{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y236EUYMEF57Z2N2V7BAORYHNM","short_pith_number":"pith:Y236EUYM","canonical_record":{"source":{"id":"2408.02085","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-04T16:50:07Z","cross_cats_sorted":["cs.AI","cs.CL","eess.SP"],"title_canon_sha256":"a386632441130afd876e2fbe5877eff8ef37327a6b247f5e48fc2155d06b8129","abstract_canon_sha256":"6198f5266b69bc49f6435c797b21053134ba4301a8a68d91fca467ff5ab1f3e4"},"schema_version":"1.0"},"canonical_sha256":"c6b7e2530c217bfce9baafc20747076b19fffa66caad5e9f9c0518c78e72a24a","source":{"kind":"arxiv","id":"2408.02085","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.02085","created_at":"2026-07-05T09:54:45Z"},{"alias_kind":"arxiv_version","alias_value":"2408.02085v5","created_at":"2026-07-05T09:54:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02085","created_at":"2026-07-05T09:54:45Z"},{"alias_kind":"pith_short_12","alias_value":"Y236EUYMEF57","created_at":"2026-07-05T09:54:45Z"},{"alias_kind":"pith_short_16","alias_value":"Y236EUYMEF57Z2N2","created_at":"2026-07-05T09:54:45Z"},{"alias_kind":"pith_short_8","alias_value":"Y236EUYM","created_at":"2026-07-05T09:54:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y236EUYMEF57Z2N2V7BAORYHNM","target":"record","payload":{"canonical_record":{"source":{"id":"2408.02085","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-04T16:50:07Z","cross_cats_sorted":["cs.AI","cs.CL","eess.SP"],"title_canon_sha256":"a386632441130afd876e2fbe5877eff8ef37327a6b247f5e48fc2155d06b8129","abstract_canon_sha256":"6198f5266b69bc49f6435c797b21053134ba4301a8a68d91fca467ff5ab1f3e4"},"schema_version":"1.0"},"canonical_sha256":"c6b7e2530c217bfce9baafc20747076b19fffa66caad5e9f9c0518c78e72a24a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:45.965080Z","signature_b64":"tCN5oDnF5K8imZo1qz8D0zvPL6q+uHh5KySNgezEdYPbQ/4ibNoG54T8Ysfnfn8VzxGIwfY5WseUnFTf42V2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6b7e2530c217bfce9baafc20747076b19fffa66caad5e9f9c0518c78e72a24a","last_reissued_at":"2026-07-05T09:54:45.964601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:45.964601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.02085","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:54:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wd1HTe1O0NFCzW+/s0uk/hXFnfdZGX8DGghEt3isM+tu4gPrEp5wY6TAa88Poi7ikohDdjeIPxdgxjr/EeDUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:41:12.856069Z"},"content_sha256":"bc0620d38726b4be8b1e49c2ca52aaf49b35fc69fe9c0c3343da09d32add4eb9","schema_version":"1.0","event_id":"sha256:bc0620d38726b4be8b1e49c2ca52aaf49b35fc69fe9c0c3343da09d32add4eb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y236EUYMEF57Z2N2V7BAORYHNM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.SP"],"primary_cat":"cs.CV","authors_text":"Gang Li, Hang Shao, Ke Li, Pengcheng Guo, Xing Sun, Yuchen Shi, Yulei Qin, Yuncheng Yang, Yun Gu, Zihan Xu","submitted_at":"2024-08-04T16:50:07Z","abstract_excerpt":"Instruction tuning plays a critical role in aligning large language models (LLMs) with human preference. Despite the vast amount of open instruction datasets, naively training a LLM on all existing instructions may not be optimal and practical. To pinpoint the most beneficial datapoints, data assessment and selection methods have been proposed in the fields of natural language processing (NLP) and deep learning. However, under the context of instruction tuning, there still exists a gap in knowledge on what kind of data evaluation metrics can be employed and how they can be integrated into the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02085","kind":"arxiv","version":5},"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/2408.02085/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":"2026-07-05T09:54:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tj+/erYY/o2hZ26B70SiwWSBIXPXmhPQ1IleHCERUznYAC/cH/O5e/UlbYdGtKvA2GfYBket/XfarVFTvC1aCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:41:12.856579Z"},"content_sha256":"dbf0e879cf86441369fb1f1723bdad99e3b9a0424ca743f5dabd6bcef0f938e3","schema_version":"1.0","event_id":"sha256:dbf0e879cf86441369fb1f1723bdad99e3b9a0424ca743f5dabd6bcef0f938e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y236EUYMEF57Z2N2V7BAORYHNM/bundle.json","state_url":"https://pith.science/pith/Y236EUYMEF57Z2N2V7BAORYHNM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y236EUYMEF57Z2N2V7BAORYHNM/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":"2026-08-05T17:41:12Z","links":{"resolver":"https://pith.science/pith/Y236EUYMEF57Z2N2V7BAORYHNM","bundle":"https://pith.science/pith/Y236EUYMEF57Z2N2V7BAORYHNM/bundle.json","state":"https://pith.science/pith/Y236EUYMEF57Z2N2V7BAORYHNM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y236EUYMEF57Z2N2V7BAORYHNM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y236EUYMEF57Z2N2V7BAORYHNM","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":"6198f5266b69bc49f6435c797b21053134ba4301a8a68d91fca467ff5ab1f3e4","cross_cats_sorted":["cs.AI","cs.CL","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-04T16:50:07Z","title_canon_sha256":"a386632441130afd876e2fbe5877eff8ef37327a6b247f5e48fc2155d06b8129"},"schema_version":"1.0","source":{"id":"2408.02085","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.02085","created_at":"2026-07-05T09:54:45Z"},{"alias_kind":"arxiv_version","alias_value":"2408.02085v5","created_at":"2026-07-05T09:54:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02085","created_at":"2026-07-05T09:54:45Z"},{"alias_kind":"pith_short_12","alias_value":"Y236EUYMEF57","created_at":"2026-07-05T09:54:45Z"},{"alias_kind":"pith_short_16","alias_value":"Y236EUYMEF57Z2N2","created_at":"2026-07-05T09:54:45Z"},{"alias_kind":"pith_short_8","alias_value":"Y236EUYM","created_at":"2026-07-05T09:54:45Z"}],"graph_snapshots":[{"event_id":"sha256:dbf0e879cf86441369fb1f1723bdad99e3b9a0424ca743f5dabd6bcef0f938e3","target":"graph","created_at":"2026-07-05T09:54:45Z","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/2408.02085/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning plays a critical role in aligning large language models (LLMs) with human preference. Despite the vast amount of open instruction datasets, naively training a LLM on all existing instructions may not be optimal and practical. To pinpoint the most beneficial datapoints, data assessment and selection methods have been proposed in the fields of natural language processing (NLP) and deep learning. However, under the context of instruction tuning, there still exists a gap in knowledge on what kind of data evaluation metrics can be employed and how they can be integrated into the ","authors_text":"Gang Li, Hang Shao, Ke Li, Pengcheng Guo, Xing Sun, Yuchen Shi, Yulei Qin, Yuncheng Yang, Yun Gu, Zihan Xu","cross_cats":["cs.AI","cs.CL","eess.SP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-04T16:50:07Z","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02085","kind":"arxiv","version":5},"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:bc0620d38726b4be8b1e49c2ca52aaf49b35fc69fe9c0c3343da09d32add4eb9","target":"record","created_at":"2026-07-05T09:54:45Z","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":"6198f5266b69bc49f6435c797b21053134ba4301a8a68d91fca467ff5ab1f3e4","cross_cats_sorted":["cs.AI","cs.CL","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-04T16:50:07Z","title_canon_sha256":"a386632441130afd876e2fbe5877eff8ef37327a6b247f5e48fc2155d06b8129"},"schema_version":"1.0","source":{"id":"2408.02085","kind":"arxiv","version":5}},"canonical_sha256":"c6b7e2530c217bfce9baafc20747076b19fffa66caad5e9f9c0518c78e72a24a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6b7e2530c217bfce9baafc20747076b19fffa66caad5e9f9c0518c78e72a24a","first_computed_at":"2026-07-05T09:54:45.964601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:45.964601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tCN5oDnF5K8imZo1qz8D0zvPL6q+uHh5KySNgezEdYPbQ/4ibNoG54T8Ysfnfn8VzxGIwfY5WseUnFTf42V2BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:45.965080Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.02085","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc0620d38726b4be8b1e49c2ca52aaf49b35fc69fe9c0c3343da09d32add4eb9","sha256:dbf0e879cf86441369fb1f1723bdad99e3b9a0424ca743f5dabd6bcef0f938e3"],"state_sha256":"8d773313b210e48adc7448b601da12b8077e575a521121601d9349c78ffab9c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pAf8u/pPuiH7X+gB6pNacqy3e7Ld54iq1EiKtNVAm9dSpQIOgMgEwDCswV2/jqEOs+7od8jOGZBtZghBoj2tBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:41:12.860664Z","bundle_sha256":"a43ecaef3a6a4a7f89f56fc07b64d8a6faf2d37f2e9143dbac60de372b7d7f94"}}