{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q4POY7AO3ZCKHKZWFF4GUNDYS2","short_pith_number":"pith:Q4POY7AO","canonical_record":{"source":{"id":"2403.11124","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-17T07:08:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"928a1d2765caa0ffa174805d3568af19498c082648a066ba7911bf64cb220ac1","abstract_canon_sha256":"dff014d54f98b822be50473e75d9ad83b3e987e77110c942a361d23d53822b32"},"schema_version":"1.0"},"canonical_sha256":"871eec7c0ede44a3ab3629786a347896a33bf781af611ed6f1a32e951ae426a5","source":{"kind":"arxiv","id":"2403.11124","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11124","created_at":"2026-07-05T08:02:25Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11124v2","created_at":"2026-07-05T08:02:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11124","created_at":"2026-07-05T08:02:25Z"},{"alias_kind":"pith_short_12","alias_value":"Q4POY7AO3ZCK","created_at":"2026-07-05T08:02:25Z"},{"alias_kind":"pith_short_16","alias_value":"Q4POY7AO3ZCKHKZW","created_at":"2026-07-05T08:02:25Z"},{"alias_kind":"pith_short_8","alias_value":"Q4POY7AO","created_at":"2026-07-05T08:02:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q4POY7AO3ZCKHKZWFF4GUNDYS2","target":"record","payload":{"canonical_record":{"source":{"id":"2403.11124","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-17T07:08:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"928a1d2765caa0ffa174805d3568af19498c082648a066ba7911bf64cb220ac1","abstract_canon_sha256":"dff014d54f98b822be50473e75d9ad83b3e987e77110c942a361d23d53822b32"},"schema_version":"1.0"},"canonical_sha256":"871eec7c0ede44a3ab3629786a347896a33bf781af611ed6f1a32e951ae426a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:25.212116Z","signature_b64":"lcCiqkCqn0lyTLHM3qRO/6ftbFWMFv50rtpORUoA23eZHioF8EA2fItGGm4O8lJnrTyWphx2S6BD97c+bncsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"871eec7c0ede44a3ab3629786a347896a33bf781af611ed6f1a32e951ae426a5","last_reissued_at":"2026-07-05T08:02:25.211616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:25.211616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.11124","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":"2026-07-05T08:02:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GWSIJZ1b2vGTiUN1hVtnRXep+P1o4TUCgQo02SwdCGGpwAl/VUUKNKaDyp2dvms5yOO3YpHCpvqItO8ifqJ5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:08:12.839597Z"},"content_sha256":"b1ae4ed13ece586c4903109329e9f15280bf028763f39a6abf37cf46cf9deba2","schema_version":"1.0","event_id":"sha256:b1ae4ed13ece586c4903109329e9f15280bf028763f39a6abf37cf46cf9deba2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q4POY7AO3ZCKHKZWFF4GUNDYS2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bowen Yu, Feifan Song, Fei Huang, Haiyang Yu, Hao Lang, Houfeng Wang, Yongbin Li","submitted_at":"2024-03-17T07:08:55Z","abstract_excerpt":"Alignment with human preference prevents large language models (LLMs) from generating misleading or toxic content while requiring high-cost human feedback. Assuming resources of human annotation are limited, there are two different ways of allocating considered: more diverse PROMPTS or more diverse RESPONSES to be labeled. Nonetheless, a straightforward comparison between their impact is absent. In this work, we first control the diversity of both sides according to the number of samples for fine-tuning, which can directly reflect their influence. We find that instead of numerous prompts, more"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11124","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/2403.11124/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":"2026-07-05T08:02:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9iKPF+r+WovbBDN1CgYVPPoaSjlvaCzc/PRzGJ18xVHjnssSNxqFWg+E9Dhmi93HL/akekyKOPGsedZonUrQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:08:12.841243Z"},"content_sha256":"4624c4a891dd377f4eb9e0e63b5ab6fa6628fbf796f871f35b8e1ba4d9d5d77c","schema_version":"1.0","event_id":"sha256:4624c4a891dd377f4eb9e0e63b5ab6fa6628fbf796f871f35b8e1ba4d9d5d77c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q4POY7AO3ZCKHKZWFF4GUNDYS2/bundle.json","state_url":"https://pith.science/pith/Q4POY7AO3ZCKHKZWFF4GUNDYS2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q4POY7AO3ZCKHKZWFF4GUNDYS2/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":"2026-08-11T10:08:12Z","links":{"resolver":"https://pith.science/pith/Q4POY7AO3ZCKHKZWFF4GUNDYS2","bundle":"https://pith.science/pith/Q4POY7AO3ZCKHKZWFF4GUNDYS2/bundle.json","state":"https://pith.science/pith/Q4POY7AO3ZCKHKZWFF4GUNDYS2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q4POY7AO3ZCKHKZWFF4GUNDYS2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q4POY7AO3ZCKHKZWFF4GUNDYS2","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":"dff014d54f98b822be50473e75d9ad83b3e987e77110c942a361d23d53822b32","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-17T07:08:55Z","title_canon_sha256":"928a1d2765caa0ffa174805d3568af19498c082648a066ba7911bf64cb220ac1"},"schema_version":"1.0","source":{"id":"2403.11124","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11124","created_at":"2026-07-05T08:02:25Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11124v2","created_at":"2026-07-05T08:02:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11124","created_at":"2026-07-05T08:02:25Z"},{"alias_kind":"pith_short_12","alias_value":"Q4POY7AO3ZCK","created_at":"2026-07-05T08:02:25Z"},{"alias_kind":"pith_short_16","alias_value":"Q4POY7AO3ZCKHKZW","created_at":"2026-07-05T08:02:25Z"},{"alias_kind":"pith_short_8","alias_value":"Q4POY7AO","created_at":"2026-07-05T08:02:25Z"}],"graph_snapshots":[{"event_id":"sha256:4624c4a891dd377f4eb9e0e63b5ab6fa6628fbf796f871f35b8e1ba4d9d5d77c","target":"graph","created_at":"2026-07-05T08:02:25Z","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/2403.11124/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Alignment with human preference prevents large language models (LLMs) from generating misleading or toxic content while requiring high-cost human feedback. Assuming resources of human annotation are limited, there are two different ways of allocating considered: more diverse PROMPTS or more diverse RESPONSES to be labeled. Nonetheless, a straightforward comparison between their impact is absent. In this work, we first control the diversity of both sides according to the number of samples for fine-tuning, which can directly reflect their influence. We find that instead of numerous prompts, more","authors_text":"Bowen Yu, Feifan Song, Fei Huang, Haiyang Yu, Hao Lang, Houfeng Wang, Yongbin Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-17T07:08:55Z","title":"Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11124","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:b1ae4ed13ece586c4903109329e9f15280bf028763f39a6abf37cf46cf9deba2","target":"record","created_at":"2026-07-05T08:02:25Z","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":"dff014d54f98b822be50473e75d9ad83b3e987e77110c942a361d23d53822b32","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-17T07:08:55Z","title_canon_sha256":"928a1d2765caa0ffa174805d3568af19498c082648a066ba7911bf64cb220ac1"},"schema_version":"1.0","source":{"id":"2403.11124","kind":"arxiv","version":2}},"canonical_sha256":"871eec7c0ede44a3ab3629786a347896a33bf781af611ed6f1a32e951ae426a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"871eec7c0ede44a3ab3629786a347896a33bf781af611ed6f1a32e951ae426a5","first_computed_at":"2026-07-05T08:02:25.211616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:25.211616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lcCiqkCqn0lyTLHM3qRO/6ftbFWMFv50rtpORUoA23eZHioF8EA2fItGGm4O8lJnrTyWphx2S6BD97c+bncsCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:25.212116Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11124","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1ae4ed13ece586c4903109329e9f15280bf028763f39a6abf37cf46cf9deba2","sha256:4624c4a891dd377f4eb9e0e63b5ab6fa6628fbf796f871f35b8e1ba4d9d5d77c"],"state_sha256":"e6592108b7c7605e2f0aefde9d809224c94b32edf165d4b9fbecaacc157a9f4e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jcZrNXfyJkSyMS79y0sMOLgV+UgsBnR389XiJ9hwr4OKUhpwYb0InIbErh1r6yDmVUM+hfOjSX5twhPbKoGnDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T10:08:12.868390Z","bundle_sha256":"144e7792260847431012da5c31340a4b7baa8350a6b8ce9e820e18618a58dd26"}}