{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RPR3MPOHDDYBSY4CAVIOFEDO52","short_pith_number":"pith:RPR3MPOH","canonical_record":{"source":{"id":"2402.13414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T22:50:41Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4f9c96b03582670d147993bb7fd9f6e8eef98fb766a288a6f9421efbad77a636","abstract_canon_sha256":"dafb7bf11473bb2f1810b161a60d864607a248cf60b5e2b654b0329a75fe50fb"},"schema_version":"1.0"},"canonical_sha256":"8be3b63dc718f01963820550e2906eee9c8715180034e9fae2295ca1799bf48d","source":{"kind":"arxiv","id":"2402.13414","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13414","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13414v2","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13414","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"pith_short_12","alias_value":"RPR3MPOHDDYB","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"pith_short_16","alias_value":"RPR3MPOHDDYBSY4C","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"pith_short_8","alias_value":"RPR3MPOH","created_at":"2026-07-05T08:36:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RPR3MPOHDDYBSY4CAVIOFEDO52","target":"record","payload":{"canonical_record":{"source":{"id":"2402.13414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T22:50:41Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4f9c96b03582670d147993bb7fd9f6e8eef98fb766a288a6f9421efbad77a636","abstract_canon_sha256":"dafb7bf11473bb2f1810b161a60d864607a248cf60b5e2b654b0329a75fe50fb"},"schema_version":"1.0"},"canonical_sha256":"8be3b63dc718f01963820550e2906eee9c8715180034e9fae2295ca1799bf48d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:22.853123Z","signature_b64":"R1PGz3Kk2SWG0koALtvkyk1bGV2V8AR/S9oLUKgtogEjAsTNkM7Z9fyt2mjQi82y3meCr6HZDqOb29YbnuHvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8be3b63dc718f01963820550e2906eee9c8715180034e9fae2295ca1799bf48d","last_reissued_at":"2026-07-05T08:36:22.852636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:22.852636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.13414","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:36:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fOH1btlifTmqAFFuKQG/pEfaRhBq16H7kMPDIfxWDowvw3cPcdsN0wFe7oqXgBPoE/34pBByPXfbZXe0s4p2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:27:04.238123Z"},"content_sha256":"be687cc47a431ce5b1c743798e798ef5d13b894bf3836ae25d44400c75f498c8","schema_version":"1.0","event_id":"sha256:be687cc47a431ce5b1c743798e798ef5d13b894bf3836ae25d44400c75f498c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RPR3MPOHDDYBSY4CAVIOFEDO52","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Harnessing Large Language Models as Post-hoc Correctors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Davide Mottin, Kuangyu Zhou, Zhiqiang Zhong","submitted_at":"2024-02-20T22:50:41Z","abstract_excerpt":"As Machine Learning (ML) models grow in size and demand higher-quality training data, the expenses associated with re-training and fine-tuning these models are escalating rapidly. Inspired by recent impressive achievements of Large Language Models (LLMs) in different fields, this paper delves into the question: can LLMs efficiently improve an ML's performance at a minimal cost? We show that, through our proposed training-free framework LlmCorr, an LLM can work as a post-hoc corrector to propose corrections for the predictions of an arbitrary ML model. In particular, we form a contextual knowle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13414","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.13414/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":"2026-07-05T08:36:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5kQCJ4I6DO2NHa2HYB/SBPwO83IHYVGuOCrnal4Z8cib7TE8/lECTuAzFS4YWvOLrorFCl4T3YvuVa+DOdhmBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:27:04.238619Z"},"content_sha256":"c8da3e8d51914f87321932dbabd8f3e0e28177c5cab9e555f59c171e1dfe578d","schema_version":"1.0","event_id":"sha256:c8da3e8d51914f87321932dbabd8f3e0e28177c5cab9e555f59c171e1dfe578d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RPR3MPOHDDYBSY4CAVIOFEDO52/bundle.json","state_url":"https://pith.science/pith/RPR3MPOHDDYBSY4CAVIOFEDO52/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RPR3MPOHDDYBSY4CAVIOFEDO52/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":"2026-08-08T08:27:04Z","links":{"resolver":"https://pith.science/pith/RPR3MPOHDDYBSY4CAVIOFEDO52","bundle":"https://pith.science/pith/RPR3MPOHDDYBSY4CAVIOFEDO52/bundle.json","state":"https://pith.science/pith/RPR3MPOHDDYBSY4CAVIOFEDO52/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RPR3MPOHDDYBSY4CAVIOFEDO52/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RPR3MPOHDDYBSY4CAVIOFEDO52","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":"dafb7bf11473bb2f1810b161a60d864607a248cf60b5e2b654b0329a75fe50fb","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T22:50:41Z","title_canon_sha256":"4f9c96b03582670d147993bb7fd9f6e8eef98fb766a288a6f9421efbad77a636"},"schema_version":"1.0","source":{"id":"2402.13414","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13414","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13414v2","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13414","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"pith_short_12","alias_value":"RPR3MPOHDDYB","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"pith_short_16","alias_value":"RPR3MPOHDDYBSY4C","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"pith_short_8","alias_value":"RPR3MPOH","created_at":"2026-07-05T08:36:22Z"}],"graph_snapshots":[{"event_id":"sha256:c8da3e8d51914f87321932dbabd8f3e0e28177c5cab9e555f59c171e1dfe578d","target":"graph","created_at":"2026-07-05T08:36:22Z","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/2402.13414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Machine Learning (ML) models grow in size and demand higher-quality training data, the expenses associated with re-training and fine-tuning these models are escalating rapidly. Inspired by recent impressive achievements of Large Language Models (LLMs) in different fields, this paper delves into the question: can LLMs efficiently improve an ML's performance at a minimal cost? We show that, through our proposed training-free framework LlmCorr, an LLM can work as a post-hoc corrector to propose corrections for the predictions of an arbitrary ML model. In particular, we form a contextual knowle","authors_text":"Davide Mottin, Kuangyu Zhou, Zhiqiang Zhong","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T22:50:41Z","title":"Harnessing Large Language Models as Post-hoc Correctors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13414","kind":"arxiv","version":2},"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:be687cc47a431ce5b1c743798e798ef5d13b894bf3836ae25d44400c75f498c8","target":"record","created_at":"2026-07-05T08:36:22Z","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":"dafb7bf11473bb2f1810b161a60d864607a248cf60b5e2b654b0329a75fe50fb","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T22:50:41Z","title_canon_sha256":"4f9c96b03582670d147993bb7fd9f6e8eef98fb766a288a6f9421efbad77a636"},"schema_version":"1.0","source":{"id":"2402.13414","kind":"arxiv","version":2}},"canonical_sha256":"8be3b63dc718f01963820550e2906eee9c8715180034e9fae2295ca1799bf48d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8be3b63dc718f01963820550e2906eee9c8715180034e9fae2295ca1799bf48d","first_computed_at":"2026-07-05T08:36:22.852636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:22.852636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R1PGz3Kk2SWG0koALtvkyk1bGV2V8AR/S9oLUKgtogEjAsTNkM7Z9fyt2mjQi82y3meCr6HZDqOb29YbnuHvAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:22.853123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13414","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be687cc47a431ce5b1c743798e798ef5d13b894bf3836ae25d44400c75f498c8","sha256:c8da3e8d51914f87321932dbabd8f3e0e28177c5cab9e555f59c171e1dfe578d"],"state_sha256":"a22613964040dc134568d2129c22a9822bf7dfeb392b94c67102481238d22b3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I9K6vRLV+ydRtQvA2HVyflQUjRgJbldGeDdaycksSFwMavl9Ae9gDYoFZA/jeOnaIt8BIUF0S7abBmb600MaCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:27:04.243623Z","bundle_sha256":"2f7028a0fb708fb5de9a3af63bda43f2c9368f2f3bf1d457ad7bb887cc2ed7a9"}}