{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KDF5MD67ERIUSMADZQP6LXXQTW","short_pith_number":"pith:KDF5MD67","canonical_record":{"source":{"id":"2502.01980","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T03:51:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"31e1d165257ff1b7151ce52ca34c327532c36fa5391d900ee2c37682e4f82b7d","abstract_canon_sha256":"917f3ce7204019ce9ffa45edad2bf0f782de800857aafc972872fcadc4e4d2c8"},"schema_version":"1.0"},"canonical_sha256":"50cbd60fdf2451493003cc1fe5def09d926112b962c406cc5dd4e9c284f52244","source":{"kind":"arxiv","id":"2502.01980","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01980","created_at":"2026-07-05T11:27:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01980v2","created_at":"2026-07-05T11:27:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01980","created_at":"2026-07-05T11:27:52Z"},{"alias_kind":"pith_short_12","alias_value":"KDF5MD67ERIU","created_at":"2026-07-05T11:27:52Z"},{"alias_kind":"pith_short_16","alias_value":"KDF5MD67ERIUSMAD","created_at":"2026-07-05T11:27:52Z"},{"alias_kind":"pith_short_8","alias_value":"KDF5MD67","created_at":"2026-07-05T11:27:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KDF5MD67ERIUSMADZQP6LXXQTW","target":"record","payload":{"canonical_record":{"source":{"id":"2502.01980","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T03:51:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"31e1d165257ff1b7151ce52ca34c327532c36fa5391d900ee2c37682e4f82b7d","abstract_canon_sha256":"917f3ce7204019ce9ffa45edad2bf0f782de800857aafc972872fcadc4e4d2c8"},"schema_version":"1.0"},"canonical_sha256":"50cbd60fdf2451493003cc1fe5def09d926112b962c406cc5dd4e9c284f52244","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:52.529367Z","signature_b64":"aJDCEjlnS2SqeHI/DdwakSe+G5xSajUevDRP7pAbsPcDljs6qAHCG4X+Hh31tyYwIeffZpBLffH5FfEUxVxYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50cbd60fdf2451493003cc1fe5def09d926112b962c406cc5dd4e9c284f52244","last_reissued_at":"2026-07-05T11:27:52.528828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:52.528828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.01980","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":"2026-07-05T11:27:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2aZT/LRkHXzVwLdTkYU2mDVyaHHw7WqT/42CFzHbAaV2BIRfX9fljYdZnnDhzYxoflkz3kdHcOcsAQDZLNFgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:17:47.273654Z"},"content_sha256":"f1ab52a1fabf03e86171d918d733d4fb28d6147a0df3efec3687e1555f2dc7ff","schema_version":"1.0","event_id":"sha256:f1ab52a1fabf03e86171d918d733d4fb28d6147a0df3efec3687e1555f2dc7ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KDF5MD67ERIUSMADZQP6LXXQTW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Data Mining with Longtail-Guided Diffusion","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Carl Vondrick, David S. Hayden, Eric Wolff, Gregory P. Meyer, Mao Ye, Siddhartha S. Srinivasa, Timur Garipov, Yuning Chai, Zhao Chen","submitted_at":"2025-02-04T03:51:00Z","abstract_excerpt":"It is difficult to anticipate the myriad challenges that a predictive model will encounter once deployed. Common practice entails a reactive, cyclical approach: model deployment, data mining, and retraining. We instead develop a proactive longtail discovery process by imagining additional data during training. In particular, we develop general model-based longtail signals, including a differentiable, single forward pass formulation of epistemic uncertainty that does not impact model parameters or predictive performance but can flag rare or hard inputs. We leverage these signals as guidance to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01980","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/2502.01980/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":"2026-07-05T11:27:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YaMWhMTlv69A4FuNOqHKbeB/9mFW0B8G5ml14qGuf+d/JAIVo0oylt2dFt4ELRaeIuMYEr/DlaG3ukz04PStAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:17:47.274614Z"},"content_sha256":"189031d4d24ce6451a15fb3f9591945e659708cda89b222af0acfbf600982eb5","schema_version":"1.0","event_id":"sha256:189031d4d24ce6451a15fb3f9591945e659708cda89b222af0acfbf600982eb5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KDF5MD67ERIUSMADZQP6LXXQTW/bundle.json","state_url":"https://pith.science/pith/KDF5MD67ERIUSMADZQP6LXXQTW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KDF5MD67ERIUSMADZQP6LXXQTW/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":"2026-07-07T07:17:47Z","links":{"resolver":"https://pith.science/pith/KDF5MD67ERIUSMADZQP6LXXQTW","bundle":"https://pith.science/pith/KDF5MD67ERIUSMADZQP6LXXQTW/bundle.json","state":"https://pith.science/pith/KDF5MD67ERIUSMADZQP6LXXQTW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KDF5MD67ERIUSMADZQP6LXXQTW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KDF5MD67ERIUSMADZQP6LXXQTW","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":"917f3ce7204019ce9ffa45edad2bf0f782de800857aafc972872fcadc4e4d2c8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T03:51:00Z","title_canon_sha256":"31e1d165257ff1b7151ce52ca34c327532c36fa5391d900ee2c37682e4f82b7d"},"schema_version":"1.0","source":{"id":"2502.01980","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01980","created_at":"2026-07-05T11:27:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01980v2","created_at":"2026-07-05T11:27:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01980","created_at":"2026-07-05T11:27:52Z"},{"alias_kind":"pith_short_12","alias_value":"KDF5MD67ERIU","created_at":"2026-07-05T11:27:52Z"},{"alias_kind":"pith_short_16","alias_value":"KDF5MD67ERIUSMAD","created_at":"2026-07-05T11:27:52Z"},{"alias_kind":"pith_short_8","alias_value":"KDF5MD67","created_at":"2026-07-05T11:27:52Z"}],"graph_snapshots":[{"event_id":"sha256:189031d4d24ce6451a15fb3f9591945e659708cda89b222af0acfbf600982eb5","target":"graph","created_at":"2026-07-05T11:27:52Z","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/2502.01980/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is difficult to anticipate the myriad challenges that a predictive model will encounter once deployed. Common practice entails a reactive, cyclical approach: model deployment, data mining, and retraining. We instead develop a proactive longtail discovery process by imagining additional data during training. In particular, we develop general model-based longtail signals, including a differentiable, single forward pass formulation of epistemic uncertainty that does not impact model parameters or predictive performance but can flag rare or hard inputs. We leverage these signals as guidance to ","authors_text":"Carl Vondrick, David S. Hayden, Eric Wolff, Gregory P. Meyer, Mao Ye, Siddhartha S. Srinivasa, Timur Garipov, Yuning Chai, Zhao Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T03:51:00Z","title":"Generative Data Mining with Longtail-Guided Diffusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01980","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:f1ab52a1fabf03e86171d918d733d4fb28d6147a0df3efec3687e1555f2dc7ff","target":"record","created_at":"2026-07-05T11:27:52Z","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":"917f3ce7204019ce9ffa45edad2bf0f782de800857aafc972872fcadc4e4d2c8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T03:51:00Z","title_canon_sha256":"31e1d165257ff1b7151ce52ca34c327532c36fa5391d900ee2c37682e4f82b7d"},"schema_version":"1.0","source":{"id":"2502.01980","kind":"arxiv","version":2}},"canonical_sha256":"50cbd60fdf2451493003cc1fe5def09d926112b962c406cc5dd4e9c284f52244","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50cbd60fdf2451493003cc1fe5def09d926112b962c406cc5dd4e9c284f52244","first_computed_at":"2026-07-05T11:27:52.528828Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:52.528828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aJDCEjlnS2SqeHI/DdwakSe+G5xSajUevDRP7pAbsPcDljs6qAHCG4X+Hh31tyYwIeffZpBLffH5FfEUxVxYBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:52.529367Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01980","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1ab52a1fabf03e86171d918d733d4fb28d6147a0df3efec3687e1555f2dc7ff","sha256:189031d4d24ce6451a15fb3f9591945e659708cda89b222af0acfbf600982eb5"],"state_sha256":"f05f03d75b6104c01833988a5b19c823b3215c803104639457989f024579a1b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oJUzt1JpuOUqRaKJZwWYj/XJp6Y+RP6pWe0NAYRzsYdYWOqEqi43gDHlBq2tMzMQangBBIFocG+jV0oXFVFBCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:17:47.278546Z","bundle_sha256":"67884f92b5838b46d94a495ef62234610978657e02192fd1293a706743933fd1"}}