{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WZYDCLPABCWULYIUXDCBTNT2HF","short_pith_number":"pith:WZYDCLPA","canonical_record":{"source":{"id":"2506.00741","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T23:03:46Z","cross_cats_sorted":[],"title_canon_sha256":"f3b6314c9b27c53c47edc654ab626d427aaca789766d47d0e8064ae1bf4efaff","abstract_canon_sha256":"e3d0d6422ddd6bbcc245121ac5a4c77b912637dfbc13544c6ccc6eb6523df0cb"},"schema_version":"1.0"},"canonical_sha256":"b670312de008ad45e114b8c419b67a3975cb7cf96a26582959c2753ad81f9ca7","source":{"kind":"arxiv","id":"2506.00741","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00741","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00741v2","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00741","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"pith_short_12","alias_value":"WZYDCLPABCWU","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"pith_short_16","alias_value":"WZYDCLPABCWULYIU","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"pith_short_8","alias_value":"WZYDCLPA","created_at":"2026-07-05T11:16:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WZYDCLPABCWULYIUXDCBTNT2HF","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00741","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T23:03:46Z","cross_cats_sorted":[],"title_canon_sha256":"f3b6314c9b27c53c47edc654ab626d427aaca789766d47d0e8064ae1bf4efaff","abstract_canon_sha256":"e3d0d6422ddd6bbcc245121ac5a4c77b912637dfbc13544c6ccc6eb6523df0cb"},"schema_version":"1.0"},"canonical_sha256":"b670312de008ad45e114b8c419b67a3975cb7cf96a26582959c2753ad81f9ca7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:59.693813Z","signature_b64":"kzvlm1ST0dX3sdBY7z+2PhQxK/OIssiLuAVjGTxU04HL0Xsx1+QM5sH8XRZmVT+y2AjkCNwnhzmKCYzMUEKfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b670312de008ad45e114b8c419b67a3975cb7cf96a26582959c2753ad81f9ca7","last_reissued_at":"2026-07-05T11:16:59.693311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:59.693311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00741","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":"2026-07-05T11:16:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lghgUg729O/rUMJ9YxT/ANSWT/b4nNz5PLZtulzF+D79Ov52nN1iyEB5/1aMhXKIixrCSZPewBvza9Yq24NyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:39:52.831025Z"},"content_sha256":"efd7722dd989ee398e4633fdbd994d122f2a429195d79349dd5986508bbb0d15","schema_version":"1.0","event_id":"sha256:efd7722dd989ee398e4633fdbd994d122f2a429195d79349dd5986508bbb0d15"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WZYDCLPABCWULYIUXDCBTNT2HF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Swarms: Optimizable Generation of Synthetic Evaluation Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shangbin Feng, Weijia Shi, Yike Wang, Yulia Tsvetkov","submitted_at":"2025-05-31T23:03:46Z","abstract_excerpt":"We propose Data Swarms, an algorithm to optimize the generation of synthetic evaluation data and advance quantitative desiderata of LLM evaluation. We first train a swarm of initial data generators using existing data, and define various evaluation objectives to reflect the desired properties of evaluation (e.g., generate more difficult problems for the evaluated models) and quantitatively evaluate data generators. We then employ particle swarm optimization to optimize the swarm of data generators, where they collaboratively search through the model parameter space to find new generators that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00741","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/2506.00741/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":"2026-07-05T11:16:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aPTGXYg3RJHqS6taLqjionDUHZ0japUXhWMi7CWc+I7CHt8/Tc/sCSFojOoanhyWsTK6N1Tl4cq/PqsWLpsiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:39:52.831945Z"},"content_sha256":"21c3f573792fcb9f856ade6b77534721293c3e708dacb4257568897aefe68756","schema_version":"1.0","event_id":"sha256:21c3f573792fcb9f856ade6b77534721293c3e708dacb4257568897aefe68756"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WZYDCLPABCWULYIUXDCBTNT2HF/bundle.json","state_url":"https://pith.science/pith/WZYDCLPABCWULYIUXDCBTNT2HF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WZYDCLPABCWULYIUXDCBTNT2HF/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":"2026-08-08T09:39:52Z","links":{"resolver":"https://pith.science/pith/WZYDCLPABCWULYIUXDCBTNT2HF","bundle":"https://pith.science/pith/WZYDCLPABCWULYIUXDCBTNT2HF/bundle.json","state":"https://pith.science/pith/WZYDCLPABCWULYIUXDCBTNT2HF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WZYDCLPABCWULYIUXDCBTNT2HF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WZYDCLPABCWULYIUXDCBTNT2HF","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":"e3d0d6422ddd6bbcc245121ac5a4c77b912637dfbc13544c6ccc6eb6523df0cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T23:03:46Z","title_canon_sha256":"f3b6314c9b27c53c47edc654ab626d427aaca789766d47d0e8064ae1bf4efaff"},"schema_version":"1.0","source":{"id":"2506.00741","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00741","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00741v2","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00741","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"pith_short_12","alias_value":"WZYDCLPABCWU","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"pith_short_16","alias_value":"WZYDCLPABCWULYIU","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"pith_short_8","alias_value":"WZYDCLPA","created_at":"2026-07-05T11:16:59Z"}],"graph_snapshots":[{"event_id":"sha256:21c3f573792fcb9f856ade6b77534721293c3e708dacb4257568897aefe68756","target":"graph","created_at":"2026-07-05T11:16:59Z","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/2506.00741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Data Swarms, an algorithm to optimize the generation of synthetic evaluation data and advance quantitative desiderata of LLM evaluation. We first train a swarm of initial data generators using existing data, and define various evaluation objectives to reflect the desired properties of evaluation (e.g., generate more difficult problems for the evaluated models) and quantitatively evaluate data generators. We then employ particle swarm optimization to optimize the swarm of data generators, where they collaboratively search through the model parameter space to find new generators that ","authors_text":"Shangbin Feng, Weijia Shi, Yike Wang, Yulia Tsvetkov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T23:03:46Z","title":"Data Swarms: Optimizable Generation of Synthetic Evaluation Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00741","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:efd7722dd989ee398e4633fdbd994d122f2a429195d79349dd5986508bbb0d15","target":"record","created_at":"2026-07-05T11:16:59Z","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":"e3d0d6422ddd6bbcc245121ac5a4c77b912637dfbc13544c6ccc6eb6523df0cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T23:03:46Z","title_canon_sha256":"f3b6314c9b27c53c47edc654ab626d427aaca789766d47d0e8064ae1bf4efaff"},"schema_version":"1.0","source":{"id":"2506.00741","kind":"arxiv","version":2}},"canonical_sha256":"b670312de008ad45e114b8c419b67a3975cb7cf96a26582959c2753ad81f9ca7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b670312de008ad45e114b8c419b67a3975cb7cf96a26582959c2753ad81f9ca7","first_computed_at":"2026-07-05T11:16:59.693311Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:59.693311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kzvlm1ST0dX3sdBY7z+2PhQxK/OIssiLuAVjGTxU04HL0Xsx1+QM5sH8XRZmVT+y2AjkCNwnhzmKCYzMUEKfAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:59.693813Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00741","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efd7722dd989ee398e4633fdbd994d122f2a429195d79349dd5986508bbb0d15","sha256:21c3f573792fcb9f856ade6b77534721293c3e708dacb4257568897aefe68756"],"state_sha256":"7952830e4f604c0552a784e7e9c3e4384e35bcc7b0f9d43b445f0b63bc4f15e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fwDu4+T1bFyH+/HHGlF5yWBnqv3MlBm9t9YCGgR6NJH8YC5dES1sAHzhbZMud/4zMXMOZICp1YSwdOcVrIx9DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:39:52.840182Z","bundle_sha256":"1c49e2f5bec194e5ba93cc24fc6b0aa702e2799c0c9da55fb7800a2fe528c877"}}