{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:X4KC45JUBABIGRT7IBIRUJ22NQ","short_pith_number":"pith:X4KC45JU","canonical_record":{"source":{"id":"2407.04173","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-04T22:22:09Z","cross_cats_sorted":["cs.AI","cs.CY","stat.ML"],"title_canon_sha256":"bf3c9371f638f31ce5f1f8b15ee73f2053d80c761db09b48cad6da4914e254a6","abstract_canon_sha256":"aa0ed06667f3a90e936848284e2bc8520f572760e8d330dd69131b1d74e9917c"},"schema_version":"1.0"},"canonical_sha256":"bf142e7534080283467f40511a275a6c1d19f49e854d063d37e4e0da4ca257cf","source":{"kind":"arxiv","id":"2407.04173","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04173","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04173v2","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04173","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_12","alias_value":"X4KC45JUBABI","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_16","alias_value":"X4KC45JUBABIGRT7","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_8","alias_value":"X4KC45JU","created_at":"2026-07-05T11:15:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:X4KC45JUBABIGRT7IBIRUJ22NQ","target":"record","payload":{"canonical_record":{"source":{"id":"2407.04173","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-04T22:22:09Z","cross_cats_sorted":["cs.AI","cs.CY","stat.ML"],"title_canon_sha256":"bf3c9371f638f31ce5f1f8b15ee73f2053d80c761db09b48cad6da4914e254a6","abstract_canon_sha256":"aa0ed06667f3a90e936848284e2bc8520f572760e8d330dd69131b1d74e9917c"},"schema_version":"1.0"},"canonical_sha256":"bf142e7534080283467f40511a275a6c1d19f49e854d063d37e4e0da4ca257cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:38.372179Z","signature_b64":"WLL38thUtPLzCUC1UkzsuxpqSbEiIA44mrVnThUhhXhydPd36Zb0G9ETyMj+eV7jF63/zZbVqsYifXgITc+vCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf142e7534080283467f40511a275a6c1d19f49e854d063d37e4e0da4ca257cf","last_reissued_at":"2026-07-05T11:15:38.371464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:38.371464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.04173","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":"2026-07-05T11:15:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JI/cfJwkzFD6p9xLibtYXAFetBpZUzsRu+Frm2jjzeumy5r4/XvrR58CQqf785LQR4P/neJJoZ1plvd6zDG7AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:23:51.637215Z"},"content_sha256":"2a3b6229b5d48167cd2dc34a4722d82a6c72a3aff690518c816a18081430e4e4","schema_version":"1.0","event_id":"sha256:2a3b6229b5d48167cd2dc34a4722d82a6c72a3aff690518c816a18081430e4e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:X4KC45JUBABIGRT7IBIRUJ22NQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantifying Prediction Consistency Under Fine-Tuning Multiplicity in Tabular LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Faisal Hamman, Freddy Lecue, Pasan Dissanayake, Sanghamitra Dutta, Saumitra Mishra","submitted_at":"2024-07-04T22:22:09Z","abstract_excerpt":"Fine-tuning LLMs on tabular classification tasks can lead to the phenomenon of fine-tuning multiplicity where equally well-performing models make conflicting predictions on the same input. Fine-tuning multiplicity can arise due to variations in the training process, e.g., seed, weight initialization, minor changes to training data, etc., raising concerns about the reliability of Tabular LLMs in high-stakes applications such as finance, hiring, education, healthcare. Our work formalizes this unique challenge of fine-tuning multiplicity in Tabular LLMs and proposes a novel measure to quantify th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04173","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/2407.04173/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":"2026-07-05T11:15:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tw/bdaXw/ODKJbPgmXBAadZu3ACGwyn4TKpZSBR7+V/OxmC8czv5MShWGqgLlP8FKPfBEa2S6WIklqdom+HfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:23:51.637729Z"},"content_sha256":"c99b6596b57fbba0391b58158112b4c540f7265715a60da707992ce2c9d0af86","schema_version":"1.0","event_id":"sha256:c99b6596b57fbba0391b58158112b4c540f7265715a60da707992ce2c9d0af86"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X4KC45JUBABIGRT7IBIRUJ22NQ/bundle.json","state_url":"https://pith.science/pith/X4KC45JUBABIGRT7IBIRUJ22NQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X4KC45JUBABIGRT7IBIRUJ22NQ/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":"2026-08-10T06:23:51Z","links":{"resolver":"https://pith.science/pith/X4KC45JUBABIGRT7IBIRUJ22NQ","bundle":"https://pith.science/pith/X4KC45JUBABIGRT7IBIRUJ22NQ/bundle.json","state":"https://pith.science/pith/X4KC45JUBABIGRT7IBIRUJ22NQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X4KC45JUBABIGRT7IBIRUJ22NQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X4KC45JUBABIGRT7IBIRUJ22NQ","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":"aa0ed06667f3a90e936848284e2bc8520f572760e8d330dd69131b1d74e9917c","cross_cats_sorted":["cs.AI","cs.CY","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-04T22:22:09Z","title_canon_sha256":"bf3c9371f638f31ce5f1f8b15ee73f2053d80c761db09b48cad6da4914e254a6"},"schema_version":"1.0","source":{"id":"2407.04173","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04173","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04173v2","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04173","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_12","alias_value":"X4KC45JUBABI","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_16","alias_value":"X4KC45JUBABIGRT7","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_8","alias_value":"X4KC45JU","created_at":"2026-07-05T11:15:38Z"}],"graph_snapshots":[{"event_id":"sha256:c99b6596b57fbba0391b58158112b4c540f7265715a60da707992ce2c9d0af86","target":"graph","created_at":"2026-07-05T11:15:38Z","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/2407.04173/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning LLMs on tabular classification tasks can lead to the phenomenon of fine-tuning multiplicity where equally well-performing models make conflicting predictions on the same input. Fine-tuning multiplicity can arise due to variations in the training process, e.g., seed, weight initialization, minor changes to training data, etc., raising concerns about the reliability of Tabular LLMs in high-stakes applications such as finance, hiring, education, healthcare. Our work formalizes this unique challenge of fine-tuning multiplicity in Tabular LLMs and proposes a novel measure to quantify th","authors_text":"Faisal Hamman, Freddy Lecue, Pasan Dissanayake, Sanghamitra Dutta, Saumitra Mishra","cross_cats":["cs.AI","cs.CY","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-04T22:22:09Z","title":"Quantifying Prediction Consistency Under Fine-Tuning Multiplicity in Tabular LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04173","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":"sha256:2a3b6229b5d48167cd2dc34a4722d82a6c72a3aff690518c816a18081430e4e4","target":"record","created_at":"2026-07-05T11:15:38Z","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":"aa0ed06667f3a90e936848284e2bc8520f572760e8d330dd69131b1d74e9917c","cross_cats_sorted":["cs.AI","cs.CY","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-04T22:22:09Z","title_canon_sha256":"bf3c9371f638f31ce5f1f8b15ee73f2053d80c761db09b48cad6da4914e254a6"},"schema_version":"1.0","source":{"id":"2407.04173","kind":"arxiv","version":2}},"canonical_sha256":"bf142e7534080283467f40511a275a6c1d19f49e854d063d37e4e0da4ca257cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf142e7534080283467f40511a275a6c1d19f49e854d063d37e4e0da4ca257cf","first_computed_at":"2026-07-05T11:15:38.371464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:38.371464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WLL38thUtPLzCUC1UkzsuxpqSbEiIA44mrVnThUhhXhydPd36Zb0G9ETyMj+eV7jF63/zZbVqsYifXgITc+vCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:38.372179Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04173","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a3b6229b5d48167cd2dc34a4722d82a6c72a3aff690518c816a18081430e4e4","sha256:c99b6596b57fbba0391b58158112b4c540f7265715a60da707992ce2c9d0af86"],"state_sha256":"42c7c9c22841b980c344ec7db06ccbdf3a96dea366ec95cd0a0734eda97b8b3a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2gtXppufcQC90KT54DoBV5A3/EfrTs2T7EXGInzjNrd6DslBDRXajtaQK1v/Rk6koSg61/ToP4cu8+yp5EYgCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:23:51.642783Z","bundle_sha256":"13a4fad0efba8cf8de97290d5e07540194aafd29ce3934575ce3c2d68c556963"}}