{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4VS2Y5UCBOTEH4RJ5JWW5WCGSW","short_pith_number":"pith:4VS2Y5UC","schema_version":"1.0","canonical_sha256":"e565ac76820ba643f229ea6d6ed84695b151908780f4c8569315ed33e9d3068f","source":{"kind":"arxiv","id":"2506.06508","version":1},"attestation_state":"computed","paper":{"title":"Information-Theoretic Detection of Unusual Source Code Changes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Adriano Torres, Christoph Treude, Markus Wagner, Sebastian Baltes","submitted_at":"2025-06-06T20:03:13Z","abstract_excerpt":"The code base of software projects evolves essentially through inserting and removing information to and from the source code. We can measure this evolution via the elements of information - tokens, words, nodes - of the respective representation of the code. In this work, we approach the measurement of the information content of the source code of open-source projects from an information-theoretic standpoint. Our focus is on the entropy of two fundamental representations of code: tokens and abstract syntax tree nodes, from which we derive definitions of textual and structural entropy. We proc"},"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":"2506.06508","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-06T20:03:13Z","cross_cats_sorted":[],"title_canon_sha256":"f33cd315e722a041358dd925bd7d1ee8d05ec4a05b7c7a1ddc47b949966c5abe","abstract_canon_sha256":"7f999a7f7cb33977c10c618e3bef0848b57e051ed5aeb9e0b480d1c5575382fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:51.399466Z","signature_b64":"6Zw2LtWtW1rz84CUREQY+sJl2vvbOAxL9LZbY57evm1Teajq6Aa26ru+ASIMATE6Kdo5MV8Wc9ycq4bvow5MBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e565ac76820ba643f229ea6d6ed84695b151908780f4c8569315ed33e9d3068f","last_reissued_at":"2026-07-05T11:17:51.398993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:51.398993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Information-Theoretic Detection of Unusual Source Code Changes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Adriano Torres, Christoph Treude, Markus Wagner, Sebastian Baltes","submitted_at":"2025-06-06T20:03:13Z","abstract_excerpt":"The code base of software projects evolves essentially through inserting and removing information to and from the source code. We can measure this evolution via the elements of information - tokens, words, nodes - of the respective representation of the code. In this work, we approach the measurement of the information content of the source code of open-source projects from an information-theoretic standpoint. Our focus is on the entropy of two fundamental representations of code: tokens and abstract syntax tree nodes, from which we derive definitions of textual and structural entropy. We proc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06508","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/2506.06508/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.06508","created_at":"2026-07-05T11:17:51.399058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06508v1","created_at":"2026-07-05T11:17:51.399058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06508","created_at":"2026-07-05T11:17:51.399058+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VS2Y5UCBOTE","created_at":"2026-07-05T11:17:51.399058+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VS2Y5UCBOTEH4RJ","created_at":"2026-07-05T11:17:51.399058+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VS2Y5UC","created_at":"2026-07-05T11:17:51.399058+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/4VS2Y5UCBOTEH4RJ5JWW5WCGSW","json":"https://pith.science/pith/4VS2Y5UCBOTEH4RJ5JWW5WCGSW.json","graph_json":"https://pith.science/api/pith-number/4VS2Y5UCBOTEH4RJ5JWW5WCGSW/graph.json","events_json":"https://pith.science/api/pith-number/4VS2Y5UCBOTEH4RJ5JWW5WCGSW/events.json","paper":"https://pith.science/paper/4VS2Y5UC"},"agent_actions":{"view_html":"https://pith.science/pith/4VS2Y5UCBOTEH4RJ5JWW5WCGSW","download_json":"https://pith.science/pith/4VS2Y5UCBOTEH4RJ5JWW5WCGSW.json","view_paper":"https://pith.science/paper/4VS2Y5UC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06508&json=true","fetch_graph":"https://pith.science/api/pith-number/4VS2Y5UCBOTEH4RJ5JWW5WCGSW/graph.json","fetch_events":"https://pith.science/api/pith-number/4VS2Y5UCBOTEH4RJ5JWW5WCGSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VS2Y5UCBOTEH4RJ5JWW5WCGSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VS2Y5UCBOTEH4RJ5JWW5WCGSW/action/storage_attestation","attest_author":"https://pith.science/pith/4VS2Y5UCBOTEH4RJ5JWW5WCGSW/action/author_attestation","sign_citation":"https://pith.science/pith/4VS2Y5UCBOTEH4RJ5JWW5WCGSW/action/citation_signature","submit_replication":"https://pith.science/pith/4VS2Y5UCBOTEH4RJ5JWW5WCGSW/action/replication_record"}},"created_at":"2026-07-05T11:17:51.399058+00:00","updated_at":"2026-07-05T11:17:51.399058+00:00"}