{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:H6MSL7XUCTXME2EJNP3MJE4F32","short_pith_number":"pith:H6MSL7XU","canonical_record":{"source":{"id":"1804.10657","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-04-27T19:20:39Z","cross_cats_sorted":[],"title_canon_sha256":"40e481ade5f1fcd76bf73d3d0d7f0052f86660a756a4eb76ce396cdd7ede2487","abstract_canon_sha256":"4cc7c269a7207998907db4d49cfe8f109d319cd895a75e2c5a593a8745c6d1df"},"schema_version":"1.0"},"canonical_sha256":"3f9925fef414eec268896bf6c49385dea97a3b748788f0edf9fa582ec0387ba8","source":{"kind":"arxiv","id":"1804.10657","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.10657","created_at":"2026-05-18T00:17:15Z"},{"alias_kind":"arxiv_version","alias_value":"1804.10657v1","created_at":"2026-05-18T00:17:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10657","created_at":"2026-05-18T00:17:15Z"},{"alias_kind":"pith_short_12","alias_value":"H6MSL7XUCTXM","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"H6MSL7XUCTXME2EJ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"H6MSL7XU","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:H6MSL7XUCTXME2EJNP3MJE4F32","target":"record","payload":{"canonical_record":{"source":{"id":"1804.10657","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-04-27T19:20:39Z","cross_cats_sorted":[],"title_canon_sha256":"40e481ade5f1fcd76bf73d3d0d7f0052f86660a756a4eb76ce396cdd7ede2487","abstract_canon_sha256":"4cc7c269a7207998907db4d49cfe8f109d319cd895a75e2c5a593a8745c6d1df"},"schema_version":"1.0"},"canonical_sha256":"3f9925fef414eec268896bf6c49385dea97a3b748788f0edf9fa582ec0387ba8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:15.949165Z","signature_b64":"x2kIcy3TiYfnk8omkuPwyZ3jCeQL1GeVHrQ0L9wwMlAZnPzYG/T2AZznKRjRHWXpwb9tBUemBjzIRo1fhVCMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f9925fef414eec268896bf6c49385dea97a3b748788f0edf9fa582ec0387ba8","last_reissued_at":"2026-05-18T00:17:15.948598Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:15.948598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.10657","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":"2026-05-18T00:17:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AOn+aGIWnjc0io5tXNikXGxzlrxG0Fvh0AowEV5wWMC/GeK0TqPYP5GKioWsMB0Uf4688c7AJ8edzkiYdL7DAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T08:11:52.509097Z"},"content_sha256":"c1fcb7fda006a3bc82d37edaa4cc7f0e31ab4b7c2fef577e07a5a650a88e3467","schema_version":"1.0","event_id":"sha256:c1fcb7fda006a3bc82d37edaa4cc7f0e31ab4b7c2fef577e07a5a650a88e3467"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:H6MSL7XUCTXME2EJNP3MJE4F32","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can You Explain That, Better? Comprehensible Text Analytics for SE Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Amritanshu Agrawal, Huy Tu, Tim Menzies","submitted_at":"2018-04-27T19:20:39Z","abstract_excerpt":"Text mining methods are used for a wide range of Software Engineering (SE) tasks. The biggest challenge of text mining is high dimensional data, i.e., a corpus of documents can contain $10^4$ to $10^6$ unique words. To address this complexity, some very convoluted text mining methods have been applied. Is that complexity necessary? Are there simpler ways to quickly generate models that perform as well as the more convoluted methods and also be human-readable?\n  To answer these questions, we explore a combination of LDA (Latent Dirichlet Allocation) and FFTs (Fast and Frugal Trees) to classify "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.10657","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":"2026-05-18T00:17:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"spuSkjqmW8DCBHgReJnZVmIh82pmbg9OJ8O9Rm2Ed8DC+Ic4tDSWz2OeQ6vUXny2G9CPYFC1cKFXHJ9x4PG5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T08:11:52.509491Z"},"content_sha256":"5b953ebfb626bfea2195bb1adac269c5468714b2804841a7faee081f10a1d690","schema_version":"1.0","event_id":"sha256:5b953ebfb626bfea2195bb1adac269c5468714b2804841a7faee081f10a1d690"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H6MSL7XUCTXME2EJNP3MJE4F32/bundle.json","state_url":"https://pith.science/pith/H6MSL7XUCTXME2EJNP3MJE4F32/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H6MSL7XUCTXME2EJNP3MJE4F32/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":"2026-06-12T08:11:52Z","links":{"resolver":"https://pith.science/pith/H6MSL7XUCTXME2EJNP3MJE4F32","bundle":"https://pith.science/pith/H6MSL7XUCTXME2EJNP3MJE4F32/bundle.json","state":"https://pith.science/pith/H6MSL7XUCTXME2EJNP3MJE4F32/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H6MSL7XUCTXME2EJNP3MJE4F32/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:H6MSL7XUCTXME2EJNP3MJE4F32","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":"4cc7c269a7207998907db4d49cfe8f109d319cd895a75e2c5a593a8745c6d1df","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-04-27T19:20:39Z","title_canon_sha256":"40e481ade5f1fcd76bf73d3d0d7f0052f86660a756a4eb76ce396cdd7ede2487"},"schema_version":"1.0","source":{"id":"1804.10657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.10657","created_at":"2026-05-18T00:17:15Z"},{"alias_kind":"arxiv_version","alias_value":"1804.10657v1","created_at":"2026-05-18T00:17:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10657","created_at":"2026-05-18T00:17:15Z"},{"alias_kind":"pith_short_12","alias_value":"H6MSL7XUCTXM","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"H6MSL7XUCTXME2EJ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"H6MSL7XU","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:5b953ebfb626bfea2195bb1adac269c5468714b2804841a7faee081f10a1d690","target":"graph","created_at":"2026-05-18T00:17:15Z","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":"Text mining methods are used for a wide range of Software Engineering (SE) tasks. The biggest challenge of text mining is high dimensional data, i.e., a corpus of documents can contain $10^4$ to $10^6$ unique words. To address this complexity, some very convoluted text mining methods have been applied. Is that complexity necessary? Are there simpler ways to quickly generate models that perform as well as the more convoluted methods and also be human-readable?\n  To answer these questions, we explore a combination of LDA (Latent Dirichlet Allocation) and FFTs (Fast and Frugal Trees) to classify ","authors_text":"Amritanshu Agrawal, Huy Tu, Tim Menzies","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-04-27T19:20:39Z","title":"Can You Explain That, Better? Comprehensible Text Analytics for SE Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.10657","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:c1fcb7fda006a3bc82d37edaa4cc7f0e31ab4b7c2fef577e07a5a650a88e3467","target":"record","created_at":"2026-05-18T00:17:15Z","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":"4cc7c269a7207998907db4d49cfe8f109d319cd895a75e2c5a593a8745c6d1df","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-04-27T19:20:39Z","title_canon_sha256":"40e481ade5f1fcd76bf73d3d0d7f0052f86660a756a4eb76ce396cdd7ede2487"},"schema_version":"1.0","source":{"id":"1804.10657","kind":"arxiv","version":1}},"canonical_sha256":"3f9925fef414eec268896bf6c49385dea97a3b748788f0edf9fa582ec0387ba8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f9925fef414eec268896bf6c49385dea97a3b748788f0edf9fa582ec0387ba8","first_computed_at":"2026-05-18T00:17:15.948598Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:15.948598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x2kIcy3TiYfnk8omkuPwyZ3jCeQL1GeVHrQ0L9wwMlAZnPzYG/T2AZznKRjRHWXpwb9tBUemBjzIRo1fhVCMAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:15.949165Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.10657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1fcb7fda006a3bc82d37edaa4cc7f0e31ab4b7c2fef577e07a5a650a88e3467","sha256:5b953ebfb626bfea2195bb1adac269c5468714b2804841a7faee081f10a1d690"],"state_sha256":"b254422b0ecdeb7158fd2699eeae3257e0bb1b01846d576b01896158f93a4004"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ohh6fga4OnE/uYCYbvPv/n8dD8jEfogmMI6MFcBQNk6l4jZ1RiksOC7CPCC7ZTvWgLB9U2mWB6IlUlN+ugzNDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T08:11:52.511949Z","bundle_sha256":"607ca4c35091267b37ad3af9773e5dbdd691d8a03fd3a1cba7a3b7a8a97b2da8"}}