{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:Z45QCBA44CM5QCDV6HAISZS4CK","short_pith_number":"pith:Z45QCBA4","canonical_record":{"source":{"id":"1602.05772","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-18T12:08:05Z","cross_cats_sorted":[],"title_canon_sha256":"3681706fd5a6519f0cb5db6d7153a20fa06e11b0850a4741e422db89228b3eb0","abstract_canon_sha256":"a125a2a6e2dc01aea5996e284954a18321dc66c6520b6fa19eccc9240753a7c6"},"schema_version":"1.0"},"canonical_sha256":"cf3b01041ce099d80875f1c089665c12b467d953b6d378eda7da9fe4c7c977ad","source":{"kind":"arxiv","id":"1602.05772","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.05772","created_at":"2026-05-18T01:20:23Z"},{"alias_kind":"arxiv_version","alias_value":"1602.05772v1","created_at":"2026-05-18T01:20:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.05772","created_at":"2026-05-18T01:20:23Z"},{"alias_kind":"pith_short_12","alias_value":"Z45QCBA44CM5","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"Z45QCBA44CM5QCDV","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"Z45QCBA4","created_at":"2026-05-18T12:30:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:Z45QCBA44CM5QCDV6HAISZS4CK","target":"record","payload":{"canonical_record":{"source":{"id":"1602.05772","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-18T12:08:05Z","cross_cats_sorted":[],"title_canon_sha256":"3681706fd5a6519f0cb5db6d7153a20fa06e11b0850a4741e422db89228b3eb0","abstract_canon_sha256":"a125a2a6e2dc01aea5996e284954a18321dc66c6520b6fa19eccc9240753a7c6"},"schema_version":"1.0"},"canonical_sha256":"cf3b01041ce099d80875f1c089665c12b467d953b6d378eda7da9fe4c7c977ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:23.251286Z","signature_b64":"1/K5uQf/nLSLiYpnOC3W7+4tSuk0NvAlKSSJx7HZYENaeMKhIrR98a0A97g2uh3ZeSQ6AnXUjNzcj+j6lCdCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf3b01041ce099d80875f1c089665c12b467d953b6d378eda7da9fe4c7c977ad","last_reissued_at":"2026-05-18T01:20:23.250682Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:23.250682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.05772","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":"2026-05-18T01:20:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z8HMitz5Gsqot/fUzet+rxYXtewOy12uoD53bccXKIy9l8zoqqAOzqqxUbvz4HbTG5bijxfnaN/mMglGe4nVDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T04:15:39.036878Z"},"content_sha256":"02d0719e27886187e514587cfb8271654fbcd6a5a2a65b463098b7db7778d1ac","schema_version":"1.0","event_id":"sha256:02d0719e27886187e514587cfb8271654fbcd6a5a2a65b463098b7db7778d1ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:Z45QCBA44CM5QCDV6HAISZS4CK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Corpus analysis without prior linguistic knowledge - unsupervised mining of phrases and subphrase structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Klaus U. Schulz, Stefan Gerdjikov","submitted_at":"2016-02-18T12:08:05Z","abstract_excerpt":"When looking at the structure of natural language, \"phrases\" and \"words\" are central notions. We consider the problem of identifying such \"meaningful subparts\" of language of any length and underlying composition principles in a completely corpus-based and language-independent way without using any kind of prior linguistic knowledge. Unsupervised methods for identifying \"phrases\", mining subphrase structure and finding words in a fully automated way are described. This can be considered as a step towards automatically computing a \"general dictionary and grammar of the corpus\". We hope that in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.05772","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":""},"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":"2026-05-18T01:20:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tWQ6LKyce2c+n5mQjbYlZVu+InZXOq7YeNIOLzDYtn7YKxND51zlxdGyvhXX1nPEkMmrrsv/1XXC6l/TkBMXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T04:15:39.037224Z"},"content_sha256":"7f421c2fdb10702bda21d6428a4e86d3b39b3b296292f73ceec57fd8b347fb1c","schema_version":"1.0","event_id":"sha256:7f421c2fdb10702bda21d6428a4e86d3b39b3b296292f73ceec57fd8b347fb1c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z45QCBA44CM5QCDV6HAISZS4CK/bundle.json","state_url":"https://pith.science/pith/Z45QCBA44CM5QCDV6HAISZS4CK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z45QCBA44CM5QCDV6HAISZS4CK/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":"2026-07-21T04:15:39Z","links":{"resolver":"https://pith.science/pith/Z45QCBA44CM5QCDV6HAISZS4CK","bundle":"https://pith.science/pith/Z45QCBA44CM5QCDV6HAISZS4CK/bundle.json","state":"https://pith.science/pith/Z45QCBA44CM5QCDV6HAISZS4CK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z45QCBA44CM5QCDV6HAISZS4CK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:Z45QCBA44CM5QCDV6HAISZS4CK","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":"a125a2a6e2dc01aea5996e284954a18321dc66c6520b6fa19eccc9240753a7c6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-18T12:08:05Z","title_canon_sha256":"3681706fd5a6519f0cb5db6d7153a20fa06e11b0850a4741e422db89228b3eb0"},"schema_version":"1.0","source":{"id":"1602.05772","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.05772","created_at":"2026-05-18T01:20:23Z"},{"alias_kind":"arxiv_version","alias_value":"1602.05772v1","created_at":"2026-05-18T01:20:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.05772","created_at":"2026-05-18T01:20:23Z"},{"alias_kind":"pith_short_12","alias_value":"Z45QCBA44CM5","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"Z45QCBA44CM5QCDV","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"Z45QCBA4","created_at":"2026-05-18T12:30:53Z"}],"graph_snapshots":[{"event_id":"sha256:7f421c2fdb10702bda21d6428a4e86d3b39b3b296292f73ceec57fd8b347fb1c","target":"graph","created_at":"2026-05-18T01:20:23Z","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":"When looking at the structure of natural language, \"phrases\" and \"words\" are central notions. We consider the problem of identifying such \"meaningful subparts\" of language of any length and underlying composition principles in a completely corpus-based and language-independent way without using any kind of prior linguistic knowledge. Unsupervised methods for identifying \"phrases\", mining subphrase structure and finding words in a fully automated way are described. This can be considered as a step towards automatically computing a \"general dictionary and grammar of the corpus\". We hope that in ","authors_text":"Klaus U. Schulz, Stefan Gerdjikov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-18T12:08:05Z","title":"Corpus analysis without prior linguistic knowledge - unsupervised mining of phrases and subphrase structure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.05772","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":"sha256:02d0719e27886187e514587cfb8271654fbcd6a5a2a65b463098b7db7778d1ac","target":"record","created_at":"2026-05-18T01:20:23Z","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":"a125a2a6e2dc01aea5996e284954a18321dc66c6520b6fa19eccc9240753a7c6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-18T12:08:05Z","title_canon_sha256":"3681706fd5a6519f0cb5db6d7153a20fa06e11b0850a4741e422db89228b3eb0"},"schema_version":"1.0","source":{"id":"1602.05772","kind":"arxiv","version":1}},"canonical_sha256":"cf3b01041ce099d80875f1c089665c12b467d953b6d378eda7da9fe4c7c977ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf3b01041ce099d80875f1c089665c12b467d953b6d378eda7da9fe4c7c977ad","first_computed_at":"2026-05-18T01:20:23.250682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:20:23.250682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1/K5uQf/nLSLiYpnOC3W7+4tSuk0NvAlKSSJx7HZYENaeMKhIrR98a0A97g2uh3ZeSQ6AnXUjNzcj+j6lCdCCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:20:23.251286Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.05772","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02d0719e27886187e514587cfb8271654fbcd6a5a2a65b463098b7db7778d1ac","sha256:7f421c2fdb10702bda21d6428a4e86d3b39b3b296292f73ceec57fd8b347fb1c"],"state_sha256":"6814e52326342193a79eb8d33be775479468bbcc883e64edc37520af7dd76c61"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7gwad3NpV+TxzvF9Unfc/t2q5k+RUpwnN27x31DJueyMum3IjpAvHCFBMp/p22jU8+pkgvPpqFElGnPwBmbKAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T04:15:39.039789Z","bundle_sha256":"4a1de8c36d70404d4181d4cbdd025b46aaa0c5197e5f84c7574d4103fe831224"}}