{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EUQJ3IU7LA55YYNVGCIABTUGBY","short_pith_number":"pith:EUQJ3IU7","canonical_record":{"source":{"id":"2410.01109","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-01T22:35:56Z","cross_cats_sorted":["cs.CE","cs.CL"],"title_canon_sha256":"d8ec616653b58cdba8904ac391e0f8c04c5d490aecc0f66d00108e4299d0917d","abstract_canon_sha256":"fde7e10525922fb2706c91f217c63319b995a36bcc8c28208f715d3228839dec"},"schema_version":"1.0"},"canonical_sha256":"25209da29f583bdc61b5309000ce860e11b8eabe41c96af37e73c6fb38e0e7e8","source":{"kind":"arxiv","id":"2410.01109","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01109","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01109v2","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01109","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_12","alias_value":"EUQJ3IU7LA55","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_16","alias_value":"EUQJ3IU7LA55YYNV","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_8","alias_value":"EUQJ3IU7","created_at":"2026-07-05T09:44:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EUQJ3IU7LA55YYNVGCIABTUGBY","target":"record","payload":{"canonical_record":{"source":{"id":"2410.01109","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-01T22:35:56Z","cross_cats_sorted":["cs.CE","cs.CL"],"title_canon_sha256":"d8ec616653b58cdba8904ac391e0f8c04c5d490aecc0f66d00108e4299d0917d","abstract_canon_sha256":"fde7e10525922fb2706c91f217c63319b995a36bcc8c28208f715d3228839dec"},"schema_version":"1.0"},"canonical_sha256":"25209da29f583bdc61b5309000ce860e11b8eabe41c96af37e73c6fb38e0e7e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:36.057697Z","signature_b64":"AQrYR5s8hNJp2p8EB4wnd69+9p6qxLv0xZHy0IqZFqruncIitlSEMnUPo/r20p1xr51FSwMJuvr6xICxITAQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25209da29f583bdc61b5309000ce860e11b8eabe41c96af37e73c6fb38e0e7e8","last_reissued_at":"2026-07-05T09:44:36.057011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:36.057011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.01109","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":"2026-07-05T09:44:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QI2I+WrB1OeuePgRqiMZdoRO+pghpmtHJfV1MEd4UaIz77FK6Z5d6qLQnQFq4+Ei/i+T9uy5+gdVqcCMsCVoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:15:09.309049Z"},"content_sha256":"81dea3570e30d668a4f439e312feb67c4b4461bbc485e0c9ef4219e9bbaf601a","schema_version":"1.0","event_id":"sha256:81dea3570e30d668a4f439e312feb67c4b4461bbc485e0c9ef4219e9bbaf601a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EUQJ3IU7LA55YYNVGCIABTUGBY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mixing It Up: The Cocktail Effect of Multi-Task Fine-Tuning on LLM Performance -- A Case Study in Finance","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CE","cs.CL"],"primary_cat":"cs.AI","authors_text":"Eitam Sheetrit, Gil Shenderovitz, Meni Brief, Noga Ben Yoash, Oded Ovadia, Rachel Lemberg","submitted_at":"2024-10-01T22:35:56Z","abstract_excerpt":"The application of large language models (LLMs) in domain-specific contexts, including finance, has expanded rapidly. Domain-specific LLMs are typically evaluated based on their performance in various downstream tasks relevant to the domain. In this work, we present a detailed analysis of fine-tuning LLMs for such tasks. Somewhat counterintuitively, we find that in domain-specific cases, fine-tuning exclusively on the target task is not always the most effective strategy. Instead, multi-task finetuning - where models are trained on a cocktail of related tasks - can significantly enhance perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01109","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/2410.01109/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":"2026-07-05T09:44:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"piZ1uxWC1SJWoN8hI0yHRQsdKANprj4xaJUnD4B1G1hde93OGlMap+d0oJpWDvxIG1apttVSlIBUGBoTL5CXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:15:09.309433Z"},"content_sha256":"0becae00484604567d98958aee6235c69dbd120ad54b5d6bbba2df0b2f13fc32","schema_version":"1.0","event_id":"sha256:0becae00484604567d98958aee6235c69dbd120ad54b5d6bbba2df0b2f13fc32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EUQJ3IU7LA55YYNVGCIABTUGBY/bundle.json","state_url":"https://pith.science/pith/EUQJ3IU7LA55YYNVGCIABTUGBY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EUQJ3IU7LA55YYNVGCIABTUGBY/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":"2026-07-06T16:15:09Z","links":{"resolver":"https://pith.science/pith/EUQJ3IU7LA55YYNVGCIABTUGBY","bundle":"https://pith.science/pith/EUQJ3IU7LA55YYNVGCIABTUGBY/bundle.json","state":"https://pith.science/pith/EUQJ3IU7LA55YYNVGCIABTUGBY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EUQJ3IU7LA55YYNVGCIABTUGBY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EUQJ3IU7LA55YYNVGCIABTUGBY","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":"fde7e10525922fb2706c91f217c63319b995a36bcc8c28208f715d3228839dec","cross_cats_sorted":["cs.CE","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-01T22:35:56Z","title_canon_sha256":"d8ec616653b58cdba8904ac391e0f8c04c5d490aecc0f66d00108e4299d0917d"},"schema_version":"1.0","source":{"id":"2410.01109","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01109","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01109v2","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01109","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_12","alias_value":"EUQJ3IU7LA55","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_16","alias_value":"EUQJ3IU7LA55YYNV","created_at":"2026-07-05T09:44:36Z"},{"alias_kind":"pith_short_8","alias_value":"EUQJ3IU7","created_at":"2026-07-05T09:44:36Z"}],"graph_snapshots":[{"event_id":"sha256:0becae00484604567d98958aee6235c69dbd120ad54b5d6bbba2df0b2f13fc32","target":"graph","created_at":"2026-07-05T09:44:36Z","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/2410.01109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The application of large language models (LLMs) in domain-specific contexts, including finance, has expanded rapidly. Domain-specific LLMs are typically evaluated based on their performance in various downstream tasks relevant to the domain. In this work, we present a detailed analysis of fine-tuning LLMs for such tasks. Somewhat counterintuitively, we find that in domain-specific cases, fine-tuning exclusively on the target task is not always the most effective strategy. Instead, multi-task finetuning - where models are trained on a cocktail of related tasks - can significantly enhance perfor","authors_text":"Eitam Sheetrit, Gil Shenderovitz, Meni Brief, Noga Ben Yoash, Oded Ovadia, Rachel Lemberg","cross_cats":["cs.CE","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-01T22:35:56Z","title":"Mixing It Up: The Cocktail Effect of Multi-Task Fine-Tuning on LLM Performance -- A Case Study in Finance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01109","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":"sha256:81dea3570e30d668a4f439e312feb67c4b4461bbc485e0c9ef4219e9bbaf601a","target":"record","created_at":"2026-07-05T09:44:36Z","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":"fde7e10525922fb2706c91f217c63319b995a36bcc8c28208f715d3228839dec","cross_cats_sorted":["cs.CE","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-01T22:35:56Z","title_canon_sha256":"d8ec616653b58cdba8904ac391e0f8c04c5d490aecc0f66d00108e4299d0917d"},"schema_version":"1.0","source":{"id":"2410.01109","kind":"arxiv","version":2}},"canonical_sha256":"25209da29f583bdc61b5309000ce860e11b8eabe41c96af37e73c6fb38e0e7e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25209da29f583bdc61b5309000ce860e11b8eabe41c96af37e73c6fb38e0e7e8","first_computed_at":"2026-07-05T09:44:36.057011Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:36.057011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AQrYR5s8hNJp2p8EB4wnd69+9p6qxLv0xZHy0IqZFqruncIitlSEMnUPo/r20p1xr51FSwMJuvr6xICxITAQCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:36.057697Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01109","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81dea3570e30d668a4f439e312feb67c4b4461bbc485e0c9ef4219e9bbaf601a","sha256:0becae00484604567d98958aee6235c69dbd120ad54b5d6bbba2df0b2f13fc32"],"state_sha256":"12abb9f05928e510da6497e1e6bd59727fd67ab25b4d41112711783c7dcf20f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NhEyigHoEAYlPh1DaDDLEscNgmUMf+mGOdtkyGiF6diZqSEU2uIxnd19VVo87hSMh86LYYYhRKC7ZsPh4MKjBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:15:09.311415Z","bundle_sha256":"cf870bba8860c8c559eff7d4bd4a323e98fc9c77ca9995a3488173b257d2a4a5"}}