{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6U357Z4A3V6JQTLVQOBPZ7X5MT","short_pith_number":"pith:6U357Z4A","canonical_record":{"source":{"id":"2405.00705","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T04:56:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3f4ad844dd2cd0d1267c219acdf78eac1af72bb4c06cb732ec573f58fcccdb5a","abstract_canon_sha256":"e4f066d877440a3cc6d83a8033785ceab3f323bc3c1be5141303d25cb78cfe3c"},"schema_version":"1.0"},"canonical_sha256":"f537dfe780dd7c984d758382fcfefd64ed308e6a0e0807d1a94396cfb6e9bc19","source":{"kind":"arxiv","id":"2405.00705","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.00705","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"arxiv_version","alias_value":"2405.00705v2","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00705","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"pith_short_12","alias_value":"6U357Z4A3V6J","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"pith_short_16","alias_value":"6U357Z4A3V6JQTLV","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"pith_short_8","alias_value":"6U357Z4A","created_at":"2026-07-05T09:28:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6U357Z4A3V6JQTLVQOBPZ7X5MT","target":"record","payload":{"canonical_record":{"source":{"id":"2405.00705","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T04:56:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3f4ad844dd2cd0d1267c219acdf78eac1af72bb4c06cb732ec573f58fcccdb5a","abstract_canon_sha256":"e4f066d877440a3cc6d83a8033785ceab3f323bc3c1be5141303d25cb78cfe3c"},"schema_version":"1.0"},"canonical_sha256":"f537dfe780dd7c984d758382fcfefd64ed308e6a0e0807d1a94396cfb6e9bc19","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:11.907149Z","signature_b64":"XQxIvxS2t/n+PasgNN1H6bR2ls/SF+Y/EEDKRZzhiAaqKcPqKwF0mpfM45pcAK5QbRBMimjjtjpo/zS+cSB4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f537dfe780dd7c984d758382fcfefd64ed308e6a0e0807d1a94396cfb6e9bc19","last_reissued_at":"2026-07-05T09:28:11.906689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:11.906689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.00705","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":"2026-07-05T09:28:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KTeVZNuEpcDVWMvkBL2L2Tp/xpFbcQrcffGANwb2MH3K485dRMtHorlZv209ia+PpGNG2qzaezbK3akA2edADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:50:05.107819Z"},"content_sha256":"54bc2183dd43952c1e1972504486992e5a8c94bb6ebf701ea2d30f51f691b733","schema_version":"1.0","event_id":"sha256:54bc2183dd43952c1e1972504486992e5a8c94bb6ebf701ea2d30f51f691b733"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6U357Z4A3V6JQTLVQOBPZ7X5MT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ang Li, Guoheng Sun, Hongyi Wang, Yexiao He, Yongkai Wu, Yucong Dai, Zheyu Shen, Ziyao Wang","submitted_at":"2024-04-23T04:56:48Z","abstract_excerpt":"The pre-trained Large Language Models (LLMs) can be adapted for many downstream tasks and tailored to align with human preferences through fine-tuning. Recent studies have discovered that LLMs can achieve desirable performance with only a small amount of high-quality data, suggesting that a large amount of the data in these extensive datasets is redundant or even harmful. Identifying high-quality data from vast datasets to curate small yet effective datasets has emerged as a critical challenge. In this paper, we introduce SHED, an automated dataset refinement framework based on Shapley value f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00705","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/2405.00705/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":"2026-07-05T09:28:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J7Jt76fV7aLA0eZ5s96tylkpT8mVIPFNJvV2jgg5LGl66cPA+qASH4VUqyHNc9QMlE4wDyzljARdGtOflmLABw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:50:05.108790Z"},"content_sha256":"d5e9ea8cdf59f443cf463da91641f281ee7154c17211ef829b3d6df446742b33","schema_version":"1.0","event_id":"sha256:d5e9ea8cdf59f443cf463da91641f281ee7154c17211ef829b3d6df446742b33"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6U357Z4A3V6JQTLVQOBPZ7X5MT/bundle.json","state_url":"https://pith.science/pith/6U357Z4A3V6JQTLVQOBPZ7X5MT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6U357Z4A3V6JQTLVQOBPZ7X5MT/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":"2026-08-10T18:50:05Z","links":{"resolver":"https://pith.science/pith/6U357Z4A3V6JQTLVQOBPZ7X5MT","bundle":"https://pith.science/pith/6U357Z4A3V6JQTLVQOBPZ7X5MT/bundle.json","state":"https://pith.science/pith/6U357Z4A3V6JQTLVQOBPZ7X5MT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6U357Z4A3V6JQTLVQOBPZ7X5MT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6U357Z4A3V6JQTLVQOBPZ7X5MT","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":"e4f066d877440a3cc6d83a8033785ceab3f323bc3c1be5141303d25cb78cfe3c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T04:56:48Z","title_canon_sha256":"3f4ad844dd2cd0d1267c219acdf78eac1af72bb4c06cb732ec573f58fcccdb5a"},"schema_version":"1.0","source":{"id":"2405.00705","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.00705","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"arxiv_version","alias_value":"2405.00705v2","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00705","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"pith_short_12","alias_value":"6U357Z4A3V6J","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"pith_short_16","alias_value":"6U357Z4A3V6JQTLV","created_at":"2026-07-05T09:28:11Z"},{"alias_kind":"pith_short_8","alias_value":"6U357Z4A","created_at":"2026-07-05T09:28:11Z"}],"graph_snapshots":[{"event_id":"sha256:d5e9ea8cdf59f443cf463da91641f281ee7154c17211ef829b3d6df446742b33","target":"graph","created_at":"2026-07-05T09:28:11Z","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/2405.00705/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The pre-trained Large Language Models (LLMs) can be adapted for many downstream tasks and tailored to align with human preferences through fine-tuning. Recent studies have discovered that LLMs can achieve desirable performance with only a small amount of high-quality data, suggesting that a large amount of the data in these extensive datasets is redundant or even harmful. Identifying high-quality data from vast datasets to curate small yet effective datasets has emerged as a critical challenge. In this paper, we introduce SHED, an automated dataset refinement framework based on Shapley value f","authors_text":"Ang Li, Guoheng Sun, Hongyi Wang, Yexiao He, Yongkai Wu, Yucong Dai, Zheyu Shen, Ziyao Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T04:56:48Z","title":"SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00705","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":"sha256:54bc2183dd43952c1e1972504486992e5a8c94bb6ebf701ea2d30f51f691b733","target":"record","created_at":"2026-07-05T09:28:11Z","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":"e4f066d877440a3cc6d83a8033785ceab3f323bc3c1be5141303d25cb78cfe3c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T04:56:48Z","title_canon_sha256":"3f4ad844dd2cd0d1267c219acdf78eac1af72bb4c06cb732ec573f58fcccdb5a"},"schema_version":"1.0","source":{"id":"2405.00705","kind":"arxiv","version":2}},"canonical_sha256":"f537dfe780dd7c984d758382fcfefd64ed308e6a0e0807d1a94396cfb6e9bc19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f537dfe780dd7c984d758382fcfefd64ed308e6a0e0807d1a94396cfb6e9bc19","first_computed_at":"2026-07-05T09:28:11.906689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:11.906689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XQxIvxS2t/n+PasgNN1H6bR2ls/SF+Y/EEDKRZzhiAaqKcPqKwF0mpfM45pcAK5QbRBMimjjtjpo/zS+cSB4Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:11.907149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.00705","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54bc2183dd43952c1e1972504486992e5a8c94bb6ebf701ea2d30f51f691b733","sha256:d5e9ea8cdf59f443cf463da91641f281ee7154c17211ef829b3d6df446742b33"],"state_sha256":"2ba9a7cf8f33fb5b380788cf89fc8d98546dce0e7f42c5eab1cb1f2c9feda045"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H2ka7xJWTHmZNevltavgRk/aYeUe0LVJpBIzTGloI0bAzszFo4JFga1ZWPapYtemV6Sx+qb4FjJUoTW7HPrZAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:50:05.116120Z","bundle_sha256":"4580e31fdd591ab55078754b66a9c6ee1c09cbf10100f6a48e3d068b2bf1c8a2"}}