{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BJHCYKRGCWDKQLHZIPMAF4P7NP","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":"f5233cca0ff4ed2473836d402a3b87d8f4400f23e5a2c79ea36c534aa532c01c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2017-11-13T17:05:36Z","title_canon_sha256":"4c3ef2a7db3fa074efec7d9de679a355dbab14ed366f745d4eb99de83b34b7c3"},"schema_version":"1.0","source":{"id":"1711.04705","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.04705","created_at":"2026-05-18T00:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"1711.04705v1","created_at":"2026-05-18T00:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04705","created_at":"2026-05-18T00:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"BJHCYKRGCWDK","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BJHCYKRGCWDKQLHZ","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BJHCYKRG","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:ccf66a2de0eb5b3a7c66292604a264c83e5511cedd2333e28910830135b160e9","target":"graph","created_at":"2026-05-18T00:03:49Z","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"},"paper":{"abstract_excerpt":"Contemporary software documentation is as complicated as the software itself. During its lifecycle, the documentation accumulates a lot of near duplicate fragments, i.e. chunks of text that were copied from a single source and were later modified in different ways. Such near duplicates decrease documentation quality and thus hamper its further utilization. At the same time, they are hard to detect manually due to their fuzzy nature. In this paper we give a formal definition of near duplicates and present an algorithm for their detection in software documents. This algorithm is based on the exa","authors_text":"A.N. Terekhov, D.V. Koznov, D.V. Luciv, G.A. Chernishev","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2017-11-13T17:05:36Z","title":"Detecting Near Duplicates in Software Documentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04705","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":"sha256:61c4de70e70b1f162fd2d2e5e66601444ff3f250512a242bcaa3aeff4b526a0e","target":"record","created_at":"2026-05-18T00:03:49Z","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":"f5233cca0ff4ed2473836d402a3b87d8f4400f23e5a2c79ea36c534aa532c01c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2017-11-13T17:05:36Z","title_canon_sha256":"4c3ef2a7db3fa074efec7d9de679a355dbab14ed366f745d4eb99de83b34b7c3"},"schema_version":"1.0","source":{"id":"1711.04705","kind":"arxiv","version":1}},"canonical_sha256":"0a4e2c2a261586a82cf943d802f1ff6bc57fc5eaa004e9fc5c67ac9d3c85bd6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a4e2c2a261586a82cf943d802f1ff6bc57fc5eaa004e9fc5c67ac9d3c85bd6b","first_computed_at":"2026-05-18T00:03:49.917310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:49.917310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ViJDhn3cN604tHXifzvUs/XUyhaZX10tLUQvSWHU7COuD1Y8JDgql7MA/Wbs8U8d6r4oaQThm22e8DpklR3eDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:49.917960Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.04705","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61c4de70e70b1f162fd2d2e5e66601444ff3f250512a242bcaa3aeff4b526a0e","sha256:ccf66a2de0eb5b3a7c66292604a264c83e5511cedd2333e28910830135b160e9"],"state_sha256":"acea9ef5ede26cb4bbf292eca8d13cd9dc77b73a50b5a3591498388fede06022"}