{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YVV7T7TO45JIHJZHL43M57A4TU","short_pith_number":"pith:YVV7T7TO","schema_version":"1.0","canonical_sha256":"c56bf9fe6ee75283a7275f36cefc1c9d3504ee9222551a1a2e9049072be3228b","source":{"kind":"arxiv","id":"1802.06997","version":2},"attestation_state":"computed","paper":{"title":"Categorizing the Content of GitHub README Files","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Christoph Treude, David Lo, Ferdian Thung, Gede Artha Azriadi Prana, Thushari Atapattu","submitted_at":"2018-02-20T07:50:56Z","abstract_excerpt":"README files play an essential role in shaping a developer's first impression of a software repository and in documenting the software project that the repository hosts. Yet, we lack a systematic understanding of the content of a typical README file as well as tools that can process these files automatically. To close this gap, we conduct a qualitative study involving the manual annotation of 4,226 README file sections from 393 randomly sampled GitHub repositories and we design and evaluate a classifier and a set of features that can categorize these sections automatically. We find that inform"},"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":"1802.06997","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-02-20T07:50:56Z","cross_cats_sorted":[],"title_canon_sha256":"a992e5ed10abd5725dde46216daadf29af1a58161fe236226b978a3542bd1ac3","abstract_canon_sha256":"4c187f148edd6892e2bbb47bed81b94efb20ddc7bcfffa18a7413dd0b025dc9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:35.977184Z","signature_b64":"4qA+ywPtr74a3NA0x1/lSJpYSnopJK7kUskdcCemnqqK3qZyLxx2DuuLqu5UbyiD9nEW++n9kae6ZD2QKTMOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c56bf9fe6ee75283a7275f36cefc1c9d3504ee9222551a1a2e9049072be3228b","last_reissued_at":"2026-05-18T00:09:35.976665Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:35.976665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Categorizing the Content of GitHub README Files","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Christoph Treude, David Lo, Ferdian Thung, Gede Artha Azriadi Prana, Thushari Atapattu","submitted_at":"2018-02-20T07:50:56Z","abstract_excerpt":"README files play an essential role in shaping a developer's first impression of a software repository and in documenting the software project that the repository hosts. Yet, we lack a systematic understanding of the content of a typical README file as well as tools that can process these files automatically. To close this gap, we conduct a qualitative study involving the manual annotation of 4,226 README file sections from 393 randomly sampled GitHub repositories and we design and evaluate a classifier and a set of features that can categorize these sections automatically. We find that inform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06997","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":"1802.06997","created_at":"2026-05-18T00:09:35.976749+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.06997v2","created_at":"2026-05-18T00:09:35.976749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06997","created_at":"2026-05-18T00:09:35.976749+00:00"},{"alias_kind":"pith_short_12","alias_value":"YVV7T7TO45JI","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YVV7T7TO45JIHJZH","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YVV7T7TO","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.00822","citing_title":"ContextCov: Deriving and Enforcing Executable Constraints from Agent Instruction Files","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YVV7T7TO45JIHJZHL43M57A4TU","json":"https://pith.science/pith/YVV7T7TO45JIHJZHL43M57A4TU.json","graph_json":"https://pith.science/api/pith-number/YVV7T7TO45JIHJZHL43M57A4TU/graph.json","events_json":"https://pith.science/api/pith-number/YVV7T7TO45JIHJZHL43M57A4TU/events.json","paper":"https://pith.science/paper/YVV7T7TO"},"agent_actions":{"view_html":"https://pith.science/pith/YVV7T7TO45JIHJZHL43M57A4TU","download_json":"https://pith.science/pith/YVV7T7TO45JIHJZHL43M57A4TU.json","view_paper":"https://pith.science/paper/YVV7T7TO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.06997&json=true","fetch_graph":"https://pith.science/api/pith-number/YVV7T7TO45JIHJZHL43M57A4TU/graph.json","fetch_events":"https://pith.science/api/pith-number/YVV7T7TO45JIHJZHL43M57A4TU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YVV7T7TO45JIHJZHL43M57A4TU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YVV7T7TO45JIHJZHL43M57A4TU/action/storage_attestation","attest_author":"https://pith.science/pith/YVV7T7TO45JIHJZHL43M57A4TU/action/author_attestation","sign_citation":"https://pith.science/pith/YVV7T7TO45JIHJZHL43M57A4TU/action/citation_signature","submit_replication":"https://pith.science/pith/YVV7T7TO45JIHJZHL43M57A4TU/action/replication_record"}},"created_at":"2026-05-18T00:09:35.976749+00:00","updated_at":"2026-05-18T00:09:35.976749+00:00"}