{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5VXDIQSW3JP7EMVWU6IE7JJS7Y","short_pith_number":"pith:5VXDIQSW","canonical_record":{"source":{"id":"2602.21218","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-31T00:04:08Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"title_canon_sha256":"90ad4d5f9f96bd669cdaa38e59093deef263a6ad887f46bce1c6718595c3a7aa","abstract_canon_sha256":"d95e1b609eb9f4a805d57e00182f0a63a7c7c16d1b1856b1bba0a0aa4191650f"},"schema_version":"1.0"},"canonical_sha256":"ed6e344256da5ff232b6a7904fa532fe179bb2faaa20b3e26737d3d3834816a2","source":{"kind":"arxiv","id":"2602.21218","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.21218","created_at":"2026-06-23T02:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"2602.21218v2","created_at":"2026-06-23T02:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.21218","created_at":"2026-06-23T02:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"5VXDIQSW3JP7","created_at":"2026-06-23T02:13:21Z"},{"alias_kind":"pith_short_16","alias_value":"5VXDIQSW3JP7EMVW","created_at":"2026-06-23T02:13:21Z"},{"alias_kind":"pith_short_8","alias_value":"5VXDIQSW","created_at":"2026-06-23T02:13:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5VXDIQSW3JP7EMVWU6IE7JJS7Y","target":"record","payload":{"canonical_record":{"source":{"id":"2602.21218","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-31T00:04:08Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"title_canon_sha256":"90ad4d5f9f96bd669cdaa38e59093deef263a6ad887f46bce1c6718595c3a7aa","abstract_canon_sha256":"d95e1b609eb9f4a805d57e00182f0a63a7c7c16d1b1856b1bba0a0aa4191650f"},"schema_version":"1.0"},"canonical_sha256":"ed6e344256da5ff232b6a7904fa532fe179bb2faaa20b3e26737d3d3834816a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:21.453956Z","signature_b64":"JdokKCy7qreSMjcfNMLAtzcT/qt6YZAq5XFKf+w+KHTXZl4AUg03fMNb/yIMDfSIAJuu01NSWyPdsFy4Buk7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed6e344256da5ff232b6a7904fa532fe179bb2faaa20b3e26737d3d3834816a2","last_reissued_at":"2026-06-23T02:13:21.453515Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:21.453515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.21218","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":"2026-06-23T02:13:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QbSmofVetEhjsf7iFSK+fNNnk7eWR9Adm3YqTprQi18DVaDmIzqSFLI+x30cWEYZ1I1y1beQQTpfptfD5rxRDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T05:43:54.084794Z"},"content_sha256":"5a3f0f2dca6e021aa785372f0c6f8d37badf8495d29c10fd76c00721b982c47c","schema_version":"1.0","event_id":"sha256:5a3f0f2dca6e021aa785372f0c6f8d37badf8495d29c10fd76c00721b982c47c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5VXDIQSW3JP7EMVWU6IE7JJS7Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alfy Samuel, Amin Banayeeanzade, Anoop Kumar, Deqing Fu, Erin Babinsky, Qingchuan Yang, Robin Jia, Sai Praneeth Karimireddy, Spencer Hong","submitted_at":"2026-01-31T00:04:08Z","abstract_excerpt":"High-quality data is essential for modern machine learning, yet many valuable corpora are sensitive and cannot be freely shared. Synthetic data offers a practical substitute for downstream development, and large language models (LLMs) have emerged as powerful engines for generating it. However, existing private text generation methods are severely inefficient: they are data-intensive, computationally slow, and often require large private corpora or batch sizes to achieve usable quality. We introduce EPSVec, a differentially-private lightweight alternative that steers LLM generation using *data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.21218","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/2602.21218/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":"2026-06-23T02:13:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eSWVEEq6p+8JoKr7I+ySrMuw9qVpxggHWKmfZDRospBCx5Oxg1FQ9tBzrKSHwXt5nbNiXNfOxgN91AqdzfauBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T05:43:54.085187Z"},"content_sha256":"e02438d65f8d4927573a32b718797e89ba9ef472bbb6b3c660332a1b84436a58","schema_version":"1.0","event_id":"sha256:e02438d65f8d4927573a32b718797e89ba9ef472bbb6b3c660332a1b84436a58"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5VXDIQSW3JP7EMVWU6IE7JJS7Y/bundle.json","state_url":"https://pith.science/pith/5VXDIQSW3JP7EMVWU6IE7JJS7Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5VXDIQSW3JP7EMVWU6IE7JJS7Y/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":"2026-06-28T05:43:54Z","links":{"resolver":"https://pith.science/pith/5VXDIQSW3JP7EMVWU6IE7JJS7Y","bundle":"https://pith.science/pith/5VXDIQSW3JP7EMVWU6IE7JJS7Y/bundle.json","state":"https://pith.science/pith/5VXDIQSW3JP7EMVWU6IE7JJS7Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5VXDIQSW3JP7EMVWU6IE7JJS7Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5VXDIQSW3JP7EMVWU6IE7JJS7Y","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":"d95e1b609eb9f4a805d57e00182f0a63a7c7c16d1b1856b1bba0a0aa4191650f","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-31T00:04:08Z","title_canon_sha256":"90ad4d5f9f96bd669cdaa38e59093deef263a6ad887f46bce1c6718595c3a7aa"},"schema_version":"1.0","source":{"id":"2602.21218","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.21218","created_at":"2026-06-23T02:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"2602.21218v2","created_at":"2026-06-23T02:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.21218","created_at":"2026-06-23T02:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"5VXDIQSW3JP7","created_at":"2026-06-23T02:13:21Z"},{"alias_kind":"pith_short_16","alias_value":"5VXDIQSW3JP7EMVW","created_at":"2026-06-23T02:13:21Z"},{"alias_kind":"pith_short_8","alias_value":"5VXDIQSW","created_at":"2026-06-23T02:13:21Z"}],"graph_snapshots":[{"event_id":"sha256:e02438d65f8d4927573a32b718797e89ba9ef472bbb6b3c660332a1b84436a58","target":"graph","created_at":"2026-06-23T02:13:21Z","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/2602.21218/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality data is essential for modern machine learning, yet many valuable corpora are sensitive and cannot be freely shared. Synthetic data offers a practical substitute for downstream development, and large language models (LLMs) have emerged as powerful engines for generating it. However, existing private text generation methods are severely inefficient: they are data-intensive, computationally slow, and often require large private corpora or batch sizes to achieve usable quality. We introduce EPSVec, a differentially-private lightweight alternative that steers LLM generation using *data","authors_text":"Alfy Samuel, Amin Banayeeanzade, Anoop Kumar, Deqing Fu, Erin Babinsky, Qingchuan Yang, Robin Jia, Sai Praneeth Karimireddy, Spencer Hong","cross_cats":["cs.AI","cs.CR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-31T00:04:08Z","title":"EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.21218","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":"sha256:5a3f0f2dca6e021aa785372f0c6f8d37badf8495d29c10fd76c00721b982c47c","target":"record","created_at":"2026-06-23T02:13:21Z","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":"d95e1b609eb9f4a805d57e00182f0a63a7c7c16d1b1856b1bba0a0aa4191650f","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-31T00:04:08Z","title_canon_sha256":"90ad4d5f9f96bd669cdaa38e59093deef263a6ad887f46bce1c6718595c3a7aa"},"schema_version":"1.0","source":{"id":"2602.21218","kind":"arxiv","version":2}},"canonical_sha256":"ed6e344256da5ff232b6a7904fa532fe179bb2faaa20b3e26737d3d3834816a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed6e344256da5ff232b6a7904fa532fe179bb2faaa20b3e26737d3d3834816a2","first_computed_at":"2026-06-23T02:13:21.453515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:21.453515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JdokKCy7qreSMjcfNMLAtzcT/qt6YZAq5XFKf+w+KHTXZl4AUg03fMNb/yIMDfSIAJuu01NSWyPdsFy4Buk7Cw==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:21.453956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.21218","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a3f0f2dca6e021aa785372f0c6f8d37badf8495d29c10fd76c00721b982c47c","sha256:e02438d65f8d4927573a32b718797e89ba9ef472bbb6b3c660332a1b84436a58"],"state_sha256":"bb6f1adc3dba5b9feb75c8c0e666362066ea03fd5994d9606c5388834bb3fe53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pZlhX1k8BPqf2P+LBtmFDCZBcnLawlrbdEIYXW/ks0C3sU8jY3nK6D1SJXOLj3v+RQ6ea+r/o+qqM1z3tSjkBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T05:43:54.087494Z","bundle_sha256":"7ba7a02cd443700f14ff7fbf50168bdb8112fd6211cd1e8fe241714f60263808"}}