{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZYJ2NQTVJMH45G66HO54L5BOL4","short_pith_number":"pith:ZYJ2NQTV","canonical_record":{"source":{"id":"2112.11800","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2021-12-22T11:15:49Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"620ba3bc7b03d5f90c8d1c933b417b88e49c1b897750e014a8e0abec5f0a52a8","abstract_canon_sha256":"07226704b2bd7931124e83def43ae2cb46eed6811402320c2f2b741c900fff8c"},"schema_version":"1.0"},"canonical_sha256":"ce13a6c2754b0fce9bde3bbbc5f42e5f37d810034484a62c196097198bdc651c","source":{"kind":"arxiv","id":"2112.11800","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.11800","created_at":"2026-07-05T05:25:13Z"},{"alias_kind":"arxiv_version","alias_value":"2112.11800v3","created_at":"2026-07-05T05:25:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11800","created_at":"2026-07-05T05:25:13Z"},{"alias_kind":"pith_short_12","alias_value":"ZYJ2NQTVJMH4","created_at":"2026-07-05T05:25:13Z"},{"alias_kind":"pith_short_16","alias_value":"ZYJ2NQTVJMH45G66","created_at":"2026-07-05T05:25:13Z"},{"alias_kind":"pith_short_8","alias_value":"ZYJ2NQTV","created_at":"2026-07-05T05:25:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZYJ2NQTVJMH45G66HO54L5BOL4","target":"record","payload":{"canonical_record":{"source":{"id":"2112.11800","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2021-12-22T11:15:49Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"620ba3bc7b03d5f90c8d1c933b417b88e49c1b897750e014a8e0abec5f0a52a8","abstract_canon_sha256":"07226704b2bd7931124e83def43ae2cb46eed6811402320c2f2b741c900fff8c"},"schema_version":"1.0"},"canonical_sha256":"ce13a6c2754b0fce9bde3bbbc5f42e5f37d810034484a62c196097198bdc651c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:13.453347Z","signature_b64":"jpobrJf59rgf8nqD778XhJ2vdZKbpHypS7ZR/Wn36ex26ChWeu0PfIiLxD1Un31EndfT/1I3d/MPUb3z8FqxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce13a6c2754b0fce9bde3bbbc5f42e5f37d810034484a62c196097198bdc651c","last_reissued_at":"2026-07-05T05:25:13.452880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:13.452880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.11800","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:25:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uc00aWgI1cPQMp3e4zBk5ggskE4gWFofYHH7/+b+q7Gt/MN5WC3Q86W3/SS8K6q+zUHPaj8bXUDiOdiwfvYVBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:59:01.920045Z"},"content_sha256":"5fabb81b06a798b7a0d534cb27f2998a2498f25247fbcd9effdff352511185d7","schema_version":"1.0","event_id":"sha256:5fabb81b06a798b7a0d534cb27f2998a2498f25247fbcd9effdff352511185d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZYJ2NQTVJMH45G66HO54L5BOL4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"STEREO: Scientific Text Reuse in Open Access Publications","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.DL","authors_text":"Benno Stein, Bjarne Sievers, Lukas Gienapp, Martin Potthast, Wolfgang Kircheis","submitted_at":"2021-12-22T11:15:49Z","abstract_excerpt":"We present the Webis-STEREO-21 dataset, a massive collection of Scientific Text Reuse in Open-access publications. It contains more than 91 million cases of reused text passages found in 4.2 million unique open-access publications. Featuring a high coverage of scientific disciplines and varieties of reuse, as well as comprehensive metadata to contextualize each case, our dataset addresses the most salient shortcomings of previous ones on scientific writing. Webis-STEREO-21 allows for tackling a wide range of research questions from different scientific backgrounds, facilitating both qualitativ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11800","kind":"arxiv","version":3},"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/2112.11800/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":"2026-07-05T05:25:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fu0fU7ULHrV+FK+pOxb3T5vFP4fcbxxV82JGB2CnaAY/2IUp3aYSMTyl+8pFFxOk750CQgbvq1SQbxaNqd/WAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:59:01.920750Z"},"content_sha256":"12fab89dd8b5ede98cc1bccb7d545a614da3289dcab11a5a4bb4d02ce8199c84","schema_version":"1.0","event_id":"sha256:12fab89dd8b5ede98cc1bccb7d545a614da3289dcab11a5a4bb4d02ce8199c84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZYJ2NQTVJMH45G66HO54L5BOL4/bundle.json","state_url":"https://pith.science/pith/ZYJ2NQTVJMH45G66HO54L5BOL4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZYJ2NQTVJMH45G66HO54L5BOL4/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":"2026-08-09T00:59:01Z","links":{"resolver":"https://pith.science/pith/ZYJ2NQTVJMH45G66HO54L5BOL4","bundle":"https://pith.science/pith/ZYJ2NQTVJMH45G66HO54L5BOL4/bundle.json","state":"https://pith.science/pith/ZYJ2NQTVJMH45G66HO54L5BOL4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZYJ2NQTVJMH45G66HO54L5BOL4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZYJ2NQTVJMH45G66HO54L5BOL4","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":"07226704b2bd7931124e83def43ae2cb46eed6811402320c2f2b741c900fff8c","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2021-12-22T11:15:49Z","title_canon_sha256":"620ba3bc7b03d5f90c8d1c933b417b88e49c1b897750e014a8e0abec5f0a52a8"},"schema_version":"1.0","source":{"id":"2112.11800","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.11800","created_at":"2026-07-05T05:25:13Z"},{"alias_kind":"arxiv_version","alias_value":"2112.11800v3","created_at":"2026-07-05T05:25:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11800","created_at":"2026-07-05T05:25:13Z"},{"alias_kind":"pith_short_12","alias_value":"ZYJ2NQTVJMH4","created_at":"2026-07-05T05:25:13Z"},{"alias_kind":"pith_short_16","alias_value":"ZYJ2NQTVJMH45G66","created_at":"2026-07-05T05:25:13Z"},{"alias_kind":"pith_short_8","alias_value":"ZYJ2NQTV","created_at":"2026-07-05T05:25:13Z"}],"graph_snapshots":[{"event_id":"sha256:12fab89dd8b5ede98cc1bccb7d545a614da3289dcab11a5a4bb4d02ce8199c84","target":"graph","created_at":"2026-07-05T05:25:13Z","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/2112.11800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the Webis-STEREO-21 dataset, a massive collection of Scientific Text Reuse in Open-access publications. It contains more than 91 million cases of reused text passages found in 4.2 million unique open-access publications. Featuring a high coverage of scientific disciplines and varieties of reuse, as well as comprehensive metadata to contextualize each case, our dataset addresses the most salient shortcomings of previous ones on scientific writing. Webis-STEREO-21 allows for tackling a wide range of research questions from different scientific backgrounds, facilitating both qualitativ","authors_text":"Benno Stein, Bjarne Sievers, Lukas Gienapp, Martin Potthast, Wolfgang Kircheis","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2021-12-22T11:15:49Z","title":"STEREO: Scientific Text Reuse in Open Access Publications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11800","kind":"arxiv","version":3},"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":"sha256:5fabb81b06a798b7a0d534cb27f2998a2498f25247fbcd9effdff352511185d7","target":"record","created_at":"2026-07-05T05:25:13Z","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":"07226704b2bd7931124e83def43ae2cb46eed6811402320c2f2b741c900fff8c","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2021-12-22T11:15:49Z","title_canon_sha256":"620ba3bc7b03d5f90c8d1c933b417b88e49c1b897750e014a8e0abec5f0a52a8"},"schema_version":"1.0","source":{"id":"2112.11800","kind":"arxiv","version":3}},"canonical_sha256":"ce13a6c2754b0fce9bde3bbbc5f42e5f37d810034484a62c196097198bdc651c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce13a6c2754b0fce9bde3bbbc5f42e5f37d810034484a62c196097198bdc651c","first_computed_at":"2026-07-05T05:25:13.452880Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:25:13.452880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jpobrJf59rgf8nqD778XhJ2vdZKbpHypS7ZR/Wn36ex26ChWeu0PfIiLxD1Un31EndfT/1I3d/MPUb3z8FqxCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:25:13.453347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.11800","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fabb81b06a798b7a0d534cb27f2998a2498f25247fbcd9effdff352511185d7","sha256:12fab89dd8b5ede98cc1bccb7d545a614da3289dcab11a5a4bb4d02ce8199c84"],"state_sha256":"66a70339d81d700e4757c1c3b4a4991bfa1e48c21b529e5f1dfe0a970aeb3b42"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xoflcTk4gpLA/Tgloi60svRzflqytTexKpu0m4Bb8/R0J2T9xp/EIFktEdmfW6/LRvBnbN38KiK4lnfBszNGAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:59:01.925617Z","bundle_sha256":"b8d7f92df43f12eb5a8d0a257abae540faa6062f5b7684a3da7748cea57a2f5d"}}