{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PZEPOH6SFPICMXPSYI424K7XPT","short_pith_number":"pith:PZEPOH6S","canonical_record":{"source":{"id":"2110.00735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-02T06:19:14Z","cross_cats_sorted":["cs.CY","cs.IT","cs.SE","math.IT"],"title_canon_sha256":"21eb2d627528cb1e95fbdbf9acf286f6e7d1d47858fad2eca30745a4f7e4280c","abstract_canon_sha256":"9f866a38a347f4f17249bd66645063c6f81c2bcc5bcda20d076f993e3826f376"},"schema_version":"1.0"},"canonical_sha256":"7e48f71fd22bd0265df2c239ae2bf77ce9cbc53feb07aae6f215b3d3855fe101","source":{"kind":"arxiv","id":"2110.00735","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.00735","created_at":"2026-07-05T04:21:06Z"},{"alias_kind":"arxiv_version","alias_value":"2110.00735v1","created_at":"2026-07-05T04:21:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00735","created_at":"2026-07-05T04:21:06Z"},{"alias_kind":"pith_short_12","alias_value":"PZEPOH6SFPIC","created_at":"2026-07-05T04:21:06Z"},{"alias_kind":"pith_short_16","alias_value":"PZEPOH6SFPICMXPS","created_at":"2026-07-05T04:21:06Z"},{"alias_kind":"pith_short_8","alias_value":"PZEPOH6S","created_at":"2026-07-05T04:21:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PZEPOH6SFPICMXPSYI424K7XPT","target":"record","payload":{"canonical_record":{"source":{"id":"2110.00735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-02T06:19:14Z","cross_cats_sorted":["cs.CY","cs.IT","cs.SE","math.IT"],"title_canon_sha256":"21eb2d627528cb1e95fbdbf9acf286f6e7d1d47858fad2eca30745a4f7e4280c","abstract_canon_sha256":"9f866a38a347f4f17249bd66645063c6f81c2bcc5bcda20d076f993e3826f376"},"schema_version":"1.0"},"canonical_sha256":"7e48f71fd22bd0265df2c239ae2bf77ce9cbc53feb07aae6f215b3d3855fe101","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:06.184694Z","signature_b64":"4q6TV9zySxpSA8rnjVrlKVNCwZ/xZ6oy5pNo6Oo7ZuWb2k2MfMUE9btrsQv3dczCW+CWRGC03l/0a2O7yTd2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e48f71fd22bd0265df2c239ae2bf77ce9cbc53feb07aae6f215b3d3855fe101","last_reissued_at":"2026-07-05T04:21:06.184270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:06.184270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.00735","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":"2026-07-05T04:21:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QCCkf2hLGjdrBpGqJRgs+SIJ4GdrKnbOYxc5XTJ0SMrdFyKj2YsT/HEhgJxPnQ81vhx/ikY81qgcXhL0+ShJBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:26:38.337259Z"},"content_sha256":"e94963c77343bad1125eb2e67817cb2b425ad8fc45b48b0ea614a09e5d9f84eb","schema_version":"1.0","event_id":"sha256:e94963c77343bad1125eb2e67817cb2b425ad8fc45b48b0ea614a09e5d9f84eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PZEPOH6SFPICMXPSYI424K7XPT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Simplify Your Law: Using Information Theory to Deduplicate Legal Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.IT","cs.SE","math.IT"],"primary_cat":"cs.CL","authors_text":"Corinna Coupette, Holger Spamann, Jyotsna Singh","submitted_at":"2021-10-02T06:19:14Z","abstract_excerpt":"Textual redundancy is one of the main challenges to ensuring that legal texts remain comprehensible and maintainable. Drawing inspiration from the refactoring literature in software engineering, which has developed methods to expose and eliminate duplicated code, we introduce the duplicated phrase detection problem for legal texts and propose the Dupex algorithm to solve it. Leveraging the Minimum Description Length principle from information theory, Dupex identifies a set of duplicated phrases, called patterns, that together best compress a given input text. Through an extensive set of experi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00735","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/2110.00735/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":"2026-07-05T04:21:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sBc3rPIYYo+Mj/DjLT0It3NZFx31WVOsGrPjb6duH6bVQtN0Z1W9c/LybcK+Q+1FlDKpWwHlsqhIQUdyiifTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:26:38.337656Z"},"content_sha256":"f17f8b409ec8d2255e75b40c5b4a75aab1e39ccda476e8f11098f673722a5e6b","schema_version":"1.0","event_id":"sha256:f17f8b409ec8d2255e75b40c5b4a75aab1e39ccda476e8f11098f673722a5e6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PZEPOH6SFPICMXPSYI424K7XPT/bundle.json","state_url":"https://pith.science/pith/PZEPOH6SFPICMXPSYI424K7XPT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PZEPOH6SFPICMXPSYI424K7XPT/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":"2026-07-07T08:26:38Z","links":{"resolver":"https://pith.science/pith/PZEPOH6SFPICMXPSYI424K7XPT","bundle":"https://pith.science/pith/PZEPOH6SFPICMXPSYI424K7XPT/bundle.json","state":"https://pith.science/pith/PZEPOH6SFPICMXPSYI424K7XPT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PZEPOH6SFPICMXPSYI424K7XPT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PZEPOH6SFPICMXPSYI424K7XPT","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":"9f866a38a347f4f17249bd66645063c6f81c2bcc5bcda20d076f993e3826f376","cross_cats_sorted":["cs.CY","cs.IT","cs.SE","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-02T06:19:14Z","title_canon_sha256":"21eb2d627528cb1e95fbdbf9acf286f6e7d1d47858fad2eca30745a4f7e4280c"},"schema_version":"1.0","source":{"id":"2110.00735","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.00735","created_at":"2026-07-05T04:21:06Z"},{"alias_kind":"arxiv_version","alias_value":"2110.00735v1","created_at":"2026-07-05T04:21:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00735","created_at":"2026-07-05T04:21:06Z"},{"alias_kind":"pith_short_12","alias_value":"PZEPOH6SFPIC","created_at":"2026-07-05T04:21:06Z"},{"alias_kind":"pith_short_16","alias_value":"PZEPOH6SFPICMXPS","created_at":"2026-07-05T04:21:06Z"},{"alias_kind":"pith_short_8","alias_value":"PZEPOH6S","created_at":"2026-07-05T04:21:06Z"}],"graph_snapshots":[{"event_id":"sha256:f17f8b409ec8d2255e75b40c5b4a75aab1e39ccda476e8f11098f673722a5e6b","target":"graph","created_at":"2026-07-05T04:21:06Z","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/2110.00735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Textual redundancy is one of the main challenges to ensuring that legal texts remain comprehensible and maintainable. Drawing inspiration from the refactoring literature in software engineering, which has developed methods to expose and eliminate duplicated code, we introduce the duplicated phrase detection problem for legal texts and propose the Dupex algorithm to solve it. Leveraging the Minimum Description Length principle from information theory, Dupex identifies a set of duplicated phrases, called patterns, that together best compress a given input text. Through an extensive set of experi","authors_text":"Corinna Coupette, Holger Spamann, Jyotsna Singh","cross_cats":["cs.CY","cs.IT","cs.SE","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-02T06:19:14Z","title":"Simplify Your Law: Using Information Theory to Deduplicate Legal Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00735","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:e94963c77343bad1125eb2e67817cb2b425ad8fc45b48b0ea614a09e5d9f84eb","target":"record","created_at":"2026-07-05T04:21:06Z","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":"9f866a38a347f4f17249bd66645063c6f81c2bcc5bcda20d076f993e3826f376","cross_cats_sorted":["cs.CY","cs.IT","cs.SE","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-02T06:19:14Z","title_canon_sha256":"21eb2d627528cb1e95fbdbf9acf286f6e7d1d47858fad2eca30745a4f7e4280c"},"schema_version":"1.0","source":{"id":"2110.00735","kind":"arxiv","version":1}},"canonical_sha256":"7e48f71fd22bd0265df2c239ae2bf77ce9cbc53feb07aae6f215b3d3855fe101","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e48f71fd22bd0265df2c239ae2bf77ce9cbc53feb07aae6f215b3d3855fe101","first_computed_at":"2026-07-05T04:21:06.184270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:21:06.184270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4q6TV9zySxpSA8rnjVrlKVNCwZ/xZ6oy5pNo6Oo7ZuWb2k2MfMUE9btrsQv3dczCW+CWRGC03l/0a2O7yTd2Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:21:06.184694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.00735","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e94963c77343bad1125eb2e67817cb2b425ad8fc45b48b0ea614a09e5d9f84eb","sha256:f17f8b409ec8d2255e75b40c5b4a75aab1e39ccda476e8f11098f673722a5e6b"],"state_sha256":"dc030752725c4814f4dc7485f1b17ab90da5e30d1bd696a14ee0fd1b245409a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G2DdThlPFFqSDlOiTLDbA0QLbkm6H81DU+bTNbsIXkQTxXGCtiLQUBB75E1f3IzNYIUk76cc7pfETG/Qss6UBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:26:38.339529Z","bundle_sha256":"a1cff974a471409067d42361471f603d32b8d68bde2f4bbb6670a6e85f862eb5"}}