{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Y7TSQAO3DIXC2VMVDTIBLEZWX6","short_pith_number":"pith:Y7TSQAO3","canonical_record":{"source":{"id":"2607.04563","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T00:31:31Z","cross_cats_sorted":[],"title_canon_sha256":"a5b22c37039ca50636961759cd2e1934ded30eefb06c90d315376465a2758aba","abstract_canon_sha256":"1fb7fef3deab80b7928137d0f222dcbd0bfda49614d8824ade7b1953e78137a7"},"schema_version":"1.0"},"canonical_sha256":"c7e72801db1a2e2d55951cd0159336bf8295ac70a67be506efebe7eee112d3c3","source":{"kind":"arxiv","id":"2607.04563","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04563","created_at":"2026-07-07T02:19:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04563v1","created_at":"2026-07-07T02:19:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04563","created_at":"2026-07-07T02:19:25Z"},{"alias_kind":"pith_short_12","alias_value":"Y7TSQAO3DIXC","created_at":"2026-07-07T02:19:25Z"},{"alias_kind":"pith_short_16","alias_value":"Y7TSQAO3DIXC2VMV","created_at":"2026-07-07T02:19:25Z"},{"alias_kind":"pith_short_8","alias_value":"Y7TSQAO3","created_at":"2026-07-07T02:19:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Y7TSQAO3DIXC2VMVDTIBLEZWX6","target":"record","payload":{"canonical_record":{"source":{"id":"2607.04563","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T00:31:31Z","cross_cats_sorted":[],"title_canon_sha256":"a5b22c37039ca50636961759cd2e1934ded30eefb06c90d315376465a2758aba","abstract_canon_sha256":"1fb7fef3deab80b7928137d0f222dcbd0bfda49614d8824ade7b1953e78137a7"},"schema_version":"1.0"},"canonical_sha256":"c7e72801db1a2e2d55951cd0159336bf8295ac70a67be506efebe7eee112d3c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:25.117027Z","signature_b64":"qEqa0mh6Ug2faDCUxzhjN48locu9cWSHglROIevcwCUfwsXRdYgerxNx5Bpu23mA/9NmbLkNcHYylNj+uPGnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7e72801db1a2e2d55951cd0159336bf8295ac70a67be506efebe7eee112d3c3","last_reissued_at":"2026-07-07T02:19:25.116478Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:25.116478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.04563","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":"2026-07-07T02:19:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ouHSWyM3PtKhXXoRww1cyFlvvDthECzoH1+hc+HFLSI5fkYRAoNaqud5x6be4Hfi/KHcNFpx5LqmT4tL4nBQDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:58:12.789293Z"},"content_sha256":"9f68a25fb7be23c5c308dfabbfdd094fb9c36ca73d77d75184e4419168714b1b","schema_version":"1.0","event_id":"sha256:9f68a25fb7be23c5c308dfabbfdd094fb9c36ca73d77d75184e4419168714b1b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Y7TSQAO3DIXC2VMVDTIBLEZWX6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fidelity-Diversity Metrics for Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amanda Wang, Florentina Bunea, John Thickstun, Tudor Manole","submitted_at":"2026-07-06T00:31:31Z","abstract_excerpt":"As language modeling technology matures, there is an increasing research focus on the composition and curation of datasets used to train these models. For instance, practitioners commonly seek to augment high-quality datasets with additional text to enhance the performance of models trained on that data. However, informed decisions about data augmentation require more nuanced assessments about data quality. We build on work measuring the precision and recall of generative models to develop a pair of metrics that quantify (1) fidelity, capturing how closely candidate text resembles reference da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04563","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/2607.04563/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":"2026-07-07T02:19:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vx/t42htfgJu50EiWRfL7ko3ElvrZbKaTOFV7BBIPwue2MedZbt45egPTTQ3QRm+gHCeNqCNO1jd56j21g9WCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:58:12.789794Z"},"content_sha256":"329e4bcb977a8f9bb37b7bcf1a3b5ed39d0a23e8c4c9c6a5a231703f9dabc60e","schema_version":"1.0","event_id":"sha256:329e4bcb977a8f9bb37b7bcf1a3b5ed39d0a23e8c4c9c6a5a231703f9dabc60e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y7TSQAO3DIXC2VMVDTIBLEZWX6/bundle.json","state_url":"https://pith.science/pith/Y7TSQAO3DIXC2VMVDTIBLEZWX6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y7TSQAO3DIXC2VMVDTIBLEZWX6/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":"2026-08-04T00:58:12Z","links":{"resolver":"https://pith.science/pith/Y7TSQAO3DIXC2VMVDTIBLEZWX6","bundle":"https://pith.science/pith/Y7TSQAO3DIXC2VMVDTIBLEZWX6/bundle.json","state":"https://pith.science/pith/Y7TSQAO3DIXC2VMVDTIBLEZWX6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y7TSQAO3DIXC2VMVDTIBLEZWX6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y7TSQAO3DIXC2VMVDTIBLEZWX6","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":"1fb7fef3deab80b7928137d0f222dcbd0bfda49614d8824ade7b1953e78137a7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T00:31:31Z","title_canon_sha256":"a5b22c37039ca50636961759cd2e1934ded30eefb06c90d315376465a2758aba"},"schema_version":"1.0","source":{"id":"2607.04563","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04563","created_at":"2026-07-07T02:19:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04563v1","created_at":"2026-07-07T02:19:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04563","created_at":"2026-07-07T02:19:25Z"},{"alias_kind":"pith_short_12","alias_value":"Y7TSQAO3DIXC","created_at":"2026-07-07T02:19:25Z"},{"alias_kind":"pith_short_16","alias_value":"Y7TSQAO3DIXC2VMV","created_at":"2026-07-07T02:19:25Z"},{"alias_kind":"pith_short_8","alias_value":"Y7TSQAO3","created_at":"2026-07-07T02:19:25Z"}],"graph_snapshots":[{"event_id":"sha256:329e4bcb977a8f9bb37b7bcf1a3b5ed39d0a23e8c4c9c6a5a231703f9dabc60e","target":"graph","created_at":"2026-07-07T02:19:25Z","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/2607.04563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As language modeling technology matures, there is an increasing research focus on the composition and curation of datasets used to train these models. For instance, practitioners commonly seek to augment high-quality datasets with additional text to enhance the performance of models trained on that data. However, informed decisions about data augmentation require more nuanced assessments about data quality. We build on work measuring the precision and recall of generative models to develop a pair of metrics that quantify (1) fidelity, capturing how closely candidate text resembles reference da","authors_text":"Amanda Wang, Florentina Bunea, John Thickstun, Tudor Manole","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T00:31:31Z","title":"Fidelity-Diversity Metrics for Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04563","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":"sha256:9f68a25fb7be23c5c308dfabbfdd094fb9c36ca73d77d75184e4419168714b1b","target":"record","created_at":"2026-07-07T02:19:25Z","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":"1fb7fef3deab80b7928137d0f222dcbd0bfda49614d8824ade7b1953e78137a7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T00:31:31Z","title_canon_sha256":"a5b22c37039ca50636961759cd2e1934ded30eefb06c90d315376465a2758aba"},"schema_version":"1.0","source":{"id":"2607.04563","kind":"arxiv","version":1}},"canonical_sha256":"c7e72801db1a2e2d55951cd0159336bf8295ac70a67be506efebe7eee112d3c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7e72801db1a2e2d55951cd0159336bf8295ac70a67be506efebe7eee112d3c3","first_computed_at":"2026-07-07T02:19:25.116478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:25.116478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qEqa0mh6Ug2faDCUxzhjN48locu9cWSHglROIevcwCUfwsXRdYgerxNx5Bpu23mA/9NmbLkNcHYylNj+uPGnBA==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:25.117027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04563","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f68a25fb7be23c5c308dfabbfdd094fb9c36ca73d77d75184e4419168714b1b","sha256:329e4bcb977a8f9bb37b7bcf1a3b5ed39d0a23e8c4c9c6a5a231703f9dabc60e"],"state_sha256":"f1d88648d3726e0a82497c2f745d94eaeb8897860772b9320bb2ff7b78d472cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7uszBKuonAlYmDXtRBe7IDL3C2Qs4T5fuQ0rHPBwOk/siF92OgI5qVOXGHplKGnfyVI6PcTGI1psFnopo+MNBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T00:58:12.794822Z","bundle_sha256":"e43a36604025571b72e02269bd869644745e6a39fd2668274d912b4bf5af6adc"}}