{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:J7HRO5PZJJIOJFQR6N3CSEZSGJ","short_pith_number":"pith:J7HRO5PZ","canonical_record":{"source":{"id":"2505.00903","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T22:47:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"20b743a189eeb4d3a97ad771471b6853f06bd25b01982e86a80bea710749ba05","abstract_canon_sha256":"e33f39fd1e0f6ec2d6c27f3c3461f7edb53d7cb7152b2ee580a2a78591884d3f"},"schema_version":"1.0"},"canonical_sha256":"4fcf1775f94a50e49611f3762913323243e459605919c305dfa9a050d27b2e1f","source":{"kind":"arxiv","id":"2505.00903","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00903","created_at":"2026-07-05T10:57:41Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00903v1","created_at":"2026-07-05T10:57:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00903","created_at":"2026-07-05T10:57:41Z"},{"alias_kind":"pith_short_12","alias_value":"J7HRO5PZJJIO","created_at":"2026-07-05T10:57:41Z"},{"alias_kind":"pith_short_16","alias_value":"J7HRO5PZJJIOJFQR","created_at":"2026-07-05T10:57:41Z"},{"alias_kind":"pith_short_8","alias_value":"J7HRO5PZ","created_at":"2026-07-05T10:57:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:J7HRO5PZJJIOJFQR6N3CSEZSGJ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.00903","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T22:47:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"20b743a189eeb4d3a97ad771471b6853f06bd25b01982e86a80bea710749ba05","abstract_canon_sha256":"e33f39fd1e0f6ec2d6c27f3c3461f7edb53d7cb7152b2ee580a2a78591884d3f"},"schema_version":"1.0"},"canonical_sha256":"4fcf1775f94a50e49611f3762913323243e459605919c305dfa9a050d27b2e1f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:41.482998Z","signature_b64":"YEcwlqVxGRpjn2TvOS8l2foDvfDNl1D1bNceOJlsMFUYMPehGR5DJx4ZW4HhzVODmuCXlwUloCH7pOyVVGiBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fcf1775f94a50e49611f3762913323243e459605919c305dfa9a050d27b2e1f","last_reissued_at":"2026-07-05T10:57:41.482569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:41.482569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.00903","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":"2026-07-05T10:57:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hGrkGPIWQpD8UpYzH7Y120M2oQiyuY758WuzT+l/XRBM2O89XgHHjvMtghUkrLMcrwQx+3jc2HPzyBr8WUdfDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:21:43.833672Z"},"content_sha256":"db41ccd5cb77838f4af66aef14c33646f2fcbfaad8ab11e478ddcabe10a5e1ae","schema_version":"1.0","event_id":"sha256:db41ccd5cb77838f4af66aef14c33646f2fcbfaad8ab11e478ddcabe10a5e1ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:J7HRO5PZJJIOJFQR6N3CSEZSGJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NeMo-Inspector: A Visualization Tool for LLM Generation Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Daria Gitman, Evelina Bakhturina, Igor Gitman","submitted_at":"2025-05-01T22:47:06Z","abstract_excerpt":"Adapting Large Language Models (LLMs) to novel tasks and enhancing their overall capabilities often requires large, high-quality training datasets. Synthetic data, generated at scale, serves a valuable alternative when real-world data is scarce or difficult to obtain. However, ensuring the quality of synthetic datasets is challenging, as developers must manually inspect and refine numerous samples to identify errors and areas for improvement. This process is time-consuming and requires specialized tools. We introduce NeMo-Inspector, an open-source tool designed to simplify the analysis of synt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00903","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/2505.00903/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":"2026-07-05T10:57:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dhs+90gfrfMqEvgYlhzTzmp+wKBid6i/RVSm9YozAvo6tfk3pltcPJ5fS3JvuI8TEZnRNHzcUA5oPKre60RvAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:21:43.834197Z"},"content_sha256":"2ba6af14ca6900ee4e9f292bea30db21b985932ba7bcdf6ce3f1b58ad39e9955","schema_version":"1.0","event_id":"sha256:2ba6af14ca6900ee4e9f292bea30db21b985932ba7bcdf6ce3f1b58ad39e9955"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J7HRO5PZJJIOJFQR6N3CSEZSGJ/bundle.json","state_url":"https://pith.science/pith/J7HRO5PZJJIOJFQR6N3CSEZSGJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J7HRO5PZJJIOJFQR6N3CSEZSGJ/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":"2026-08-17T20:21:43Z","links":{"resolver":"https://pith.science/pith/J7HRO5PZJJIOJFQR6N3CSEZSGJ","bundle":"https://pith.science/pith/J7HRO5PZJJIOJFQR6N3CSEZSGJ/bundle.json","state":"https://pith.science/pith/J7HRO5PZJJIOJFQR6N3CSEZSGJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J7HRO5PZJJIOJFQR6N3CSEZSGJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J7HRO5PZJJIOJFQR6N3CSEZSGJ","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":"e33f39fd1e0f6ec2d6c27f3c3461f7edb53d7cb7152b2ee580a2a78591884d3f","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T22:47:06Z","title_canon_sha256":"20b743a189eeb4d3a97ad771471b6853f06bd25b01982e86a80bea710749ba05"},"schema_version":"1.0","source":{"id":"2505.00903","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00903","created_at":"2026-07-05T10:57:41Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00903v1","created_at":"2026-07-05T10:57:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00903","created_at":"2026-07-05T10:57:41Z"},{"alias_kind":"pith_short_12","alias_value":"J7HRO5PZJJIO","created_at":"2026-07-05T10:57:41Z"},{"alias_kind":"pith_short_16","alias_value":"J7HRO5PZJJIOJFQR","created_at":"2026-07-05T10:57:41Z"},{"alias_kind":"pith_short_8","alias_value":"J7HRO5PZ","created_at":"2026-07-05T10:57:41Z"}],"graph_snapshots":[{"event_id":"sha256:2ba6af14ca6900ee4e9f292bea30db21b985932ba7bcdf6ce3f1b58ad39e9955","target":"graph","created_at":"2026-07-05T10:57:41Z","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/2505.00903/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adapting Large Language Models (LLMs) to novel tasks and enhancing their overall capabilities often requires large, high-quality training datasets. Synthetic data, generated at scale, serves a valuable alternative when real-world data is scarce or difficult to obtain. However, ensuring the quality of synthetic datasets is challenging, as developers must manually inspect and refine numerous samples to identify errors and areas for improvement. This process is time-consuming and requires specialized tools. We introduce NeMo-Inspector, an open-source tool designed to simplify the analysis of synt","authors_text":"Daria Gitman, Evelina Bakhturina, Igor Gitman","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T22:47:06Z","title":"NeMo-Inspector: A Visualization Tool for LLM Generation Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00903","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:db41ccd5cb77838f4af66aef14c33646f2fcbfaad8ab11e478ddcabe10a5e1ae","target":"record","created_at":"2026-07-05T10:57:41Z","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":"e33f39fd1e0f6ec2d6c27f3c3461f7edb53d7cb7152b2ee580a2a78591884d3f","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T22:47:06Z","title_canon_sha256":"20b743a189eeb4d3a97ad771471b6853f06bd25b01982e86a80bea710749ba05"},"schema_version":"1.0","source":{"id":"2505.00903","kind":"arxiv","version":1}},"canonical_sha256":"4fcf1775f94a50e49611f3762913323243e459605919c305dfa9a050d27b2e1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4fcf1775f94a50e49611f3762913323243e459605919c305dfa9a050d27b2e1f","first_computed_at":"2026-07-05T10:57:41.482569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:41.482569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YEcwlqVxGRpjn2TvOS8l2foDvfDNl1D1bNceOJlsMFUYMPehGR5DJx4ZW4HhzVODmuCXlwUloCH7pOyVVGiBAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:41.482998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.00903","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db41ccd5cb77838f4af66aef14c33646f2fcbfaad8ab11e478ddcabe10a5e1ae","sha256:2ba6af14ca6900ee4e9f292bea30db21b985932ba7bcdf6ce3f1b58ad39e9955"],"state_sha256":"36b3dc2b34ec0e6f0a657d64df499bf3fd5faf4d98a1875b25e1eeac4ef1d1fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YPdtFdQWD4CaNxvFRs5uexBDW6wbWeCVtoZtzcgzbiMch9JXtLFtR7skD0OOjIFtmJ0sLBDpTImV6mv/2gC/BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:21:43.837908Z","bundle_sha256":"4d0212711fcea3b05dc4ff252d853a743e041d8ec6e268c5191317b55e7ae159"}}