{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:I5FD5HZ2NBTGIS7XCJKTBZ6P5F","short_pith_number":"pith:I5FD5HZ2","canonical_record":{"source":{"id":"2505.05327","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T15:17:37Z","cross_cats_sorted":[],"title_canon_sha256":"c57ec4872e3f949ca7372a327aca28d8a124e574e8c291538961654983a68ea5","abstract_canon_sha256":"e3d6e0addde383bc89e5ef08a61c41ef9d8f7706e3452cb423c1274f6de4e1f0"},"schema_version":"1.0"},"canonical_sha256":"474a3e9f3a6866644bf7125530e7cfe95ae91e4dad4938717d2e4badde599fe7","source":{"kind":"arxiv","id":"2505.05327","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05327","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05327v2","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05327","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"I5FD5HZ2NBTG","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"I5FD5HZ2NBTGIS7X","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"I5FD5HZ2","created_at":"2026-07-05T11:04:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:I5FD5HZ2NBTGIS7XCJKTBZ6P5F","target":"record","payload":{"canonical_record":{"source":{"id":"2505.05327","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T15:17:37Z","cross_cats_sorted":[],"title_canon_sha256":"c57ec4872e3f949ca7372a327aca28d8a124e574e8c291538961654983a68ea5","abstract_canon_sha256":"e3d6e0addde383bc89e5ef08a61c41ef9d8f7706e3452cb423c1274f6de4e1f0"},"schema_version":"1.0"},"canonical_sha256":"474a3e9f3a6866644bf7125530e7cfe95ae91e4dad4938717d2e4badde599fe7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:50.727588Z","signature_b64":"xu3nsJOSq9M5ET2b+Z0piU84Be8GAUNnK+vv4uoszYk+fiymrMIQHPl0+CkzOyG/h/7Pys+K1HaAXNUacv1BBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"474a3e9f3a6866644bf7125530e7cfe95ae91e4dad4938717d2e4badde599fe7","last_reissued_at":"2026-07-05T11:04:50.727019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:50.727019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.05327","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":"2026-07-05T11:04:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JYwdIo5808F/l/FCpBpXx+nlF9Whku/cai5PrDi/MwGF1i4YPK+jKIB4gL7QBW6SajxF2zC4oxl+Lksn4838Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:40:24.187127Z"},"content_sha256":"e0e2534770bb4888d627fbd1bae0e33af0c219bd4d39387e4181d32618d933fe","schema_version":"1.0","event_id":"sha256:e0e2534770bb4888d627fbd1bae0e33af0c219bd4d39387e4181d32618d933fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:I5FD5HZ2NBTGIS7XCJKTBZ6P5F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fangwei Zhu, Linli Yao, Qingxiu Dong, Yixin Yang, Zhifang Sui","submitted_at":"2025-05-08T15:17:37Z","abstract_excerpt":"Data selection for instruction tuning is crucial for improving the performance of large language models (LLMs) while reducing training costs. In this paper, we propose Refined Contribution Measurement with In-Context Learning (RICo), a novel gradient-free method that quantifies the fine-grained contribution of individual samples to both task-level and global-level model performance. RICo enables more accurate identification of high-contribution data, leading to better instruction tuning. We further introduce a lightweight selection paradigm trained on RICo scores, enabling scalable data select"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05327","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/2505.05327/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":"2026-07-05T11:04:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EAgV8FGDwlGz3ePM/usWN6XItKMSuGJ7Jm8Jm397WChVcTuw1C2hSqS7Wv7g6hYZuBF+BbdbieLF39L9bqXZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:40:24.187518Z"},"content_sha256":"a9918fc04d50ac47c5264b8065f3bd722fab8d7ac22a37efd07c9a7c0b44dd6b","schema_version":"1.0","event_id":"sha256:a9918fc04d50ac47c5264b8065f3bd722fab8d7ac22a37efd07c9a7c0b44dd6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I5FD5HZ2NBTGIS7XCJKTBZ6P5F/bundle.json","state_url":"https://pith.science/pith/I5FD5HZ2NBTGIS7XCJKTBZ6P5F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I5FD5HZ2NBTGIS7XCJKTBZ6P5F/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":"2026-07-07T12:40:24Z","links":{"resolver":"https://pith.science/pith/I5FD5HZ2NBTGIS7XCJKTBZ6P5F","bundle":"https://pith.science/pith/I5FD5HZ2NBTGIS7XCJKTBZ6P5F/bundle.json","state":"https://pith.science/pith/I5FD5HZ2NBTGIS7XCJKTBZ6P5F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I5FD5HZ2NBTGIS7XCJKTBZ6P5F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I5FD5HZ2NBTGIS7XCJKTBZ6P5F","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":"e3d6e0addde383bc89e5ef08a61c41ef9d8f7706e3452cb423c1274f6de4e1f0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T15:17:37Z","title_canon_sha256":"c57ec4872e3f949ca7372a327aca28d8a124e574e8c291538961654983a68ea5"},"schema_version":"1.0","source":{"id":"2505.05327","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05327","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05327v2","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05327","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"I5FD5HZ2NBTG","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"I5FD5HZ2NBTGIS7X","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"I5FD5HZ2","created_at":"2026-07-05T11:04:50Z"}],"graph_snapshots":[{"event_id":"sha256:a9918fc04d50ac47c5264b8065f3bd722fab8d7ac22a37efd07c9a7c0b44dd6b","target":"graph","created_at":"2026-07-05T11:04:50Z","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/2505.05327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data selection for instruction tuning is crucial for improving the performance of large language models (LLMs) while reducing training costs. In this paper, we propose Refined Contribution Measurement with In-Context Learning (RICo), a novel gradient-free method that quantifies the fine-grained contribution of individual samples to both task-level and global-level model performance. RICo enables more accurate identification of high-contribution data, leading to better instruction tuning. We further introduce a lightweight selection paradigm trained on RICo scores, enabling scalable data select","authors_text":"Fangwei Zhu, Linli Yao, Qingxiu Dong, Yixin Yang, Zhifang Sui","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T15:17:37Z","title":"RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05327","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:e0e2534770bb4888d627fbd1bae0e33af0c219bd4d39387e4181d32618d933fe","target":"record","created_at":"2026-07-05T11:04:50Z","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":"e3d6e0addde383bc89e5ef08a61c41ef9d8f7706e3452cb423c1274f6de4e1f0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T15:17:37Z","title_canon_sha256":"c57ec4872e3f949ca7372a327aca28d8a124e574e8c291538961654983a68ea5"},"schema_version":"1.0","source":{"id":"2505.05327","kind":"arxiv","version":2}},"canonical_sha256":"474a3e9f3a6866644bf7125530e7cfe95ae91e4dad4938717d2e4badde599fe7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"474a3e9f3a6866644bf7125530e7cfe95ae91e4dad4938717d2e4badde599fe7","first_computed_at":"2026-07-05T11:04:50.727019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:50.727019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xu3nsJOSq9M5ET2b+Z0piU84Be8GAUNnK+vv4uoszYk+fiymrMIQHPl0+CkzOyG/h/7Pys+K1HaAXNUacv1BBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:50.727588Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05327","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0e2534770bb4888d627fbd1bae0e33af0c219bd4d39387e4181d32618d933fe","sha256:a9918fc04d50ac47c5264b8065f3bd722fab8d7ac22a37efd07c9a7c0b44dd6b"],"state_sha256":"abf9e94b8c70ec7a6459f6291a7da355a0841936c9f5ef9b677509e9be25cded"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bOAz6ofa7rvYY0WKJT+KecOgk4U4eosQPPot34UZjehOt2t1NmGFpY67iotFjCb0e9Fb++j28AwuD4305LkWAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:40:24.189438Z","bundle_sha256":"15c812263b30e45524372359846cf8004cc86fc5aac88c42a6a0efd1443dcab1"}}