{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RLNMVC3E5LQZLLE3R74A2XSZ3Y","short_pith_number":"pith:RLNMVC3E","canonical_record":{"source":{"id":"2505.24768","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T16:31:05Z","cross_cats_sorted":[],"title_canon_sha256":"2983a0f422071d46be3ab68164a85c92d6cc3fc86f06b420c9dea5ee4d37920f","abstract_canon_sha256":"800c8c9bc48deaa7f903bf08849e1a63fafcf1c1f487867d2b0b0cc1eb1b2aab"},"schema_version":"1.0"},"canonical_sha256":"8adaca8b64eae195ac9b8ff80d5e59de34572333b30fcaebd02a77f34efba89f","source":{"kind":"arxiv","id":"2505.24768","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24768","created_at":"2026-07-05T11:12:56Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24768v1","created_at":"2026-07-05T11:12:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24768","created_at":"2026-07-05T11:12:56Z"},{"alias_kind":"pith_short_12","alias_value":"RLNMVC3E5LQZ","created_at":"2026-07-05T11:12:56Z"},{"alias_kind":"pith_short_16","alias_value":"RLNMVC3E5LQZLLE3","created_at":"2026-07-05T11:12:56Z"},{"alias_kind":"pith_short_8","alias_value":"RLNMVC3E","created_at":"2026-07-05T11:12:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RLNMVC3E5LQZLLE3R74A2XSZ3Y","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24768","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T16:31:05Z","cross_cats_sorted":[],"title_canon_sha256":"2983a0f422071d46be3ab68164a85c92d6cc3fc86f06b420c9dea5ee4d37920f","abstract_canon_sha256":"800c8c9bc48deaa7f903bf08849e1a63fafcf1c1f487867d2b0b0cc1eb1b2aab"},"schema_version":"1.0"},"canonical_sha256":"8adaca8b64eae195ac9b8ff80d5e59de34572333b30fcaebd02a77f34efba89f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:56.305452Z","signature_b64":"KrKNUcCFvKg65cI1RmLb/kYNnWSNRQnH/oka/7gtPwWr6g8bN28nmE71ZtIEBHEAdryvLujpVb11FD2EXPenCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8adaca8b64eae195ac9b8ff80d5e59de34572333b30fcaebd02a77f34efba89f","last_reissued_at":"2026-07-05T11:12:56.304844Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:56.304844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24768","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":"2026-07-05T11:12:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dFoH61thvH5m31VI/oU0/OEDHsT4mOUxtFQasJd3qP2LCScGHaYOs5kmFUQNnj4fooGw88It5L8KhaLvwjAJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:07:15.681336Z"},"content_sha256":"e6b90bc209af2067a1dcfd402f8692985ce416abdbec8e56a62180910f53222f","schema_version":"1.0","event_id":"sha256:e6b90bc209af2067a1dcfd402f8692985ce416abdbec8e56a62180910f53222f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RLNMVC3E5LQZLLE3R74A2XSZ3Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Macro to Micro: Probing Dataset Diversity in Language Model Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoyu Li, Kun Liu, Xuhong Li, Yiming Dong","submitted_at":"2025-05-30T16:31:05Z","abstract_excerpt":"Dataset diversity plays a pivotal role for the successful training of many machine learning models, particularly in the supervised fine-tuning (SFT) stage of large language model (LLM) development. Despite increasing recognition of its importance, systematic analyses of dataset diversity still remain underexplored. To address this gap, this work presents a systematic taxonomy of existing diversity-control strategies, which primarily focus on the instruction component, operating at either macroscopic (entire instruction semantics) or mesoscopic levels (instruction units), and furthermore introd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24768","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/2505.24768/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":"2026-07-05T11:12:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oHnY/G/nA+sltwGIWu8pDr7PmeG6nlX+wdzjM1XddVVaMnZV9xGYSGr5g8UZcNxg0mMskirW8594HFNmF0D4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:07:15.681887Z"},"content_sha256":"12e27f941b859a58721d29e2a55338c2688400f626cd3ef22724d7420d4901d7","schema_version":"1.0","event_id":"sha256:12e27f941b859a58721d29e2a55338c2688400f626cd3ef22724d7420d4901d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RLNMVC3E5LQZLLE3R74A2XSZ3Y/bundle.json","state_url":"https://pith.science/pith/RLNMVC3E5LQZLLE3R74A2XSZ3Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RLNMVC3E5LQZLLE3R74A2XSZ3Y/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":"2026-08-09T12:07:15Z","links":{"resolver":"https://pith.science/pith/RLNMVC3E5LQZLLE3R74A2XSZ3Y","bundle":"https://pith.science/pith/RLNMVC3E5LQZLLE3R74A2XSZ3Y/bundle.json","state":"https://pith.science/pith/RLNMVC3E5LQZLLE3R74A2XSZ3Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RLNMVC3E5LQZLLE3R74A2XSZ3Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RLNMVC3E5LQZLLE3R74A2XSZ3Y","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":"800c8c9bc48deaa7f903bf08849e1a63fafcf1c1f487867d2b0b0cc1eb1b2aab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T16:31:05Z","title_canon_sha256":"2983a0f422071d46be3ab68164a85c92d6cc3fc86f06b420c9dea5ee4d37920f"},"schema_version":"1.0","source":{"id":"2505.24768","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24768","created_at":"2026-07-05T11:12:56Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24768v1","created_at":"2026-07-05T11:12:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24768","created_at":"2026-07-05T11:12:56Z"},{"alias_kind":"pith_short_12","alias_value":"RLNMVC3E5LQZ","created_at":"2026-07-05T11:12:56Z"},{"alias_kind":"pith_short_16","alias_value":"RLNMVC3E5LQZLLE3","created_at":"2026-07-05T11:12:56Z"},{"alias_kind":"pith_short_8","alias_value":"RLNMVC3E","created_at":"2026-07-05T11:12:56Z"}],"graph_snapshots":[{"event_id":"sha256:12e27f941b859a58721d29e2a55338c2688400f626cd3ef22724d7420d4901d7","target":"graph","created_at":"2026-07-05T11:12:56Z","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/2505.24768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dataset diversity plays a pivotal role for the successful training of many machine learning models, particularly in the supervised fine-tuning (SFT) stage of large language model (LLM) development. Despite increasing recognition of its importance, systematic analyses of dataset diversity still remain underexplored. To address this gap, this work presents a systematic taxonomy of existing diversity-control strategies, which primarily focus on the instruction component, operating at either macroscopic (entire instruction semantics) or mesoscopic levels (instruction units), and furthermore introd","authors_text":"Haoyu Li, Kun Liu, Xuhong Li, Yiming Dong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T16:31:05Z","title":"From Macro to Micro: Probing Dataset Diversity in Language Model Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24768","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:e6b90bc209af2067a1dcfd402f8692985ce416abdbec8e56a62180910f53222f","target":"record","created_at":"2026-07-05T11:12:56Z","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":"800c8c9bc48deaa7f903bf08849e1a63fafcf1c1f487867d2b0b0cc1eb1b2aab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T16:31:05Z","title_canon_sha256":"2983a0f422071d46be3ab68164a85c92d6cc3fc86f06b420c9dea5ee4d37920f"},"schema_version":"1.0","source":{"id":"2505.24768","kind":"arxiv","version":1}},"canonical_sha256":"8adaca8b64eae195ac9b8ff80d5e59de34572333b30fcaebd02a77f34efba89f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8adaca8b64eae195ac9b8ff80d5e59de34572333b30fcaebd02a77f34efba89f","first_computed_at":"2026-07-05T11:12:56.304844Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:56.304844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KrKNUcCFvKg65cI1RmLb/kYNnWSNRQnH/oka/7gtPwWr6g8bN28nmE71ZtIEBHEAdryvLujpVb11FD2EXPenCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:56.305452Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24768","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6b90bc209af2067a1dcfd402f8692985ce416abdbec8e56a62180910f53222f","sha256:12e27f941b859a58721d29e2a55338c2688400f626cd3ef22724d7420d4901d7"],"state_sha256":"4f0cca0b864fea167ef4b186ad493d7acfc6b99b31d99a469841571e2e125f42"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0ghNCTbvNpm2sIEjeKhpUE6gRULjsnjY/bb6Xe+z7RHaKYXIuLvuaWt4ceNENx32cqI5/VDx7NbhecMrX76OCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T12:07:15.685085Z","bundle_sha256":"e0c37e0046b4897d5491ab2d324942b259d97a36d097def36e05c39759b6b6ef"}}