{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y5TGWAMU5PB3RVLQMSMI5XFDHD","short_pith_number":"pith:Y5TGWAMU","canonical_record":{"source":{"id":"2402.17355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T09:47:36Z","cross_cats_sorted":[],"title_canon_sha256":"a576fec7dd7045adf6a12867b8b2eb9ea8ea34731a2ff1b27007b96c08492249","abstract_canon_sha256":"916d126b4aaa6dbad443f967450de666348507eb661ceb13fc89391a2342fb1e"},"schema_version":"1.0"},"canonical_sha256":"c7666b0194ebc3b8d57064988edca338f43eeaf9080d0e6950299097d07c5480","source":{"kind":"arxiv","id":"2402.17355","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17355","created_at":"2026-07-05T09:56:20Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17355v1","created_at":"2026-07-05T09:56:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17355","created_at":"2026-07-05T09:56:20Z"},{"alias_kind":"pith_short_12","alias_value":"Y5TGWAMU5PB3","created_at":"2026-07-05T09:56:20Z"},{"alias_kind":"pith_short_16","alias_value":"Y5TGWAMU5PB3RVLQ","created_at":"2026-07-05T09:56:20Z"},{"alias_kind":"pith_short_8","alias_value":"Y5TGWAMU","created_at":"2026-07-05T09:56:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y5TGWAMU5PB3RVLQMSMI5XFDHD","target":"record","payload":{"canonical_record":{"source":{"id":"2402.17355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T09:47:36Z","cross_cats_sorted":[],"title_canon_sha256":"a576fec7dd7045adf6a12867b8b2eb9ea8ea34731a2ff1b27007b96c08492249","abstract_canon_sha256":"916d126b4aaa6dbad443f967450de666348507eb661ceb13fc89391a2342fb1e"},"schema_version":"1.0"},"canonical_sha256":"c7666b0194ebc3b8d57064988edca338f43eeaf9080d0e6950299097d07c5480","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:20.846401Z","signature_b64":"a5QLUhTM/9ZMlmp7xgamIS1JFVFxUfeoG0UsJq0pKiqPV/EDJij4xYIX2grINtIJ34e9D3Q/mcRcHORjEWUvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7666b0194ebc3b8d57064988edca338f43eeaf9080d0e6950299097d07c5480","last_reissued_at":"2026-07-05T09:56:20.845968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:20.845968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.17355","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":"2026-07-05T09:56:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9wBEnSHfVsRs1crpykPpHFMwT+1R39XX8PyRbu1LysliIHtRbQpJJZ9+qLdsU2IIAriUEFN7PAbiXts4xDoLAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:05:31.747836Z"},"content_sha256":"9e0c52235ffc1b44a1fa2f34fdd579d0d8f7bed6f3a63421898332420f990f1c","schema_version":"1.0","event_id":"sha256:9e0c52235ffc1b44a1fa2f34fdd579d0d8f7bed6f3a63421898332420f990f1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y5TGWAMU5PB3RVLQMSMI5XFDHD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RECOST: External Knowledge Guided Data-efficient Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haobo Wang, Junbo Zhao, Qi Zhang, Yiming Zhang","submitted_at":"2024-02-27T09:47:36Z","abstract_excerpt":"In the current landscape of large language models (LLMs), the process of instruction tuning serves as an essential step. Considering the high computing power overhead, data-efficient instruction tuning was proposed to reduce the training data size in this process, aiming at selecting high-quality instructional data. Nevertheless, we argue that most current data-efficient instruction-tuning methods are highly dependent on the quality of the original instruction-tuning dataset. When it comes to datasets synthesized by LLMs, a common scenario in this field, dirty samples will even be selected wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17355","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/2402.17355/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":"2026-07-05T09:56:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Pqnz6we29Nl8BxrrslCfy0+IZwrd1GwE/DzMYgAu4wo5sF7Y9eOVDgPYR+gNr2pINhPojtrtxUtmktR/EaJBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:05:31.748336Z"},"content_sha256":"f2e645aa07e801d0273de734043ad5125792c28b5dd8ab97d603d56d78c2455f","schema_version":"1.0","event_id":"sha256:f2e645aa07e801d0273de734043ad5125792c28b5dd8ab97d603d56d78c2455f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y5TGWAMU5PB3RVLQMSMI5XFDHD/bundle.json","state_url":"https://pith.science/pith/Y5TGWAMU5PB3RVLQMSMI5XFDHD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y5TGWAMU5PB3RVLQMSMI5XFDHD/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":"2026-08-23T17:05:31Z","links":{"resolver":"https://pith.science/pith/Y5TGWAMU5PB3RVLQMSMI5XFDHD","bundle":"https://pith.science/pith/Y5TGWAMU5PB3RVLQMSMI5XFDHD/bundle.json","state":"https://pith.science/pith/Y5TGWAMU5PB3RVLQMSMI5XFDHD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y5TGWAMU5PB3RVLQMSMI5XFDHD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y5TGWAMU5PB3RVLQMSMI5XFDHD","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":"916d126b4aaa6dbad443f967450de666348507eb661ceb13fc89391a2342fb1e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T09:47:36Z","title_canon_sha256":"a576fec7dd7045adf6a12867b8b2eb9ea8ea34731a2ff1b27007b96c08492249"},"schema_version":"1.0","source":{"id":"2402.17355","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17355","created_at":"2026-07-05T09:56:20Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17355v1","created_at":"2026-07-05T09:56:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17355","created_at":"2026-07-05T09:56:20Z"},{"alias_kind":"pith_short_12","alias_value":"Y5TGWAMU5PB3","created_at":"2026-07-05T09:56:20Z"},{"alias_kind":"pith_short_16","alias_value":"Y5TGWAMU5PB3RVLQ","created_at":"2026-07-05T09:56:20Z"},{"alias_kind":"pith_short_8","alias_value":"Y5TGWAMU","created_at":"2026-07-05T09:56:20Z"}],"graph_snapshots":[{"event_id":"sha256:f2e645aa07e801d0273de734043ad5125792c28b5dd8ab97d603d56d78c2455f","target":"graph","created_at":"2026-07-05T09:56:20Z","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/2402.17355/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the current landscape of large language models (LLMs), the process of instruction tuning serves as an essential step. Considering the high computing power overhead, data-efficient instruction tuning was proposed to reduce the training data size in this process, aiming at selecting high-quality instructional data. Nevertheless, we argue that most current data-efficient instruction-tuning methods are highly dependent on the quality of the original instruction-tuning dataset. When it comes to datasets synthesized by LLMs, a common scenario in this field, dirty samples will even be selected wit","authors_text":"Haobo Wang, Junbo Zhao, Qi Zhang, Yiming Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T09:47:36Z","title":"RECOST: External Knowledge Guided Data-efficient Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17355","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":"sha256:9e0c52235ffc1b44a1fa2f34fdd579d0d8f7bed6f3a63421898332420f990f1c","target":"record","created_at":"2026-07-05T09:56:20Z","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":"916d126b4aaa6dbad443f967450de666348507eb661ceb13fc89391a2342fb1e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T09:47:36Z","title_canon_sha256":"a576fec7dd7045adf6a12867b8b2eb9ea8ea34731a2ff1b27007b96c08492249"},"schema_version":"1.0","source":{"id":"2402.17355","kind":"arxiv","version":1}},"canonical_sha256":"c7666b0194ebc3b8d57064988edca338f43eeaf9080d0e6950299097d07c5480","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7666b0194ebc3b8d57064988edca338f43eeaf9080d0e6950299097d07c5480","first_computed_at":"2026-07-05T09:56:20.845968Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:20.845968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a5QLUhTM/9ZMlmp7xgamIS1JFVFxUfeoG0UsJq0pKiqPV/EDJij4xYIX2grINtIJ34e9D3Q/mcRcHORjEWUvBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:20.846401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17355","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e0c52235ffc1b44a1fa2f34fdd579d0d8f7bed6f3a63421898332420f990f1c","sha256:f2e645aa07e801d0273de734043ad5125792c28b5dd8ab97d603d56d78c2455f"],"state_sha256":"996c51c6f01ee3703680e468de10e5eeacfacff74dfbb0d4aff83a1c287b814b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rF6cg5BQ2cdJ8csFRY+AOR1Z2aLDTFjPnt9S0KhuSBzuL2iZgmDdzoLvUQazyJ5fr9CDPOKiqfnX/bfmpAUZDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T17:05:31.753116Z","bundle_sha256":"a321a45e030b161f711f49fdc93bee3c39873c684c1eb0fce8dd23b90a6ef1a5"}}