{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:YCQTPZ6VJVRQLSWF4JYNKMHPXC","short_pith_number":"pith:YCQTPZ6V","schema_version":"1.0","canonical_sha256":"c0a137e7d54d6305cac5e270d530efb8bee0031bc789ab8aa791479793382bbe","source":{"kind":"arxiv","id":"1106.4064","version":2},"attestation_state":"computed","paper":{"title":"Algorithmic Programming Language Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Klein, Kyle Murray, Simon Weber","submitted_at":"2011-06-21T00:37:23Z","abstract_excerpt":"Motivated by the amount of code that goes unidentified on the web, we introduce a practical method for algorithmically identifying the programming language of source code. Our work is based on supervised learning and intelligent statistical features. We also explored, but abandoned, a grammatical approach. In testing, our implementation greatly outperforms that of an existing tool that relies on a Bayesian classifier. Code is written in Python and available under an MIT license."},"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":"1106.4064","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-21T00:37:23Z","cross_cats_sorted":[],"title_canon_sha256":"fe8bad432f83f7b05c03253fce710912a000946ca62339867bb58c7f68728df7","abstract_canon_sha256":"0e066cfee9a62f198961fd41eb993e930baadc731bea2368ada48657cc8200f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:08:44.599053Z","signature_b64":"QtxzV5stVrb/TfSZwUNXUfkzXjPuSHOW0Y3ybqo8cCspyzu50b+WEoJfQ4Y/+fdhgdIqqarYnMa7BLazZmNJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0a137e7d54d6305cac5e270d530efb8bee0031bc789ab8aa791479793382bbe","last_reissued_at":"2026-05-18T04:08:44.598576Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:08:44.598576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Algorithmic Programming Language Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Klein, Kyle Murray, Simon Weber","submitted_at":"2011-06-21T00:37:23Z","abstract_excerpt":"Motivated by the amount of code that goes unidentified on the web, we introduce a practical method for algorithmically identifying the programming language of source code. Our work is based on supervised learning and intelligent statistical features. We also explored, but abandoned, a grammatical approach. In testing, our implementation greatly outperforms that of an existing tool that relies on a Bayesian classifier. Code is written in Python and available under an MIT license."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1106.4064","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":"1106.4064","created_at":"2026-05-18T04:08:44.598648+00:00"},{"alias_kind":"arxiv_version","alias_value":"1106.4064v2","created_at":"2026-05-18T04:08:44.598648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1106.4064","created_at":"2026-05-18T04:08:44.598648+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCQTPZ6VJVRQ","created_at":"2026-05-18T12:26:47.523578+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCQTPZ6VJVRQLSWF","created_at":"2026-05-18T12:26:47.523578+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCQTPZ6V","created_at":"2026-05-18T12:26:47.523578+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/YCQTPZ6VJVRQLSWF4JYNKMHPXC","json":"https://pith.science/pith/YCQTPZ6VJVRQLSWF4JYNKMHPXC.json","graph_json":"https://pith.science/api/pith-number/YCQTPZ6VJVRQLSWF4JYNKMHPXC/graph.json","events_json":"https://pith.science/api/pith-number/YCQTPZ6VJVRQLSWF4JYNKMHPXC/events.json","paper":"https://pith.science/paper/YCQTPZ6V"},"agent_actions":{"view_html":"https://pith.science/pith/YCQTPZ6VJVRQLSWF4JYNKMHPXC","download_json":"https://pith.science/pith/YCQTPZ6VJVRQLSWF4JYNKMHPXC.json","view_paper":"https://pith.science/paper/YCQTPZ6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1106.4064&json=true","fetch_graph":"https://pith.science/api/pith-number/YCQTPZ6VJVRQLSWF4JYNKMHPXC/graph.json","fetch_events":"https://pith.science/api/pith-number/YCQTPZ6VJVRQLSWF4JYNKMHPXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCQTPZ6VJVRQLSWF4JYNKMHPXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCQTPZ6VJVRQLSWF4JYNKMHPXC/action/storage_attestation","attest_author":"https://pith.science/pith/YCQTPZ6VJVRQLSWF4JYNKMHPXC/action/author_attestation","sign_citation":"https://pith.science/pith/YCQTPZ6VJVRQLSWF4JYNKMHPXC/action/citation_signature","submit_replication":"https://pith.science/pith/YCQTPZ6VJVRQLSWF4JYNKMHPXC/action/replication_record"}},"created_at":"2026-05-18T04:08:44.598648+00:00","updated_at":"2026-05-18T04:08:44.598648+00:00"}