c62bf9448d22003d6fdb837a463101aac9fb812fd9b34","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-21T11:35:41Z","title_canon_sha256":"56e85b86f9bcd3b899632fd8158ea444a595254e813dfca696d71eae833de3f4"},"schema_version":"1.0","source":{"id":"2109.10104","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.10104","created_at":"2026-07-05T08:26:54Z"},{"alias_kind":"arxiv_version","alias_value":"2109.10104v2","created_at":"2026-07-05T08:26:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10104","created_at":"2026-07-05T08:26:54Z"},{"alias_kind":"pith_short_12","alias_value":"XO5SOW6FOVCU","created_at":"2026-07-05T08:26:54Z"},{"alias_kind":"pith_short_16","alias_value":"XO5SOW6FOVCU3JEQ","created_at":"2026-07-05T08:26:54Z"},{"alias_kind":"pith_short_8","alias_value":"XO5SOW6F","created_at":"2026-07-05T08:26:54Z"}],"graph_snapshots":[{"event_id":"sha256:40dd98553fc94adc73af392363690c22f20915565f783f46f0c5fd99109a566e","target":"graph","created_at":"2026-07-05T08:26:54Z","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/2109.10104/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Digital Humanities and Computational Literary Studies apply text mining methods to investigate literature. Such automated approaches enable quantitative studies on large corpora which would not be feasible by manual inspection alone. However, due to copyright restrictions, the availability of relevant digitized literary works is limited. Derived Text Formats (DTFs) have been proposed as a solution. Here, textual materials are transformed in such a way that copyright-critical features are removed, but that the use of certain analytical methods remains possible. Contextualized word embeddings pr","authors_text":"Achim Rettinger, Johannes H\\\"ohmann, Kai Kugler, Simon M\\\"unker","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-21T11:35:41Z","title":"InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10104","kind":"arxiv","version":2},"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":"sha256:3b84184deac2e0a2f7cd20bb60f596b01cb29cbe2883482d423be4341f980acb","target":"record","created_at":"2026-07-05T08:26:54Z","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":"17382764c7af7eab321c62bf9448d22003d6fdb837a463101aac9fb812fd9b34","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-21T11:35:41Z","title_canon_sha256":"56e85b86f9bcd3b899632fd8158ea444a595254e813dfca696d71eae833de3f4"},"schema_version":"1.0","source":{"id":"2109.10104","kind":"arxiv","version":2}},"canonical_sha256":"bbbb275bc575454da490fa64dc0a9b2b88245a575bceb7151256a73de4341eca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbbb275bc575454da490fa64dc0a9b2b88245a575bceb7151256a73de4341eca","first_computed_at":"2026-07-05T08:26:54.631930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:54.631930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i4N+pe/+I9QzUuD6lnt3KYYy0oWFNDhJImlHx4EkCXQYqaYR7TjpF4sL1HltBf9TrBeT/QStlemNhWo3TGbTAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:54.632471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.10104","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b84184deac2e0a2f7cd20bb60f596b01cb29cbe2883482d423be4341f980acb","sha256:40dd98553fc94adc73af392363690c22f20915565f783f46f0c5fd99109a566e"],"state_sha256":"1d93ba13d070f299c9b12136b5261c27df251e32fea458f0e0f4f47469f218e6"}