{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GROVDYIH2LP2ITVI4TC4VI6X4J","short_pith_number":"pith:GROVDYIH","canonical_record":{"source":{"id":"2412.08291","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T11:07:50Z","cross_cats_sorted":[],"title_canon_sha256":"506902388de046630cffa40b46567a4b9126fdde0501dea248588a4e651a86cc","abstract_canon_sha256":"aaacf56be8640f3cb48da04aca902b5d33ea064edd331e7c959376f76b41c2ab"},"schema_version":"1.0"},"canonical_sha256":"345d51e107d2dfa44ea8e4c5caa3d7e249b160e237d182e52f64070d6b1ce949","source":{"kind":"arxiv","id":"2412.08291","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08291","created_at":"2026-07-05T09:47:47Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08291v1","created_at":"2026-07-05T09:47:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08291","created_at":"2026-07-05T09:47:47Z"},{"alias_kind":"pith_short_12","alias_value":"GROVDYIH2LP2","created_at":"2026-07-05T09:47:47Z"},{"alias_kind":"pith_short_16","alias_value":"GROVDYIH2LP2ITVI","created_at":"2026-07-05T09:47:47Z"},{"alias_kind":"pith_short_8","alias_value":"GROVDYIH","created_at":"2026-07-05T09:47:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GROVDYIH2LP2ITVI4TC4VI6X4J","target":"record","payload":{"canonical_record":{"source":{"id":"2412.08291","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T11:07:50Z","cross_cats_sorted":[],"title_canon_sha256":"506902388de046630cffa40b46567a4b9126fdde0501dea248588a4e651a86cc","abstract_canon_sha256":"aaacf56be8640f3cb48da04aca902b5d33ea064edd331e7c959376f76b41c2ab"},"schema_version":"1.0"},"canonical_sha256":"345d51e107d2dfa44ea8e4c5caa3d7e249b160e237d182e52f64070d6b1ce949","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:47.814296Z","signature_b64":"F5cZj4tutIdJRr/8dPtWOwo3t1S5qaVDG3g5hLAuKZttsg38etGnNyDZH4u/wAGPVC5rC+kFrrMCPawsi+gGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"345d51e107d2dfa44ea8e4c5caa3d7e249b160e237d182e52f64070d6b1ce949","last_reissued_at":"2026-07-05T09:47:47.813800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:47.813800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.08291","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":"2026-07-05T09:47:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tzHn8UGwxg7aqHSVg5z6jHDWAkNGqrmhhNzUOn8gX1dbAx31tnuvqv6Cj/0zMPGBVDQasqDB1yQB0B43jt7kBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T15:00:12.513657Z"},"content_sha256":"a01622227ae24ed74459a895fe11e1c8ce3aa75139dc417a56ae1828dee54169","schema_version":"1.0","event_id":"sha256:a01622227ae24ed74459a895fe11e1c8ce3aa75139dc417a56ae1828dee54169"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GROVDYIH2LP2ITVI4TC4VI6X4J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Code LLMs: A Taxonomy-based Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian Newman, Marcos Zampieri, Nishat Raihan","submitted_at":"2024-12-11T11:07:50Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities across various NLP tasks and have recently expanded their impact to coding tasks, bridging the gap between natural languages (NL) and programming languages (PL). This taxonomy-based survey provides a comprehensive analysis of LLMs in the NL-PL domain, investigating how these models are utilized in coding tasks and examining their methodologies, architectures, and training processes. We propose a taxonomy-based framework that categorizes relevant concepts, providing a unified classification system to facilitate a deeper unde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08291","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/2412.08291/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:47:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ew+D21HOS1llBffwfGCe70UF3mm7R8swGs8Sgs6gj+GonjA2Ptj/RRTXjWK1xMCotTtisptbvhtRj176llDbAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T15:00:12.514296Z"},"content_sha256":"7e1b6e59f4e900a7370b242f2bbefc3e4ed89d1bfd67d61e4a8e198a3b94b9d7","schema_version":"1.0","event_id":"sha256:7e1b6e59f4e900a7370b242f2bbefc3e4ed89d1bfd67d61e4a8e198a3b94b9d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GROVDYIH2LP2ITVI4TC4VI6X4J/bundle.json","state_url":"https://pith.science/pith/GROVDYIH2LP2ITVI4TC4VI6X4J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GROVDYIH2LP2ITVI4TC4VI6X4J/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":"2026-07-11T15:00:12Z","links":{"resolver":"https://pith.science/pith/GROVDYIH2LP2ITVI4TC4VI6X4J","bundle":"https://pith.science/pith/GROVDYIH2LP2ITVI4TC4VI6X4J/bundle.json","state":"https://pith.science/pith/GROVDYIH2LP2ITVI4TC4VI6X4J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GROVDYIH2LP2ITVI4TC4VI6X4J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GROVDYIH2LP2ITVI4TC4VI6X4J","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":"aaacf56be8640f3cb48da04aca902b5d33ea064edd331e7c959376f76b41c2ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T11:07:50Z","title_canon_sha256":"506902388de046630cffa40b46567a4b9126fdde0501dea248588a4e651a86cc"},"schema_version":"1.0","source":{"id":"2412.08291","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08291","created_at":"2026-07-05T09:47:47Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08291v1","created_at":"2026-07-05T09:47:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08291","created_at":"2026-07-05T09:47:47Z"},{"alias_kind":"pith_short_12","alias_value":"GROVDYIH2LP2","created_at":"2026-07-05T09:47:47Z"},{"alias_kind":"pith_short_16","alias_value":"GROVDYIH2LP2ITVI","created_at":"2026-07-05T09:47:47Z"},{"alias_kind":"pith_short_8","alias_value":"GROVDYIH","created_at":"2026-07-05T09:47:47Z"}],"graph_snapshots":[{"event_id":"sha256:7e1b6e59f4e900a7370b242f2bbefc3e4ed89d1bfd67d61e4a8e198a3b94b9d7","target":"graph","created_at":"2026-07-05T09:47:47Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.08291/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities across various NLP tasks and have recently expanded their impact to coding tasks, bridging the gap between natural languages (NL) and programming languages (PL). This taxonomy-based survey provides a comprehensive analysis of LLMs in the NL-PL domain, investigating how these models are utilized in coding tasks and examining their methodologies, architectures, and training processes. We propose a taxonomy-based framework that categorizes relevant concepts, providing a unified classification system to facilitate a deeper unde","authors_text":"Christian Newman, Marcos Zampieri, Nishat Raihan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T11:07:50Z","title":"Code LLMs: A Taxonomy-based Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08291","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:a01622227ae24ed74459a895fe11e1c8ce3aa75139dc417a56ae1828dee54169","target":"record","created_at":"2026-07-05T09:47:47Z","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":"aaacf56be8640f3cb48da04aca902b5d33ea064edd331e7c959376f76b41c2ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T11:07:50Z","title_canon_sha256":"506902388de046630cffa40b46567a4b9126fdde0501dea248588a4e651a86cc"},"schema_version":"1.0","source":{"id":"2412.08291","kind":"arxiv","version":1}},"canonical_sha256":"345d51e107d2dfa44ea8e4c5caa3d7e249b160e237d182e52f64070d6b1ce949","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"345d51e107d2dfa44ea8e4c5caa3d7e249b160e237d182e52f64070d6b1ce949","first_computed_at":"2026-07-05T09:47:47.813800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:47.813800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F5cZj4tutIdJRr/8dPtWOwo3t1S5qaVDG3g5hLAuKZttsg38etGnNyDZH4u/wAGPVC5rC+kFrrMCPawsi+gGBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:47.814296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08291","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a01622227ae24ed74459a895fe11e1c8ce3aa75139dc417a56ae1828dee54169","sha256:7e1b6e59f4e900a7370b242f2bbefc3e4ed89d1bfd67d61e4a8e198a3b94b9d7"],"state_sha256":"becb9fc37b4010f6a1b39bfaf772b220ee160df808481bbe814d8ec947ef5cb0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rFQXYchrR9Fo0tJwGmSSMzm/kXnhd7Dn7KrTXB51BI/1AjvT0Z65ZHkIwVdXHXYjrRAYg9tn9KwD+H//2GfgAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T15:00:12.517489Z","bundle_sha256":"ad26699b3ac0dbaec12532a32a8297b9c97437cb0b867105d3d5e48eebfce470"}}