{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FO622MPUJCX7WRK5SY3SVHWFFJ","short_pith_number":"pith:FO622MPU","canonical_record":{"source":{"id":"2401.01701","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-01-03T12:09:43Z","cross_cats_sorted":[],"title_canon_sha256":"37a71ebc77839b62de2968bb6d31e5ed8b35fe1d0cb825459aad6fda727b561d","abstract_canon_sha256":"dc3fd74dc2f028b2ac58464579f88c9a910d32bc9740fb19302c4c778272f3e8"},"schema_version":"1.0"},"canonical_sha256":"2bbdad31f448affb455d96372a9ec52a4713f902c1a3090ab505e119c54667f9","source":{"kind":"arxiv","id":"2401.01701","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.01701","created_at":"2026-07-05T08:34:09Z"},{"alias_kind":"arxiv_version","alias_value":"2401.01701v3","created_at":"2026-07-05T08:34:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01701","created_at":"2026-07-05T08:34:09Z"},{"alias_kind":"pith_short_12","alias_value":"FO622MPUJCX7","created_at":"2026-07-05T08:34:09Z"},{"alias_kind":"pith_short_16","alias_value":"FO622MPUJCX7WRK5","created_at":"2026-07-05T08:34:09Z"},{"alias_kind":"pith_short_8","alias_value":"FO622MPU","created_at":"2026-07-05T08:34:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FO622MPUJCX7WRK5SY3SVHWFFJ","target":"record","payload":{"canonical_record":{"source":{"id":"2401.01701","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-01-03T12:09:43Z","cross_cats_sorted":[],"title_canon_sha256":"37a71ebc77839b62de2968bb6d31e5ed8b35fe1d0cb825459aad6fda727b561d","abstract_canon_sha256":"dc3fd74dc2f028b2ac58464579f88c9a910d32bc9740fb19302c4c778272f3e8"},"schema_version":"1.0"},"canonical_sha256":"2bbdad31f448affb455d96372a9ec52a4713f902c1a3090ab505e119c54667f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:09.561845Z","signature_b64":"JPBF8yDv8vrHFKvFi06ZRXQWj5PmarlLMwdk4l1XusLb1LDk28+Vg0iKQNdjsBWQh70SkE0hoJGwwHr1M0OUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bbdad31f448affb455d96372a9ec52a4713f902c1a3090ab505e119c54667f9","last_reissued_at":"2026-07-05T08:34:09.561357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:09.561357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.01701","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:34:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E21AM4i6/MYle9CVaozdIhFqKjfWZdo/UKEKlZxDgUZvMCY9M759LMG/B0cwSwL33JwMOiKdymTUlz67L5ESAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T06:43:43.827172Z"},"content_sha256":"2188d7bd427ed20a50cae364384f34fd43cd8dfdde4e05e700750b21b6380e69","schema_version":"1.0","event_id":"sha256:2188d7bd427ed20a50cae364384f34fd43cd8dfdde4e05e700750b21b6380e69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FO622MPUJCX7WRK5SY3SVHWFFJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"De-Hallucinator: Mitigating LLM Hallucinations in Code Generation Tasks via Iterative Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Aryaz Eghbali, Michael Pradel","submitted_at":"2024-01-03T12:09:43Z","abstract_excerpt":"Large language models (LLMs) trained on datasets of publicly available source code have established a new state of the art in code generation tasks. However, these models are mostly unaware of the code that exists within a specific project, preventing the models from making good use of existing APIs. Instead, LLMs often invent, or \"hallucinate\", non-existent APIs or produce variants of already existing code. This paper presents De-Hallucinator, a technique that grounds the predictions of an LLM through a novel combination of retrieving suitable API references and iteratively querying the model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01701","kind":"arxiv","version":3},"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/2401.01701/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":"2026-07-05T08:34:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qot1TcDV0XY+sU/1EiWCXGHCXL4ZZiAyBZ1sn/8s/w7cc+yVo8jRRFL1d93HFImQPMmh1bloIyaGf08QoZ27Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T06:43:43.827568Z"},"content_sha256":"38e763a114ca6d32c17cd509d39f1dfc30d637e62781092e10b1aaebf5e771bc","schema_version":"1.0","event_id":"sha256:38e763a114ca6d32c17cd509d39f1dfc30d637e62781092e10b1aaebf5e771bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FO622MPUJCX7WRK5SY3SVHWFFJ/bundle.json","state_url":"https://pith.science/pith/FO622MPUJCX7WRK5SY3SVHWFFJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FO622MPUJCX7WRK5SY3SVHWFFJ/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":"2026-07-16T06:43:43Z","links":{"resolver":"https://pith.science/pith/FO622MPUJCX7WRK5SY3SVHWFFJ","bundle":"https://pith.science/pith/FO622MPUJCX7WRK5SY3SVHWFFJ/bundle.json","state":"https://pith.science/pith/FO622MPUJCX7WRK5SY3SVHWFFJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FO622MPUJCX7WRK5SY3SVHWFFJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FO622MPUJCX7WRK5SY3SVHWFFJ","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":"dc3fd74dc2f028b2ac58464579f88c9a910d32bc9740fb19302c4c778272f3e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-01-03T12:09:43Z","title_canon_sha256":"37a71ebc77839b62de2968bb6d31e5ed8b35fe1d0cb825459aad6fda727b561d"},"schema_version":"1.0","source":{"id":"2401.01701","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.01701","created_at":"2026-07-05T08:34:09Z"},{"alias_kind":"arxiv_version","alias_value":"2401.01701v3","created_at":"2026-07-05T08:34:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01701","created_at":"2026-07-05T08:34:09Z"},{"alias_kind":"pith_short_12","alias_value":"FO622MPUJCX7","created_at":"2026-07-05T08:34:09Z"},{"alias_kind":"pith_short_16","alias_value":"FO622MPUJCX7WRK5","created_at":"2026-07-05T08:34:09Z"},{"alias_kind":"pith_short_8","alias_value":"FO622MPU","created_at":"2026-07-05T08:34:09Z"}],"graph_snapshots":[{"event_id":"sha256:38e763a114ca6d32c17cd509d39f1dfc30d637e62781092e10b1aaebf5e771bc","target":"graph","created_at":"2026-07-05T08:34:09Z","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/2401.01701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) trained on datasets of publicly available source code have established a new state of the art in code generation tasks. However, these models are mostly unaware of the code that exists within a specific project, preventing the models from making good use of existing APIs. Instead, LLMs often invent, or \"hallucinate\", non-existent APIs or produce variants of already existing code. This paper presents De-Hallucinator, a technique that grounds the predictions of an LLM through a novel combination of retrieving suitable API references and iteratively querying the model","authors_text":"Aryaz Eghbali, Michael Pradel","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-01-03T12:09:43Z","title":"De-Hallucinator: Mitigating LLM Hallucinations in Code Generation Tasks via Iterative Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01701","kind":"arxiv","version":3},"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":"sha256:2188d7bd427ed20a50cae364384f34fd43cd8dfdde4e05e700750b21b6380e69","target":"record","created_at":"2026-07-05T08:34:09Z","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":"dc3fd74dc2f028b2ac58464579f88c9a910d32bc9740fb19302c4c778272f3e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-01-03T12:09:43Z","title_canon_sha256":"37a71ebc77839b62de2968bb6d31e5ed8b35fe1d0cb825459aad6fda727b561d"},"schema_version":"1.0","source":{"id":"2401.01701","kind":"arxiv","version":3}},"canonical_sha256":"2bbdad31f448affb455d96372a9ec52a4713f902c1a3090ab505e119c54667f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bbdad31f448affb455d96372a9ec52a4713f902c1a3090ab505e119c54667f9","first_computed_at":"2026-07-05T08:34:09.561357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:09.561357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JPBF8yDv8vrHFKvFi06ZRXQWj5PmarlLMwdk4l1XusLb1LDk28+Vg0iKQNdjsBWQh70SkE0hoJGwwHr1M0OUDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:09.561845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.01701","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2188d7bd427ed20a50cae364384f34fd43cd8dfdde4e05e700750b21b6380e69","sha256:38e763a114ca6d32c17cd509d39f1dfc30d637e62781092e10b1aaebf5e771bc"],"state_sha256":"a53ea6e3bc8fd930a9590360f7cca7db910191975afb4598656c4854a7a7aae6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZExkwdNXgsRGtFNrv90LhmYJHi3kWI8z3Y31D1HvVZG9qoqzXZLyTi96kBYdjM/BJQ05a0uDApjzmkZciywCDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T06:43:43.830037Z","bundle_sha256":"65835868ef770c3e2009c2a24108709e196f4c74dfea1016cf789f5baef438aa"}}