{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XJ7EP3RF2OU4L5WBLDZODAGYMN","short_pith_number":"pith:XJ7EP3RF","canonical_record":{"source":{"id":"2412.17365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T08:01:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c728ce8fe0f8da6ffb2cf038bef76704a4968f924af7cdec47888952e80f8a39","abstract_canon_sha256":"e34c611d3ad7bf1a71c276357efa2bdeda8a3b286525cc69050ba9f409c4258e"},"schema_version":"1.0"},"canonical_sha256":"ba7e47ee25d3a9c5f6c158f2e180d86376b53ece904749534d3b5b1167a69e16","source":{"kind":"arxiv","id":"2412.17365","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17365","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17365v1","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17365","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"pith_short_12","alias_value":"XJ7EP3RF2OU4","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"pith_short_16","alias_value":"XJ7EP3RF2OU4L5WB","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"pith_short_8","alias_value":"XJ7EP3RF","created_at":"2026-07-05T09:53:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XJ7EP3RF2OU4L5WBLDZODAGYMN","target":"record","payload":{"canonical_record":{"source":{"id":"2412.17365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T08:01:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c728ce8fe0f8da6ffb2cf038bef76704a4968f924af7cdec47888952e80f8a39","abstract_canon_sha256":"e34c611d3ad7bf1a71c276357efa2bdeda8a3b286525cc69050ba9f409c4258e"},"schema_version":"1.0"},"canonical_sha256":"ba7e47ee25d3a9c5f6c158f2e180d86376b53ece904749534d3b5b1167a69e16","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:21.489770Z","signature_b64":"ML3EChQWhTfJ8WN2ugPNtgiausEJLuh4+SW/SqZUlFfgmw96cwv8uMtlnU+avjZ9Mh6GXMI35CMejnJ1N9pCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba7e47ee25d3a9c5f6c158f2e180d86376b53ece904749534d3b5b1167a69e16","last_reissued_at":"2026-07-05T09:53:21.489280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:21.489280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.17365","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":"2026-07-05T09:53:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BJT1uG3d/war1ThusOWtsOXr3uYDL7eiVxdwwwkjqFI4xDo+DKb/YOb60oVkCtU37tbMwYhaVGm+v68TjsjTDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:09:00.277839Z"},"content_sha256":"1bb5a0ff25fdb7b2ffef0156d864940f7fa8cd62cb5b01ec9706e921c266eee1","schema_version":"1.0","event_id":"sha256:1bb5a0ff25fdb7b2ffef0156d864940f7fa8cd62cb5b01ec9706e921c266eee1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XJ7EP3RF2OU4L5WBLDZODAGYMN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosting LLM via Learning from Data Iteratively and Selectively","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fuzhao Xue, Jinjie Ni, Qi Jia, Siyu Ren, Yang You, Ziheng Qin","submitted_at":"2024-12-23T08:01:24Z","abstract_excerpt":"Datasets nowadays are generally constructed from multiple sources and using different synthetic techniques, making data de-noising and de-duplication crucial before being used for post-training. In this work, we propose to perform instruction tuning by iterative data selection (\\ApproachName{}). We measure the quality of a sample from complexity and diversity simultaneously. Instead of calculating the complexity score once for all before fine-tuning, we highlight the importance of updating this model-specific score during fine-tuning to accurately accommodate the dynamic changes of the model. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17365","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/2412.17365/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":"2026-07-05T09:53:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qaPE3sosRttpIQrj8OZBpRm7R3CAbTQoUH7MSOywdcMrF41k5Jl66pYQmiB5IPH2hoaRd6wOyDY4O9m6FmXDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:09:00.278335Z"},"content_sha256":"12392b4ccdd6c6def54c12bf9d3c5e2d5788cfd615be04ef129c89e4fd50cd43","schema_version":"1.0","event_id":"sha256:12392b4ccdd6c6def54c12bf9d3c5e2d5788cfd615be04ef129c89e4fd50cd43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XJ7EP3RF2OU4L5WBLDZODAGYMN/bundle.json","state_url":"https://pith.science/pith/XJ7EP3RF2OU4L5WBLDZODAGYMN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XJ7EP3RF2OU4L5WBLDZODAGYMN/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":"2026-08-04T11:09:00Z","links":{"resolver":"https://pith.science/pith/XJ7EP3RF2OU4L5WBLDZODAGYMN","bundle":"https://pith.science/pith/XJ7EP3RF2OU4L5WBLDZODAGYMN/bundle.json","state":"https://pith.science/pith/XJ7EP3RF2OU4L5WBLDZODAGYMN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XJ7EP3RF2OU4L5WBLDZODAGYMN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XJ7EP3RF2OU4L5WBLDZODAGYMN","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":"e34c611d3ad7bf1a71c276357efa2bdeda8a3b286525cc69050ba9f409c4258e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T08:01:24Z","title_canon_sha256":"c728ce8fe0f8da6ffb2cf038bef76704a4968f924af7cdec47888952e80f8a39"},"schema_version":"1.0","source":{"id":"2412.17365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17365","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17365v1","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17365","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"pith_short_12","alias_value":"XJ7EP3RF2OU4","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"pith_short_16","alias_value":"XJ7EP3RF2OU4L5WB","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"pith_short_8","alias_value":"XJ7EP3RF","created_at":"2026-07-05T09:53:21Z"}],"graph_snapshots":[{"event_id":"sha256:12392b4ccdd6c6def54c12bf9d3c5e2d5788cfd615be04ef129c89e4fd50cd43","target":"graph","created_at":"2026-07-05T09:53:21Z","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/2412.17365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Datasets nowadays are generally constructed from multiple sources and using different synthetic techniques, making data de-noising and de-duplication crucial before being used for post-training. In this work, we propose to perform instruction tuning by iterative data selection (\\ApproachName{}). We measure the quality of a sample from complexity and diversity simultaneously. Instead of calculating the complexity score once for all before fine-tuning, we highlight the importance of updating this model-specific score during fine-tuning to accurately accommodate the dynamic changes of the model. ","authors_text":"Fuzhao Xue, Jinjie Ni, Qi Jia, Siyu Ren, Yang You, Ziheng Qin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T08:01:24Z","title":"Boosting LLM via Learning from Data Iteratively and Selectively"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17365","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":"sha256:1bb5a0ff25fdb7b2ffef0156d864940f7fa8cd62cb5b01ec9706e921c266eee1","target":"record","created_at":"2026-07-05T09:53:21Z","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":"e34c611d3ad7bf1a71c276357efa2bdeda8a3b286525cc69050ba9f409c4258e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T08:01:24Z","title_canon_sha256":"c728ce8fe0f8da6ffb2cf038bef76704a4968f924af7cdec47888952e80f8a39"},"schema_version":"1.0","source":{"id":"2412.17365","kind":"arxiv","version":1}},"canonical_sha256":"ba7e47ee25d3a9c5f6c158f2e180d86376b53ece904749534d3b5b1167a69e16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba7e47ee25d3a9c5f6c158f2e180d86376b53ece904749534d3b5b1167a69e16","first_computed_at":"2026-07-05T09:53:21.489280Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:21.489280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ML3EChQWhTfJ8WN2ugPNtgiausEJLuh4+SW/SqZUlFfgmw96cwv8uMtlnU+avjZ9Mh6GXMI35CMejnJ1N9pCBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:21.489770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.17365","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bb5a0ff25fdb7b2ffef0156d864940f7fa8cd62cb5b01ec9706e921c266eee1","sha256:12392b4ccdd6c6def54c12bf9d3c5e2d5788cfd615be04ef129c89e4fd50cd43"],"state_sha256":"949586d48a51544f0925f44c9e9411752886d36edcc0e8c25096fc1ae2b70322"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XYssfcBJqlaMUQZryRkEKZlCvHgzoccb7RV+2R08tBjmr1FOvyR8bRhrIaqhsgSCQyIxSy9kswdwgczoSe6wBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:09:00.282647Z","bundle_sha256":"96a58914ba90a3534608e71940d69c789aa0e3afddd79bca44cdbbeb667cebcc"}}