{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VGGWXGHPOKFN3NWEQCKY6LLP3O","short_pith_number":"pith:VGGWXGHP","canonical_record":{"source":{"id":"2312.11508","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T03:30:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd00c58aca3f584b4399395f15e245839709b42163cc25e53119817928ccbe9d","abstract_canon_sha256":"23144834983cc606bb16aaf76d60071cd33cdf8adb510b2db91842fb01e923dc"},"schema_version":"1.0"},"canonical_sha256":"a98d6b98ef728addb6c480958f2d6fdb984b27ebfd28f3e8b2abc808a2cfb71f","source":{"kind":"arxiv","id":"2312.11508","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11508","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11508v2","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11508","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"pith_short_12","alias_value":"VGGWXGHPOKFN","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"pith_short_16","alias_value":"VGGWXGHPOKFN3NWE","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"pith_short_8","alias_value":"VGGWXGHP","created_at":"2026-07-05T07:28:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VGGWXGHPOKFN3NWEQCKY6LLP3O","target":"record","payload":{"canonical_record":{"source":{"id":"2312.11508","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T03:30:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd00c58aca3f584b4399395f15e245839709b42163cc25e53119817928ccbe9d","abstract_canon_sha256":"23144834983cc606bb16aaf76d60071cd33cdf8adb510b2db91842fb01e923dc"},"schema_version":"1.0"},"canonical_sha256":"a98d6b98ef728addb6c480958f2d6fdb984b27ebfd28f3e8b2abc808a2cfb71f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:12.720810Z","signature_b64":"3rPs3MXV0/tdPVxDUXbbMMP3vMsaNf7o027NyO8RaL7ojQQSyADrl8bIfIkDcaFYZUeHIAUnvE8JHQQfPcjbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a98d6b98ef728addb6c480958f2d6fdb984b27ebfd28f3e8b2abc808a2cfb71f","last_reissued_at":"2026-07-05T07:28:12.720331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:12.720331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.11508","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":"2026-07-05T07:28:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nukxNEBEVK29IrawdTKJiGojRSp8HpjFoi58x38EaHFiv5UtIV1atSYH9z9PtFzy9iFGQiEc5MX05taFYqUjBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:54:48.832557Z"},"content_sha256":"da026132ad761a1acc9ae5d8613620b37229ec7d09ca1e803ac022beda8604c4","schema_version":"1.0","event_id":"sha256:da026132ad761a1acc9ae5d8613620b37229ec7d09ca1e803ac022beda8604c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VGGWXGHPOKFN3NWEQCKY6LLP3O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking the Instruction Quality: LIFT is What You Need","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Gu, Maoquan Wang, Mengnan Qi, Neel Sundaresan, Yang Xu, Yongqiang Yao, Yufan Huang","submitted_at":"2023-12-12T03:30:21Z","abstract_excerpt":"Instruction tuning, a specialized technique to enhance large language model (LLM) performance via instruction datasets, relies heavily on the quality of employed data. Existing quality improvement methods alter instruction data through dataset expansion or curation. However, the expansion method risks data redundancy, potentially compromising LLM performance, while the curation approach confines the LLM's potential to the original dataset. Our aim is to surpass the original data quality without encountering these shortcomings. To achieve this, we propose LIFT (LLM Instruction Fusion Transfer),"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11508","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/2312.11508/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":"2026-07-05T07:28:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ekQ8FjVrmL4zXlpOe+keTFsE3yv5zoaXBiHRzvXldccwjb98WZ0Edfoiimx7acMKVy2ht4gKptAPwWI05HtBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:54:48.833122Z"},"content_sha256":"310e34b8cd2c5cbd88ec3d82d9a43d7ccd58f50800c5fef73f29f0d1c0e09785","schema_version":"1.0","event_id":"sha256:310e34b8cd2c5cbd88ec3d82d9a43d7ccd58f50800c5fef73f29f0d1c0e09785"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VGGWXGHPOKFN3NWEQCKY6LLP3O/bundle.json","state_url":"https://pith.science/pith/VGGWXGHPOKFN3NWEQCKY6LLP3O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VGGWXGHPOKFN3NWEQCKY6LLP3O/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":"2026-08-07T19:54:48Z","links":{"resolver":"https://pith.science/pith/VGGWXGHPOKFN3NWEQCKY6LLP3O","bundle":"https://pith.science/pith/VGGWXGHPOKFN3NWEQCKY6LLP3O/bundle.json","state":"https://pith.science/pith/VGGWXGHPOKFN3NWEQCKY6LLP3O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VGGWXGHPOKFN3NWEQCKY6LLP3O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VGGWXGHPOKFN3NWEQCKY6LLP3O","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":"23144834983cc606bb16aaf76d60071cd33cdf8adb510b2db91842fb01e923dc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T03:30:21Z","title_canon_sha256":"cd00c58aca3f584b4399395f15e245839709b42163cc25e53119817928ccbe9d"},"schema_version":"1.0","source":{"id":"2312.11508","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11508","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11508v2","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11508","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"pith_short_12","alias_value":"VGGWXGHPOKFN","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"pith_short_16","alias_value":"VGGWXGHPOKFN3NWE","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"pith_short_8","alias_value":"VGGWXGHP","created_at":"2026-07-05T07:28:12Z"}],"graph_snapshots":[{"event_id":"sha256:310e34b8cd2c5cbd88ec3d82d9a43d7ccd58f50800c5fef73f29f0d1c0e09785","target":"graph","created_at":"2026-07-05T07:28:12Z","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/2312.11508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning, a specialized technique to enhance large language model (LLM) performance via instruction datasets, relies heavily on the quality of employed data. Existing quality improvement methods alter instruction data through dataset expansion or curation. However, the expansion method risks data redundancy, potentially compromising LLM performance, while the curation approach confines the LLM's potential to the original dataset. Our aim is to surpass the original data quality without encountering these shortcomings. To achieve this, we propose LIFT (LLM Instruction Fusion Transfer),","authors_text":"Bin Gu, Maoquan Wang, Mengnan Qi, Neel Sundaresan, Yang Xu, Yongqiang Yao, Yufan Huang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T03:30:21Z","title":"Rethinking the Instruction Quality: LIFT is What You Need"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11508","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:da026132ad761a1acc9ae5d8613620b37229ec7d09ca1e803ac022beda8604c4","target":"record","created_at":"2026-07-05T07:28:12Z","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":"23144834983cc606bb16aaf76d60071cd33cdf8adb510b2db91842fb01e923dc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T03:30:21Z","title_canon_sha256":"cd00c58aca3f584b4399395f15e245839709b42163cc25e53119817928ccbe9d"},"schema_version":"1.0","source":{"id":"2312.11508","kind":"arxiv","version":2}},"canonical_sha256":"a98d6b98ef728addb6c480958f2d6fdb984b27ebfd28f3e8b2abc808a2cfb71f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a98d6b98ef728addb6c480958f2d6fdb984b27ebfd28f3e8b2abc808a2cfb71f","first_computed_at":"2026-07-05T07:28:12.720331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:12.720331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3rPs3MXV0/tdPVxDUXbbMMP3vMsaNf7o027NyO8RaL7ojQQSyADrl8bIfIkDcaFYZUeHIAUnvE8JHQQfPcjbBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:12.720810Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.11508","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da026132ad761a1acc9ae5d8613620b37229ec7d09ca1e803ac022beda8604c4","sha256:310e34b8cd2c5cbd88ec3d82d9a43d7ccd58f50800c5fef73f29f0d1c0e09785"],"state_sha256":"f626f3025e8d80875cc8efc9160c7dca64df2bc64668d310287e861356c94d96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GdwVPL+xVj5E0wo4rZp8WLRtIRAB8WjFGMGU5T8AL3ZL6aTf2fvhJwedpM0xCVq/zn4uv/HP8j2Kq4SQfGAhDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:54:48.838113Z","bundle_sha256":"e15068e09d8b1f29eea9e47411204cf72fc147f16bec812827b3be3c166b1c81"}}