{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LPIBA6DG62RYNYJXKXS5JHUJGO","short_pith_number":"pith:LPIBA6DG","canonical_record":{"source":{"id":"2412.11378","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T02:05:49Z","cross_cats_sorted":[],"title_canon_sha256":"e7a77ed5b253974ada3b43f89c87b91bf9138cfe548e7fdcd7e1dc369207f6a5","abstract_canon_sha256":"867eb794bb6d9704f14bf75d7cf67eb6a47052ba3748510d68090910cdd4ffc4"},"schema_version":"1.0"},"canonical_sha256":"5bd0107866f6a386e13755e5d49e89339f69f3d287ab7cf752fef5287462e448","source":{"kind":"arxiv","id":"2412.11378","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11378","created_at":"2026-07-05T10:02:56Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11378v2","created_at":"2026-07-05T10:02:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11378","created_at":"2026-07-05T10:02:56Z"},{"alias_kind":"pith_short_12","alias_value":"LPIBA6DG62RY","created_at":"2026-07-05T10:02:56Z"},{"alias_kind":"pith_short_16","alias_value":"LPIBA6DG62RYNYJX","created_at":"2026-07-05T10:02:56Z"},{"alias_kind":"pith_short_8","alias_value":"LPIBA6DG","created_at":"2026-07-05T10:02:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LPIBA6DG62RYNYJXKXS5JHUJGO","target":"record","payload":{"canonical_record":{"source":{"id":"2412.11378","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T02:05:49Z","cross_cats_sorted":[],"title_canon_sha256":"e7a77ed5b253974ada3b43f89c87b91bf9138cfe548e7fdcd7e1dc369207f6a5","abstract_canon_sha256":"867eb794bb6d9704f14bf75d7cf67eb6a47052ba3748510d68090910cdd4ffc4"},"schema_version":"1.0"},"canonical_sha256":"5bd0107866f6a386e13755e5d49e89339f69f3d287ab7cf752fef5287462e448","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:56.198982Z","signature_b64":"2F/gGAwcbneY6ps/mXlR0ygOUi7ag3E56862tENwA+9z7bWxNLUSkKeHPFQBBPzkA5f0OjwK7SACtfGWWxs6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bd0107866f6a386e13755e5d49e89339f69f3d287ab7cf752fef5287462e448","last_reissued_at":"2026-07-05T10:02:56.198452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:56.198452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.11378","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":"2026-07-05T10:02:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/VJev3lF3TkofM+HGmUaVNsjOvWL1qDUeo8TuRoKjQhyeYUbJu5y0F5rDHx7WcNnZqKkZQwWXt8FI1885br/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:55:30.062677Z"},"content_sha256":"ae3d0a6ff119c9f5a906f8f58f53de8b87255a7e271375e34721bc9bfafcc956","schema_version":"1.0","event_id":"sha256:ae3d0a6ff119c9f5a906f8f58f53de8b87255a7e271375e34721bc9bfafcc956"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LPIBA6DG62RYNYJXKXS5JHUJGO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FinLoRA: Finetuning Quantized Financial Large Language Models Using Low-Rank Adaptation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Jin, Daniel Kim, Dannong Wang, Steve Yang, Tianfan Fu, Xiao-Yang Liu, Xingjian Zhao","submitted_at":"2024-12-16T02:05:49Z","abstract_excerpt":"Finetuned large language models (LLMs) have shown remarkable performance in financial tasks, such as sentiment analysis and information retrieval. Due to privacy concerns, finetuning and deploying Financial LLMs (FinLLMs) locally are crucial for institutions. However, finetuning FinLLMs poses challenges including GPU memory constraints and long input sequences. In this paper, we employ quantized low-rank adaptation (QLoRA) to finetune FinLLMs, which leverage low-rank matrix decomposition and quantization techniques to significantly reduce computational requirements while maintaining high model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11378","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/2412.11378/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":"2026-07-05T10:02:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rl/ePGVJ0/H58/F8QZyC1iIpvGEZWttEz/O4VIssVnxfXebm43amgZ3HAU7Ix2K660zKr/MsFw7Ebiag/m+zBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:55:30.063104Z"},"content_sha256":"2c9cc59fa3ae297b5b73c46c4ab23fc7d6d91fe1f6506ed1782c904bd043d4c5","schema_version":"1.0","event_id":"sha256:2c9cc59fa3ae297b5b73c46c4ab23fc7d6d91fe1f6506ed1782c904bd043d4c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LPIBA6DG62RYNYJXKXS5JHUJGO/bundle.json","state_url":"https://pith.science/pith/LPIBA6DG62RYNYJXKXS5JHUJGO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LPIBA6DG62RYNYJXKXS5JHUJGO/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":"2026-07-07T06:55:30Z","links":{"resolver":"https://pith.science/pith/LPIBA6DG62RYNYJXKXS5JHUJGO","bundle":"https://pith.science/pith/LPIBA6DG62RYNYJXKXS5JHUJGO/bundle.json","state":"https://pith.science/pith/LPIBA6DG62RYNYJXKXS5JHUJGO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LPIBA6DG62RYNYJXKXS5JHUJGO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LPIBA6DG62RYNYJXKXS5JHUJGO","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":"867eb794bb6d9704f14bf75d7cf67eb6a47052ba3748510d68090910cdd4ffc4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T02:05:49Z","title_canon_sha256":"e7a77ed5b253974ada3b43f89c87b91bf9138cfe548e7fdcd7e1dc369207f6a5"},"schema_version":"1.0","source":{"id":"2412.11378","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11378","created_at":"2026-07-05T10:02:56Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11378v2","created_at":"2026-07-05T10:02:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11378","created_at":"2026-07-05T10:02:56Z"},{"alias_kind":"pith_short_12","alias_value":"LPIBA6DG62RY","created_at":"2026-07-05T10:02:56Z"},{"alias_kind":"pith_short_16","alias_value":"LPIBA6DG62RYNYJX","created_at":"2026-07-05T10:02:56Z"},{"alias_kind":"pith_short_8","alias_value":"LPIBA6DG","created_at":"2026-07-05T10:02:56Z"}],"graph_snapshots":[{"event_id":"sha256:2c9cc59fa3ae297b5b73c46c4ab23fc7d6d91fe1f6506ed1782c904bd043d4c5","target":"graph","created_at":"2026-07-05T10:02:56Z","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/2412.11378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Finetuned large language models (LLMs) have shown remarkable performance in financial tasks, such as sentiment analysis and information retrieval. Due to privacy concerns, finetuning and deploying Financial LLMs (FinLLMs) locally are crucial for institutions. However, finetuning FinLLMs poses challenges including GPU memory constraints and long input sequences. In this paper, we employ quantized low-rank adaptation (QLoRA) to finetune FinLLMs, which leverage low-rank matrix decomposition and quantization techniques to significantly reduce computational requirements while maintaining high model","authors_text":"Bo Jin, Daniel Kim, Dannong Wang, Steve Yang, Tianfan Fu, Xiao-Yang Liu, Xingjian Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T02:05:49Z","title":"FinLoRA: Finetuning Quantized Financial Large Language Models Using Low-Rank Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11378","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:ae3d0a6ff119c9f5a906f8f58f53de8b87255a7e271375e34721bc9bfafcc956","target":"record","created_at":"2026-07-05T10:02:56Z","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":"867eb794bb6d9704f14bf75d7cf67eb6a47052ba3748510d68090910cdd4ffc4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T02:05:49Z","title_canon_sha256":"e7a77ed5b253974ada3b43f89c87b91bf9138cfe548e7fdcd7e1dc369207f6a5"},"schema_version":"1.0","source":{"id":"2412.11378","kind":"arxiv","version":2}},"canonical_sha256":"5bd0107866f6a386e13755e5d49e89339f69f3d287ab7cf752fef5287462e448","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bd0107866f6a386e13755e5d49e89339f69f3d287ab7cf752fef5287462e448","first_computed_at":"2026-07-05T10:02:56.198452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:56.198452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2F/gGAwcbneY6ps/mXlR0ygOUi7ag3E56862tENwA+9z7bWxNLUSkKeHPFQBBPzkA5f0OjwK7SACtfGWWxs6AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:56.198982Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11378","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae3d0a6ff119c9f5a906f8f58f53de8b87255a7e271375e34721bc9bfafcc956","sha256:2c9cc59fa3ae297b5b73c46c4ab23fc7d6d91fe1f6506ed1782c904bd043d4c5"],"state_sha256":"db59b3bd8a32d036a152a9557b91ccd4cc8a35d2424f0fd820ad6745c13e4197"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S2m+hz386sqNo0L6bTBoEBO/vltH3iDTQyCit4+YUYnQT5KKrKRaDH93UBpaXDROibmyh7a+yy+V5hdNkiKEAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:55:30.065194Z","bundle_sha256":"81c0e9fc40890145743c8bdb5d770335ac0b9218013a299a45bd295aa830c992"}}