{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:KZMEQG5LONK6FDTNTHYNB4FOQ3","short_pith_number":"pith:KZMEQG5L","canonical_record":{"source":{"id":"1602.08715","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-28T13:43:33Z","cross_cats_sorted":[],"title_canon_sha256":"58ed9853a477fd4a9b3754f760599018432b854bacdca65ace538a73bff238b4","abstract_canon_sha256":"0ad5112dbf10bebc94d152e41bd707a7a063e6ced7dac975e5f2fc91b9201426"},"schema_version":"1.0"},"canonical_sha256":"5658481bab7355e28e6d99f0d0f0ae86c9335efba2020104faeafd6980d70340","source":{"kind":"arxiv","id":"1602.08715","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.08715","created_at":"2026-07-05T06:23:16Z"},{"alias_kind":"arxiv_version","alias_value":"1602.08715v2","created_at":"2026-07-05T06:23:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.08715","created_at":"2026-07-05T06:23:16Z"},{"alias_kind":"pith_short_12","alias_value":"KZMEQG5LONK6","created_at":"2026-07-05T06:23:16Z"},{"alias_kind":"pith_short_16","alias_value":"KZMEQG5LONK6FDTN","created_at":"2026-07-05T06:23:16Z"},{"alias_kind":"pith_short_8","alias_value":"KZMEQG5L","created_at":"2026-07-05T06:23:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:KZMEQG5LONK6FDTNTHYNB4FOQ3","target":"record","payload":{"canonical_record":{"source":{"id":"1602.08715","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-28T13:43:33Z","cross_cats_sorted":[],"title_canon_sha256":"58ed9853a477fd4a9b3754f760599018432b854bacdca65ace538a73bff238b4","abstract_canon_sha256":"0ad5112dbf10bebc94d152e41bd707a7a063e6ced7dac975e5f2fc91b9201426"},"schema_version":"1.0"},"canonical_sha256":"5658481bab7355e28e6d99f0d0f0ae86c9335efba2020104faeafd6980d70340","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:16.642501Z","signature_b64":"mAxzlHsbUIlTxd84y7IZw4K+gX1wgx+x4fJZR8EO5ukyFwIaXPZlW9TwMonz2FNbnT/IvEO8ob9tKkaxsxnFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5658481bab7355e28e6d99f0d0f0ae86c9335efba2020104faeafd6980d70340","last_reissued_at":"2026-07-05T06:23:16.642111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:16.642111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.08715","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:23:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZH+Je1ynQERR8+YK67eptw+ZREqaJucSUaWUO9Jr0aOPRGDcvgn3Jh3huu7YDfcWAlrET5jE/MHDOfpp9UsvBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:10:42.144990Z"},"content_sha256":"ade9820b43aeb6030627bf714b24391a7fa38ed0d91dd49806555a1e0072233b","schema_version":"1.0","event_id":"sha256:ade9820b43aeb6030627bf714b24391a7fa38ed0d91dd49806555a1e0072233b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:KZMEQG5LONK6FDTNTHYNB4FOQ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Identification of Parallel Passages Across a Large Hebrew/Aramaic Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avi Shmidman, Ely Porat, Moshe Koppel","submitted_at":"2016-02-28T13:43:33Z","abstract_excerpt":"We propose a method for efficiently finding all parallel passages in a large corpus, even if the passages are not quite identical due to rephrasing and orthographic variation. The key ideas are the representation of each word in the corpus by its two most infrequent letters, finding matched pairs of strings of four or five words that differ by at most one word and then identifying clusters of such matched pairs. Using this method, over 4600 parallel pairs of passages were identified in the Babylonian Talmud, a Hebrew-Aramaic corpus of over 1.8 million words, in just over 30 seconds. Empirical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.08715","kind":"arxiv","version":2},"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/1602.08715/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":"2026-07-05T06:23:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f8zI088av9eZz0tsFiUkUU4iQupN8evCZmaPqek9xj5SJCpctJk5YMrAmYWR7k7n0kKikqGP6uHMz9Rs5B0yAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:10:42.155539Z"},"content_sha256":"a01e10c3ca02573f327d953551c623521174c3c9a069c91d3ba0f8f937a3aea2","schema_version":"1.0","event_id":"sha256:a01e10c3ca02573f327d953551c623521174c3c9a069c91d3ba0f8f937a3aea2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KZMEQG5LONK6FDTNTHYNB4FOQ3/bundle.json","state_url":"https://pith.science/pith/KZMEQG5LONK6FDTNTHYNB4FOQ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KZMEQG5LONK6FDTNTHYNB4FOQ3/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":"2026-08-04T15:10:42Z","links":{"resolver":"https://pith.science/pith/KZMEQG5LONK6FDTNTHYNB4FOQ3","bundle":"https://pith.science/pith/KZMEQG5LONK6FDTNTHYNB4FOQ3/bundle.json","state":"https://pith.science/pith/KZMEQG5LONK6FDTNTHYNB4FOQ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KZMEQG5LONK6FDTNTHYNB4FOQ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:KZMEQG5LONK6FDTNTHYNB4FOQ3","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":"0ad5112dbf10bebc94d152e41bd707a7a063e6ced7dac975e5f2fc91b9201426","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-28T13:43:33Z","title_canon_sha256":"58ed9853a477fd4a9b3754f760599018432b854bacdca65ace538a73bff238b4"},"schema_version":"1.0","source":{"id":"1602.08715","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.08715","created_at":"2026-07-05T06:23:16Z"},{"alias_kind":"arxiv_version","alias_value":"1602.08715v2","created_at":"2026-07-05T06:23:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.08715","created_at":"2026-07-05T06:23:16Z"},{"alias_kind":"pith_short_12","alias_value":"KZMEQG5LONK6","created_at":"2026-07-05T06:23:16Z"},{"alias_kind":"pith_short_16","alias_value":"KZMEQG5LONK6FDTN","created_at":"2026-07-05T06:23:16Z"},{"alias_kind":"pith_short_8","alias_value":"KZMEQG5L","created_at":"2026-07-05T06:23:16Z"}],"graph_snapshots":[{"event_id":"sha256:a01e10c3ca02573f327d953551c623521174c3c9a069c91d3ba0f8f937a3aea2","target":"graph","created_at":"2026-07-05T06:23:16Z","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/1602.08715/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a method for efficiently finding all parallel passages in a large corpus, even if the passages are not quite identical due to rephrasing and orthographic variation. The key ideas are the representation of each word in the corpus by its two most infrequent letters, finding matched pairs of strings of four or five words that differ by at most one word and then identifying clusters of such matched pairs. Using this method, over 4600 parallel pairs of passages were identified in the Babylonian Talmud, a Hebrew-Aramaic corpus of over 1.8 million words, in just over 30 seconds. Empirical ","authors_text":"Avi Shmidman, Ely Porat, Moshe Koppel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-28T13:43:33Z","title":"Identification of Parallel Passages Across a Large Hebrew/Aramaic Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.08715","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:ade9820b43aeb6030627bf714b24391a7fa38ed0d91dd49806555a1e0072233b","target":"record","created_at":"2026-07-05T06:23:16Z","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":"0ad5112dbf10bebc94d152e41bd707a7a063e6ced7dac975e5f2fc91b9201426","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-28T13:43:33Z","title_canon_sha256":"58ed9853a477fd4a9b3754f760599018432b854bacdca65ace538a73bff238b4"},"schema_version":"1.0","source":{"id":"1602.08715","kind":"arxiv","version":2}},"canonical_sha256":"5658481bab7355e28e6d99f0d0f0ae86c9335efba2020104faeafd6980d70340","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5658481bab7355e28e6d99f0d0f0ae86c9335efba2020104faeafd6980d70340","first_computed_at":"2026-07-05T06:23:16.642111Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:23:16.642111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mAxzlHsbUIlTxd84y7IZw4K+gX1wgx+x4fJZR8EO5ukyFwIaXPZlW9TwMonz2FNbnT/IvEO8ob9tKkaxsxnFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:23:16.642501Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.08715","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ade9820b43aeb6030627bf714b24391a7fa38ed0d91dd49806555a1e0072233b","sha256:a01e10c3ca02573f327d953551c623521174c3c9a069c91d3ba0f8f937a3aea2"],"state_sha256":"300a6effaa3e181c065c1a5cd5ae2f5a0e42fdc137cb64054cd11306e4da5ce9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LYNaR70dkxnbgrjpOCKcII+qx2RKHKn3NZomD+sDicLYtoVGunfVf3YNiVYxBz0GLlUkQQwQRH9Gp270jns+Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:10:42.229311Z","bundle_sha256":"ee45d841db9e7abefcf05b0592a2145ee1beb06a5eaa7bda4d2857ef5c8d8b44"}}