{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ES5WU7KJMOIWVHODGVYEBCFW6O","short_pith_number":"pith:ES5WU7KJ","canonical_record":{"source":{"id":"2607.05416","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T03:20:57Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"11dcf5f342c15679ce24466b9900030ff543dad335a18cdbb8210be5007dadc1","abstract_canon_sha256":"1c26c81c1b6df850707c5cf195356fe0c84eb423c84666525a75f5eaac82b892"},"schema_version":"1.0"},"canonical_sha256":"24bb6a7d4963916a9dc335704088b6f393f01bf99e9b10ad1d70b800d962b163","source":{"kind":"arxiv","id":"2607.05416","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05416","created_at":"2026-07-08T01:18:09Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05416v1","created_at":"2026-07-08T01:18:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05416","created_at":"2026-07-08T01:18:09Z"},{"alias_kind":"pith_short_12","alias_value":"ES5WU7KJMOIW","created_at":"2026-07-08T01:18:09Z"},{"alias_kind":"pith_short_16","alias_value":"ES5WU7KJMOIWVHOD","created_at":"2026-07-08T01:18:09Z"},{"alias_kind":"pith_short_8","alias_value":"ES5WU7KJ","created_at":"2026-07-08T01:18:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ES5WU7KJMOIWVHODGVYEBCFW6O","target":"record","payload":{"canonical_record":{"source":{"id":"2607.05416","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T03:20:57Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"11dcf5f342c15679ce24466b9900030ff543dad335a18cdbb8210be5007dadc1","abstract_canon_sha256":"1c26c81c1b6df850707c5cf195356fe0c84eb423c84666525a75f5eaac82b892"},"schema_version":"1.0"},"canonical_sha256":"24bb6a7d4963916a9dc335704088b6f393f01bf99e9b10ad1d70b800d962b163","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:09.394865Z","signature_b64":"wqitjTgUsZMBggaw44/I77wKTdhP1CGn5v6CBIgitboST1vZjMbRYbbzmcwqi/rUtmtErMwjNOxUY61p/BJ0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24bb6a7d4963916a9dc335704088b6f393f01bf99e9b10ad1d70b800d962b163","last_reissued_at":"2026-07-08T01:18:09.394226Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:09.394226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.05416","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":"2026-07-08T01:18:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kPdOyt8Qfv/ZFfZvyM++fq/EMLd9EiUdVoZkvBODkDU/n9uAxeaGFR4zJMXpF9iWOmYIFc1P9gPc/sncb6MrBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T13:16:38.079110Z"},"content_sha256":"9ee688feccfea0a1a0b4550baf3ec542281c9db83518a55805574109ecb766e2","schema_version":"1.0","event_id":"sha256:9ee688feccfea0a1a0b4550baf3ec542281c9db83518a55805574109ecb766e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ES5WU7KJMOIWVHODGVYEBCFW6O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text Distance from Nested and Hierarchical Repetitions: A Compression-Based Perspective","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.CL","authors_text":"Fengyao Zhai, Hao Liao, Jing Wang, Jingwen Zhang, Xiaojun Hu, Xiao Xie, Yu Liu, Zengru Di","submitted_at":"2026-06-23T03:20:57Z","abstract_excerpt":"We present a new method for structural sequence analysis grounded in Algorithmic Information Theory (AIT). At its core is the Ladderpath approach, which extracts nested and hierarchical relationships among repeated substructures in linguistic sequences -- an instantiation of AIT's principle of describing data through minimal generative programs. These structures are then used to define three distance measures: a normalized compression distance (NCD), and two alternative distances derived directly from the Ladderpath representation. Integrated with a $k$-nearest neighbor classifier, these dista"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05416","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/2607.05416/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":"2026-07-08T01:18:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XtUj07rD9OnKo1jctr6jvbNAksY7JRjkMLU9gkwtrBBJujIERCFSuVX7tUp7MsSWq1u2k1xhQCNf9IGxp3jABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T13:16:38.079941Z"},"content_sha256":"bac575b8abf48dbeeb43c0195bc1772943bded135646097a9ef9cfd6815848fd","schema_version":"1.0","event_id":"sha256:bac575b8abf48dbeeb43c0195bc1772943bded135646097a9ef9cfd6815848fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ES5WU7KJMOIWVHODGVYEBCFW6O/bundle.json","state_url":"https://pith.science/pith/ES5WU7KJMOIWVHODGVYEBCFW6O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ES5WU7KJMOIWVHODGVYEBCFW6O/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":"2026-08-20T13:16:38Z","links":{"resolver":"https://pith.science/pith/ES5WU7KJMOIWVHODGVYEBCFW6O","bundle":"https://pith.science/pith/ES5WU7KJMOIWVHODGVYEBCFW6O/bundle.json","state":"https://pith.science/pith/ES5WU7KJMOIWVHODGVYEBCFW6O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ES5WU7KJMOIWVHODGVYEBCFW6O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ES5WU7KJMOIWVHODGVYEBCFW6O","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":"1c26c81c1b6df850707c5cf195356fe0c84eb423c84666525a75f5eaac82b892","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T03:20:57Z","title_canon_sha256":"11dcf5f342c15679ce24466b9900030ff543dad335a18cdbb8210be5007dadc1"},"schema_version":"1.0","source":{"id":"2607.05416","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05416","created_at":"2026-07-08T01:18:09Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05416v1","created_at":"2026-07-08T01:18:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05416","created_at":"2026-07-08T01:18:09Z"},{"alias_kind":"pith_short_12","alias_value":"ES5WU7KJMOIW","created_at":"2026-07-08T01:18:09Z"},{"alias_kind":"pith_short_16","alias_value":"ES5WU7KJMOIWVHOD","created_at":"2026-07-08T01:18:09Z"},{"alias_kind":"pith_short_8","alias_value":"ES5WU7KJ","created_at":"2026-07-08T01:18:09Z"}],"graph_snapshots":[{"event_id":"sha256:bac575b8abf48dbeeb43c0195bc1772943bded135646097a9ef9cfd6815848fd","target":"graph","created_at":"2026-07-08T01:18:09Z","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/2607.05416/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a new method for structural sequence analysis grounded in Algorithmic Information Theory (AIT). At its core is the Ladderpath approach, which extracts nested and hierarchical relationships among repeated substructures in linguistic sequences -- an instantiation of AIT's principle of describing data through minimal generative programs. These structures are then used to define three distance measures: a normalized compression distance (NCD), and two alternative distances derived directly from the Ladderpath representation. Integrated with a $k$-nearest neighbor classifier, these dista","authors_text":"Fengyao Zhai, Hao Liao, Jing Wang, Jingwen Zhang, Xiaojun Hu, Xiao Xie, Yu Liu, Zengru Di","cross_cats":["cs.IT","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T03:20:57Z","title":"Text Distance from Nested and Hierarchical Repetitions: A Compression-Based Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05416","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":"sha256:9ee688feccfea0a1a0b4550baf3ec542281c9db83518a55805574109ecb766e2","target":"record","created_at":"2026-07-08T01:18:09Z","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":"1c26c81c1b6df850707c5cf195356fe0c84eb423c84666525a75f5eaac82b892","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T03:20:57Z","title_canon_sha256":"11dcf5f342c15679ce24466b9900030ff543dad335a18cdbb8210be5007dadc1"},"schema_version":"1.0","source":{"id":"2607.05416","kind":"arxiv","version":1}},"canonical_sha256":"24bb6a7d4963916a9dc335704088b6f393f01bf99e9b10ad1d70b800d962b163","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24bb6a7d4963916a9dc335704088b6f393f01bf99e9b10ad1d70b800d962b163","first_computed_at":"2026-07-08T01:18:09.394226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:18:09.394226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wqitjTgUsZMBggaw44/I77wKTdhP1CGn5v6CBIgitboST1vZjMbRYbbzmcwqi/rUtmtErMwjNOxUY61p/BJ0Aw==","signature_status":"signed_v1","signed_at":"2026-07-08T01:18:09.394865Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.05416","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ee688feccfea0a1a0b4550baf3ec542281c9db83518a55805574109ecb766e2","sha256:bac575b8abf48dbeeb43c0195bc1772943bded135646097a9ef9cfd6815848fd"],"state_sha256":"b791df3506de6820dfa52170506a4117169fe878502cc45018e118d58504efce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jgjZ9/6oYIfAjS7buvz3ecdmcYYawui4mzh2ItJ+O6LmAM8vhtMgKLS0ZzOi5B9ur1cK52i4TcYjdEdKNSYJAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T13:16:38.088324Z","bundle_sha256":"bcbf73173eb57767254355d43ff692a412c8be1f822cbad4d5b4de7b895adc82"}}