{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IJ3IUXKY4JYDWKQLT22RUEJEMW","short_pith_number":"pith:IJ3IUXKY","canonical_record":{"source":{"id":"2503.01836","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T18:56:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db0211e4c4ac732700db99dbc752b80a48a8113afbaf2aace23170f1000d80cb","abstract_canon_sha256":"8b65e1befa7a4a878eef63b66aff88e5b68587f8c3282d1cb71a7b96682eea30"},"schema_version":"1.0"},"canonical_sha256":"42768a5d58e2703b2a0b9eb51a1124659baba9b4e0796d62cb4ea370a58b797a","source":{"kind":"arxiv","id":"2503.01836","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01836","created_at":"2026-07-05T10:23:16Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01836v1","created_at":"2026-07-05T10:23:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01836","created_at":"2026-07-05T10:23:16Z"},{"alias_kind":"pith_short_12","alias_value":"IJ3IUXKY4JYD","created_at":"2026-07-05T10:23:16Z"},{"alias_kind":"pith_short_16","alias_value":"IJ3IUXKY4JYDWKQL","created_at":"2026-07-05T10:23:16Z"},{"alias_kind":"pith_short_8","alias_value":"IJ3IUXKY","created_at":"2026-07-05T10:23:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IJ3IUXKY4JYDWKQLT22RUEJEMW","target":"record","payload":{"canonical_record":{"source":{"id":"2503.01836","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T18:56:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db0211e4c4ac732700db99dbc752b80a48a8113afbaf2aace23170f1000d80cb","abstract_canon_sha256":"8b65e1befa7a4a878eef63b66aff88e5b68587f8c3282d1cb71a7b96682eea30"},"schema_version":"1.0"},"canonical_sha256":"42768a5d58e2703b2a0b9eb51a1124659baba9b4e0796d62cb4ea370a58b797a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:16.324582Z","signature_b64":"RXD1V8YS+6/5ORtfOrPjBb/IfORC4bi/Za6XPdTVzp1cOsBqHpNgsdTnDRwv/ApXZpjSSc1cFuDnGMEt/0u7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42768a5d58e2703b2a0b9eb51a1124659baba9b4e0796d62cb4ea370a58b797a","last_reissued_at":"2026-07-05T10:23:16.323920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:16.323920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.01836","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":"2026-07-05T10:23:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s/kxSTyL+ydJx9itgx8p/u+W9ECMjSDaLiKX2GEHGVoFZPFNDlFH+aEM1uCFIBBRbU60FC4O1KPECOYhiLHJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:20:31.743592Z"},"content_sha256":"2d2ff733f693a23b0e07efd1ad7e10a9b2fcb8347a688a193f16c5ae6aa3c6b1","schema_version":"1.0","event_id":"sha256:2d2ff733f693a23b0e07efd1ad7e10a9b2fcb8347a688a193f16c5ae6aa3c6b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IJ3IUXKY4JYDWKQLT22RUEJEMW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongping Chen, Lingfeng Yang, Pan Zhou, Weiwei Lin, Wenxuan Shen, Yao Wan, Yisen Li","submitted_at":"2025-03-03T18:56:44Z","abstract_excerpt":"Distilling advanced Large Language Models' instruction-following capabilities into smaller models using a selected subset has become a mainstream approach in model training. While existing synthetic instruction data selection strategies rely mainly on single-dimensional signals (i.e., reward scores, model perplexity), they fail to capture the complexity of instruction-following across diverse fields. Therefore, we investigate more diverse signals to capture comprehensive instruction-response pair characteristics and propose three foundational metrics that leverage Multi-LLM wisdom, informed by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01836","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/2503.01836/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":"2026-07-05T10:23:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sbjyWpwgU/WuUP+wyjR5GtoNlq22a2vYT+Tb10OAF0UZ018WzeqWOuKeotbetTpLfmJc6eegi+7but7GLuaQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:20:31.744523Z"},"content_sha256":"63ff8b4068bc4477a9f36b27ac41f0f3511e11ff00da98cc41ffe1a43f4d4fc5","schema_version":"1.0","event_id":"sha256:63ff8b4068bc4477a9f36b27ac41f0f3511e11ff00da98cc41ffe1a43f4d4fc5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IJ3IUXKY4JYDWKQLT22RUEJEMW/bundle.json","state_url":"https://pith.science/pith/IJ3IUXKY4JYDWKQLT22RUEJEMW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IJ3IUXKY4JYDWKQLT22RUEJEMW/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":"2026-08-09T11:20:31Z","links":{"resolver":"https://pith.science/pith/IJ3IUXKY4JYDWKQLT22RUEJEMW","bundle":"https://pith.science/pith/IJ3IUXKY4JYDWKQLT22RUEJEMW/bundle.json","state":"https://pith.science/pith/IJ3IUXKY4JYDWKQLT22RUEJEMW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IJ3IUXKY4JYDWKQLT22RUEJEMW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IJ3IUXKY4JYDWKQLT22RUEJEMW","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":"8b65e1befa7a4a878eef63b66aff88e5b68587f8c3282d1cb71a7b96682eea30","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T18:56:44Z","title_canon_sha256":"db0211e4c4ac732700db99dbc752b80a48a8113afbaf2aace23170f1000d80cb"},"schema_version":"1.0","source":{"id":"2503.01836","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01836","created_at":"2026-07-05T10:23:16Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01836v1","created_at":"2026-07-05T10:23:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01836","created_at":"2026-07-05T10:23:16Z"},{"alias_kind":"pith_short_12","alias_value":"IJ3IUXKY4JYD","created_at":"2026-07-05T10:23:16Z"},{"alias_kind":"pith_short_16","alias_value":"IJ3IUXKY4JYDWKQL","created_at":"2026-07-05T10:23:16Z"},{"alias_kind":"pith_short_8","alias_value":"IJ3IUXKY","created_at":"2026-07-05T10:23:16Z"}],"graph_snapshots":[{"event_id":"sha256:63ff8b4068bc4477a9f36b27ac41f0f3511e11ff00da98cc41ffe1a43f4d4fc5","target":"graph","created_at":"2026-07-05T10:23:16Z","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/2503.01836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distilling advanced Large Language Models' instruction-following capabilities into smaller models using a selected subset has become a mainstream approach in model training. While existing synthetic instruction data selection strategies rely mainly on single-dimensional signals (i.e., reward scores, model perplexity), they fail to capture the complexity of instruction-following across diverse fields. Therefore, we investigate more diverse signals to capture comprehensive instruction-response pair characteristics and propose three foundational metrics that leverage Multi-LLM wisdom, informed by","authors_text":"Dongping Chen, Lingfeng Yang, Pan Zhou, Weiwei Lin, Wenxuan Shen, Yao Wan, Yisen Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T18:56:44Z","title":"CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01836","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":"sha256:2d2ff733f693a23b0e07efd1ad7e10a9b2fcb8347a688a193f16c5ae6aa3c6b1","target":"record","created_at":"2026-07-05T10:23:16Z","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":"8b65e1befa7a4a878eef63b66aff88e5b68587f8c3282d1cb71a7b96682eea30","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T18:56:44Z","title_canon_sha256":"db0211e4c4ac732700db99dbc752b80a48a8113afbaf2aace23170f1000d80cb"},"schema_version":"1.0","source":{"id":"2503.01836","kind":"arxiv","version":1}},"canonical_sha256":"42768a5d58e2703b2a0b9eb51a1124659baba9b4e0796d62cb4ea370a58b797a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42768a5d58e2703b2a0b9eb51a1124659baba9b4e0796d62cb4ea370a58b797a","first_computed_at":"2026-07-05T10:23:16.323920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:16.323920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RXD1V8YS+6/5ORtfOrPjBb/IfORC4bi/Za6XPdTVzp1cOsBqHpNgsdTnDRwv/ApXZpjSSc1cFuDnGMEt/0u7Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:16.324582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01836","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d2ff733f693a23b0e07efd1ad7e10a9b2fcb8347a688a193f16c5ae6aa3c6b1","sha256:63ff8b4068bc4477a9f36b27ac41f0f3511e11ff00da98cc41ffe1a43f4d4fc5"],"state_sha256":"265fcef06dacf699fa58dfefa705e7622b079ea9736f877e5c93b74a41c9b287"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ncWCrjE5FegFYqRuxO3TP8Onuyle69Qfd20wXlG7TvtL81emQSFZR65KC2q4ArXop6G7G0GN9efsGk8fy5A+CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:20:31.751416Z","bundle_sha256":"cafbfedbf957a59af086720dd1bf97ef94a13c3141c3c94b64faf91951de72ef"}}