{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3UIWKHMNIERBF7AMO67IZURIZO","short_pith_number":"pith:3UIWKHMN","canonical_record":{"source":{"id":"2412.13337","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T21:16:59Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"47dbc308e5cceaf389c3ac59f7a188c2a051d9e2d75bf9569586b208857dc230","abstract_canon_sha256":"56cd686ee5e467512f2b61d0d5b01fb9fd9c88425da1dd125346cd33914f34b3"},"schema_version":"1.0"},"canonical_sha256":"dd11651d8d412212fc0c77be8cd228cba5e53fe04514810a95efdc80ee949b31","source":{"kind":"arxiv","id":"2412.13337","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13337","created_at":"2026-07-05T09:50:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13337v1","created_at":"2026-07-05T09:50:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13337","created_at":"2026-07-05T09:50:59Z"},{"alias_kind":"pith_short_12","alias_value":"3UIWKHMNIERB","created_at":"2026-07-05T09:50:59Z"},{"alias_kind":"pith_short_16","alias_value":"3UIWKHMNIERBF7AM","created_at":"2026-07-05T09:50:59Z"},{"alias_kind":"pith_short_8","alias_value":"3UIWKHMN","created_at":"2026-07-05T09:50:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3UIWKHMNIERBF7AMO67IZURIZO","target":"record","payload":{"canonical_record":{"source":{"id":"2412.13337","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T21:16:59Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"47dbc308e5cceaf389c3ac59f7a188c2a051d9e2d75bf9569586b208857dc230","abstract_canon_sha256":"56cd686ee5e467512f2b61d0d5b01fb9fd9c88425da1dd125346cd33914f34b3"},"schema_version":"1.0"},"canonical_sha256":"dd11651d8d412212fc0c77be8cd228cba5e53fe04514810a95efdc80ee949b31","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:59.894593Z","signature_b64":"QBX+OQMhyW0KiZymr/Jb58+O/lOpXQedgNz3M1IQCIpvPxg5897lS5e61Ps5500u8FIabVbTYnmtm9MKZ/AmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd11651d8d412212fc0c77be8cd228cba5e53fe04514810a95efdc80ee949b31","last_reissued_at":"2026-07-05T09:50:59.894136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:59.894136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.13337","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:50:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jz184JwX4AlPnAGQYvXGOXpO58/PXzIwbg8UzI/ml+waB5+y+a6tJErF7ElqT3SQR0OyNGmjOX7JR2SGk5ldBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T00:02:49.747115Z"},"content_sha256":"cdbbf3a89a1f791e0fddfe956b705101495e4d6d721256eb65c1b12c0e36ffb3","schema_version":"1.0","event_id":"sha256:cdbbf3a89a1f791e0fddfe956b705101495e4d6d721256eb65c1b12c0e36ffb3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3UIWKHMNIERBF7AMO67IZURIZO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Bhandwaldar, Akash Srivastava, Aldo Pareja, Guangxuan Xu, Hao Wang, Kai Xu, Krishnateja Killamsetty, Ligong Han, Luke Inglis, Nikhil Shivakumar Nayak, Seungwook Han, Shivchander Sudalairaj, Wenlong Zhao","submitted_at":"2024-12-17T21:16:59Z","abstract_excerpt":"The rise of large language models (LLMs) has created a significant disparity: industrial research labs with their computational resources, expert teams, and advanced infrastructures, can effectively fine-tune LLMs, while individual developers and small organizations face barriers due to limited resources. In this paper, we aim to bridge this gap by presenting a comprehensive study on supervised fine-tuning of LLMs using instruction-tuning datasets spanning diverse knowledge domains and skills. We focus on small-sized LLMs (3B to 7B parameters) for their cost-efficiency and accessibility. We ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13337","kind":"arxiv","version":1},"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/2412.13337/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":"2026-07-05T09:50:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fL6XU+dPmBayCektfwEKz06KgjcG6Kw015HNOZLLjABAEami1ROF05yM6AVL5pdR1SoXCk9aSvAQgx/c6u1DBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T00:02:49.747617Z"},"content_sha256":"b234be752e193f5b1d5a4a8fa824d84f501f19044cfddc7e42b6532204b9163e","schema_version":"1.0","event_id":"sha256:b234be752e193f5b1d5a4a8fa824d84f501f19044cfddc7e42b6532204b9163e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3UIWKHMNIERBF7AMO67IZURIZO/bundle.json","state_url":"https://pith.science/pith/3UIWKHMNIERBF7AMO67IZURIZO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3UIWKHMNIERBF7AMO67IZURIZO/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":"2026-08-16T00:02:49Z","links":{"resolver":"https://pith.science/pith/3UIWKHMNIERBF7AMO67IZURIZO","bundle":"https://pith.science/pith/3UIWKHMNIERBF7AMO67IZURIZO/bundle.json","state":"https://pith.science/pith/3UIWKHMNIERBF7AMO67IZURIZO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3UIWKHMNIERBF7AMO67IZURIZO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3UIWKHMNIERBF7AMO67IZURIZO","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":"56cd686ee5e467512f2b61d0d5b01fb9fd9c88425da1dd125346cd33914f34b3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T21:16:59Z","title_canon_sha256":"47dbc308e5cceaf389c3ac59f7a188c2a051d9e2d75bf9569586b208857dc230"},"schema_version":"1.0","source":{"id":"2412.13337","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13337","created_at":"2026-07-05T09:50:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13337v1","created_at":"2026-07-05T09:50:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13337","created_at":"2026-07-05T09:50:59Z"},{"alias_kind":"pith_short_12","alias_value":"3UIWKHMNIERB","created_at":"2026-07-05T09:50:59Z"},{"alias_kind":"pith_short_16","alias_value":"3UIWKHMNIERBF7AM","created_at":"2026-07-05T09:50:59Z"},{"alias_kind":"pith_short_8","alias_value":"3UIWKHMN","created_at":"2026-07-05T09:50:59Z"}],"graph_snapshots":[{"event_id":"sha256:b234be752e193f5b1d5a4a8fa824d84f501f19044cfddc7e42b6532204b9163e","target":"graph","created_at":"2026-07-05T09:50:59Z","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/2412.13337/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rise of large language models (LLMs) has created a significant disparity: industrial research labs with their computational resources, expert teams, and advanced infrastructures, can effectively fine-tune LLMs, while individual developers and small organizations face barriers due to limited resources. In this paper, we aim to bridge this gap by presenting a comprehensive study on supervised fine-tuning of LLMs using instruction-tuning datasets spanning diverse knowledge domains and skills. We focus on small-sized LLMs (3B to 7B parameters) for their cost-efficiency and accessibility. We ex","authors_text":"Abhishek Bhandwaldar, Akash Srivastava, Aldo Pareja, Guangxuan Xu, Hao Wang, Kai Xu, Krishnateja Killamsetty, Ligong Han, Luke Inglis, Nikhil Shivakumar Nayak, Seungwook Han, Shivchander Sudalairaj, Wenlong Zhao","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T21:16:59Z","title":"Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13337","kind":"arxiv","version":1},"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:cdbbf3a89a1f791e0fddfe956b705101495e4d6d721256eb65c1b12c0e36ffb3","target":"record","created_at":"2026-07-05T09:50:59Z","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":"56cd686ee5e467512f2b61d0d5b01fb9fd9c88425da1dd125346cd33914f34b3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T21:16:59Z","title_canon_sha256":"47dbc308e5cceaf389c3ac59f7a188c2a051d9e2d75bf9569586b208857dc230"},"schema_version":"1.0","source":{"id":"2412.13337","kind":"arxiv","version":1}},"canonical_sha256":"dd11651d8d412212fc0c77be8cd228cba5e53fe04514810a95efdc80ee949b31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd11651d8d412212fc0c77be8cd228cba5e53fe04514810a95efdc80ee949b31","first_computed_at":"2026-07-05T09:50:59.894136Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:59.894136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QBX+OQMhyW0KiZymr/Jb58+O/lOpXQedgNz3M1IQCIpvPxg5897lS5e61Ps5500u8FIabVbTYnmtm9MKZ/AmBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:59.894593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13337","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdbbf3a89a1f791e0fddfe956b705101495e4d6d721256eb65c1b12c0e36ffb3","sha256:b234be752e193f5b1d5a4a8fa824d84f501f19044cfddc7e42b6532204b9163e"],"state_sha256":"19eb6f4e2c5a4779c26c9df176482fc6d6f6f84eac5c35523c48dd85b8b85017"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oZpzSgphgh6VhD5U7QEfLKdMLvjWVVY9p8RAcqLqE1CBQne7XCA3fBOazA+oyX84qwLe83VV4iSxP0jK+XSRAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T00:02:49.751252Z","bundle_sha256":"74525cb2467b2eba775a589252587f444009164e35704e293557e5ed1ff2d38e"}}