{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KIEUJ2E4UHACDK23OILEJAWFNQ","short_pith_number":"pith:KIEUJ2E4","canonical_record":{"source":{"id":"2312.15685","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-25T10:29:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d2ec279d17a5feafe3a7a84274d904006f5d0787e380235c40ecb9fc70acc0fd","abstract_canon_sha256":"14f01d58a4ad7f427dd881724893aa44bd12dc9dbaa16629993e4468f978e47a"},"schema_version":"1.0"},"canonical_sha256":"520944e89ca1c021ab5b72164482c56c2a6f068da3ac21135890b1b8d3cb3683","source":{"kind":"arxiv","id":"2312.15685","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15685","created_at":"2026-07-05T08:08:19Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15685v2","created_at":"2026-07-05T08:08:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15685","created_at":"2026-07-05T08:08:19Z"},{"alias_kind":"pith_short_12","alias_value":"KIEUJ2E4UHAC","created_at":"2026-07-05T08:08:19Z"},{"alias_kind":"pith_short_16","alias_value":"KIEUJ2E4UHACDK23","created_at":"2026-07-05T08:08:19Z"},{"alias_kind":"pith_short_8","alias_value":"KIEUJ2E4","created_at":"2026-07-05T08:08:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KIEUJ2E4UHACDK23OILEJAWFNQ","target":"record","payload":{"canonical_record":{"source":{"id":"2312.15685","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-25T10:29:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d2ec279d17a5feafe3a7a84274d904006f5d0787e380235c40ecb9fc70acc0fd","abstract_canon_sha256":"14f01d58a4ad7f427dd881724893aa44bd12dc9dbaa16629993e4468f978e47a"},"schema_version":"1.0"},"canonical_sha256":"520944e89ca1c021ab5b72164482c56c2a6f068da3ac21135890b1b8d3cb3683","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:19.856887Z","signature_b64":"k2kMh6W2jesJKTs/KKILhKc1DvvOP6XpoH5UpXWJnkUYCFHxXQ8hesnq4eBYClCO5Mn9vZlBJSAPeigHLYBaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"520944e89ca1c021ab5b72164482c56c2a6f068da3ac21135890b1b8d3cb3683","last_reissued_at":"2026-07-05T08:08:19.856441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:19.856441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.15685","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":"2026-07-05T08:08:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vhUL04NJVoV96yR0pVv6lNyCu0ujyJ+8Lp0WOWheGkjSXn6gnb24s69QvxQJcDMGu0yBxdZ0rZHaxvbKO5ZzDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:16:21.490978Z"},"content_sha256":"fe37129a60749729e098c41cba3b3b5cf1ca7ad7fdfade0cdd0a04b7ca07c05c","schema_version":"1.0","event_id":"sha256:fe37129a60749729e098c41cba3b3b5cf1ca7ad7fdfade0cdd0a04b7ca07c05c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KIEUJ2E4UHACDK23OILEJAWFNQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Junxian He, Keqing He, Weihao Zeng, Wei Liu, Yong Jiang","submitted_at":"2023-12-25T10:29:28Z","abstract_excerpt":"Instruction tuning is a standard technique employed to align large language models to end tasks and user preferences after the initial pretraining phase. Recent research indicates the critical role of data engineering in instruction tuning -- when appropriately selected, only limited data is necessary to achieve superior performance. However, we still lack a principled understanding of what makes good instruction tuning data for alignment, and how we should select data automatically and effectively. In this work, we delve deeply into automatic data selection strategies for alignment. We start "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15685","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/2312.15685/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":"2026-07-05T08:08:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IBaEXABBH+/upgm3dG1KaVF6G7t7wNtg/sNSZkzWL8bFy2F4UeS5HAmZPx+lT+/HVLosHSvGgYg0TzxGIxKdDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:16:21.491479Z"},"content_sha256":"2a9ce3af020c264bed326380ceb3861a01732923a309f7e1b61432c24bc28de3","schema_version":"1.0","event_id":"sha256:2a9ce3af020c264bed326380ceb3861a01732923a309f7e1b61432c24bc28de3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KIEUJ2E4UHACDK23OILEJAWFNQ/bundle.json","state_url":"https://pith.science/pith/KIEUJ2E4UHACDK23OILEJAWFNQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KIEUJ2E4UHACDK23OILEJAWFNQ/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":"2026-08-05T09:16:21Z","links":{"resolver":"https://pith.science/pith/KIEUJ2E4UHACDK23OILEJAWFNQ","bundle":"https://pith.science/pith/KIEUJ2E4UHACDK23OILEJAWFNQ/bundle.json","state":"https://pith.science/pith/KIEUJ2E4UHACDK23OILEJAWFNQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KIEUJ2E4UHACDK23OILEJAWFNQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KIEUJ2E4UHACDK23OILEJAWFNQ","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":"14f01d58a4ad7f427dd881724893aa44bd12dc9dbaa16629993e4468f978e47a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-25T10:29:28Z","title_canon_sha256":"d2ec279d17a5feafe3a7a84274d904006f5d0787e380235c40ecb9fc70acc0fd"},"schema_version":"1.0","source":{"id":"2312.15685","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15685","created_at":"2026-07-05T08:08:19Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15685v2","created_at":"2026-07-05T08:08:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15685","created_at":"2026-07-05T08:08:19Z"},{"alias_kind":"pith_short_12","alias_value":"KIEUJ2E4UHAC","created_at":"2026-07-05T08:08:19Z"},{"alias_kind":"pith_short_16","alias_value":"KIEUJ2E4UHACDK23","created_at":"2026-07-05T08:08:19Z"},{"alias_kind":"pith_short_8","alias_value":"KIEUJ2E4","created_at":"2026-07-05T08:08:19Z"}],"graph_snapshots":[{"event_id":"sha256:2a9ce3af020c264bed326380ceb3861a01732923a309f7e1b61432c24bc28de3","target":"graph","created_at":"2026-07-05T08:08:19Z","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/2312.15685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning is a standard technique employed to align large language models to end tasks and user preferences after the initial pretraining phase. Recent research indicates the critical role of data engineering in instruction tuning -- when appropriately selected, only limited data is necessary to achieve superior performance. However, we still lack a principled understanding of what makes good instruction tuning data for alignment, and how we should select data automatically and effectively. In this work, we delve deeply into automatic data selection strategies for alignment. We start ","authors_text":"Junxian He, Keqing He, Weihao Zeng, Wei Liu, Yong Jiang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-25T10:29:28Z","title":"What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15685","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:fe37129a60749729e098c41cba3b3b5cf1ca7ad7fdfade0cdd0a04b7ca07c05c","target":"record","created_at":"2026-07-05T08:08:19Z","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":"14f01d58a4ad7f427dd881724893aa44bd12dc9dbaa16629993e4468f978e47a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-25T10:29:28Z","title_canon_sha256":"d2ec279d17a5feafe3a7a84274d904006f5d0787e380235c40ecb9fc70acc0fd"},"schema_version":"1.0","source":{"id":"2312.15685","kind":"arxiv","version":2}},"canonical_sha256":"520944e89ca1c021ab5b72164482c56c2a6f068da3ac21135890b1b8d3cb3683","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"520944e89ca1c021ab5b72164482c56c2a6f068da3ac21135890b1b8d3cb3683","first_computed_at":"2026-07-05T08:08:19.856441Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:19.856441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k2kMh6W2jesJKTs/KKILhKc1DvvOP6XpoH5UpXWJnkUYCFHxXQ8hesnq4eBYClCO5Mn9vZlBJSAPeigHLYBaCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:19.856887Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.15685","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe37129a60749729e098c41cba3b3b5cf1ca7ad7fdfade0cdd0a04b7ca07c05c","sha256:2a9ce3af020c264bed326380ceb3861a01732923a309f7e1b61432c24bc28de3"],"state_sha256":"90557719a2d0b3018d8ced2eedfb24a56ac92df8b385886b872e228ea1e9e1cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DS+TUYeoRRRc7l9dTae72ScL1d60V0gqkJ6f9PT1VUANtM4d2er5MyPm0nUVTrNPYbQKM6zYiOBwrATDcvU2BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:16:21.495740Z","bundle_sha256":"b5b921ca6fd8e979fbe6be6b0403f4473e529ee7b5ed9034b3855fd6f8ea9fe2"}}