{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:WX77IFZRL36VEUQE5YETAW5CRZ","short_pith_number":"pith:WX77IFZR","schema_version":"1.0","canonical_sha256":"b5fff417315efd525204ee09305ba28e5a270f2ec04ae3d1f37e2534f92ba629","source":{"kind":"arxiv","id":"1502.01410","version":2},"attestation_state":"computed","paper":{"title":"On the Lexical Distinguishability of Source Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Dong Qiu, Earl T. Barr, Martin Velez, You Zhou, Zhendong Su","submitted_at":"2015-02-05T02:19:58Z","abstract_excerpt":"Natural language is robust against noise. The meaning of many sentences survives the loss of words, sometimes many of them. Some words in a sentence, however, cannot be lost without changing the meaning of the sentence. We call these words \"wheat\" and the rest \"chaff\". The word \"not\" in the sentence \"I do not like rain\" is wheat and \"do\" is chaff. For human understanding of the purpose and behavior of source code, we hypothesize that the same holds. To quantify the extent to which we can separate code into \"wheat\" and \"chaff\", we study a large (100M LOC), diverse corpus of real-world projects "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1502.01410","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2015-02-05T02:19:58Z","cross_cats_sorted":[],"title_canon_sha256":"34dbe2029d7689ac8b218df5a490af3b6f124d32b3fe7955fe0c17ea556b493c","abstract_canon_sha256":"c5b87f953bb377d4fe45caf9e4d3015f9234647fe135f20bf3700a73d3b18a39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:11.708529Z","signature_b64":"dbKQaUT1bah02FEEfIe3kuyKWZPthPF3sVGl9S5KWkT0w5erUoj3bTKe7epXnWiy45dTKu/dJun9jw57UhAPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5fff417315efd525204ee09305ba28e5a270f2ec04ae3d1f37e2534f92ba629","last_reissued_at":"2026-05-18T00:12:11.707774Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:11.707774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Lexical Distinguishability of Source Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Dong Qiu, Earl T. Barr, Martin Velez, You Zhou, Zhendong Su","submitted_at":"2015-02-05T02:19:58Z","abstract_excerpt":"Natural language is robust against noise. The meaning of many sentences survives the loss of words, sometimes many of them. Some words in a sentence, however, cannot be lost without changing the meaning of the sentence. We call these words \"wheat\" and the rest \"chaff\". The word \"not\" in the sentence \"I do not like rain\" is wheat and \"do\" is chaff. For human understanding of the purpose and behavior of source code, we hypothesize that the same holds. To quantify the extent to which we can separate code into \"wheat\" and \"chaff\", we study a large (100M LOC), diverse corpus of real-world projects "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.01410","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1502.01410","created_at":"2026-05-18T00:12:11.707921+00:00"},{"alias_kind":"arxiv_version","alias_value":"1502.01410v2","created_at":"2026-05-18T00:12:11.707921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.01410","created_at":"2026-05-18T00:12:11.707921+00:00"},{"alias_kind":"pith_short_12","alias_value":"WX77IFZRL36V","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_16","alias_value":"WX77IFZRL36VEUQE","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_8","alias_value":"WX77IFZR","created_at":"2026-05-18T12:29:47.479230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WX77IFZRL36VEUQE5YETAW5CRZ","json":"https://pith.science/pith/WX77IFZRL36VEUQE5YETAW5CRZ.json","graph_json":"https://pith.science/api/pith-number/WX77IFZRL36VEUQE5YETAW5CRZ/graph.json","events_json":"https://pith.science/api/pith-number/WX77IFZRL36VEUQE5YETAW5CRZ/events.json","paper":"https://pith.science/paper/WX77IFZR"},"agent_actions":{"view_html":"https://pith.science/pith/WX77IFZRL36VEUQE5YETAW5CRZ","download_json":"https://pith.science/pith/WX77IFZRL36VEUQE5YETAW5CRZ.json","view_paper":"https://pith.science/paper/WX77IFZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1502.01410&json=true","fetch_graph":"https://pith.science/api/pith-number/WX77IFZRL36VEUQE5YETAW5CRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WX77IFZRL36VEUQE5YETAW5CRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WX77IFZRL36VEUQE5YETAW5CRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WX77IFZRL36VEUQE5YETAW5CRZ/action/storage_attestation","attest_author":"https://pith.science/pith/WX77IFZRL36VEUQE5YETAW5CRZ/action/author_attestation","sign_citation":"https://pith.science/pith/WX77IFZRL36VEUQE5YETAW5CRZ/action/citation_signature","submit_replication":"https://pith.science/pith/WX77IFZRL36VEUQE5YETAW5CRZ/action/replication_record"}},"created_at":"2026-05-18T00:12:11.707921+00:00","updated_at":"2026-05-18T00:12:11.707921+00:00"}