{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IEYAMPH3TNP22AKLWB5B5RPKK2","short_pith_number":"pith:IEYAMPH3","canonical_record":{"source":{"id":"2504.20651","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-04-29T11:21:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a898bfd7e66db07691f3ff34b07eec918a71e7221e6d7a1d5a23ec679943b150","abstract_canon_sha256":"67fe48a8653821f4d3ec9b371438a442a29b3c271ff10f485e51945f11b69a4c"},"schema_version":"1.0"},"canonical_sha256":"4130063cfb9b5fad014bb07a1ec5ea5699775e6f5dfe0fc9723d216d62b35490","source":{"kind":"arxiv","id":"2504.20651","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20651","created_at":"2026-07-05T10:55:46Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20651v1","created_at":"2026-07-05T10:55:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20651","created_at":"2026-07-05T10:55:46Z"},{"alias_kind":"pith_short_12","alias_value":"IEYAMPH3TNP2","created_at":"2026-07-05T10:55:46Z"},{"alias_kind":"pith_short_16","alias_value":"IEYAMPH3TNP22AKL","created_at":"2026-07-05T10:55:46Z"},{"alias_kind":"pith_short_8","alias_value":"IEYAMPH3","created_at":"2026-07-05T10:55:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IEYAMPH3TNP22AKLWB5B5RPKK2","target":"record","payload":{"canonical_record":{"source":{"id":"2504.20651","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-04-29T11:21:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a898bfd7e66db07691f3ff34b07eec918a71e7221e6d7a1d5a23ec679943b150","abstract_canon_sha256":"67fe48a8653821f4d3ec9b371438a442a29b3c271ff10f485e51945f11b69a4c"},"schema_version":"1.0"},"canonical_sha256":"4130063cfb9b5fad014bb07a1ec5ea5699775e6f5dfe0fc9723d216d62b35490","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:46.441579Z","signature_b64":"DVPJEhCPnFJVJ8H75hT1vduxp9JWaHWFnC3qDoMsAE9xpJMWiyX2kXcI3yB46fDynqaekhPjB9Kwjiw2jc8sAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4130063cfb9b5fad014bb07a1ec5ea5699775e6f5dfe0fc9723d216d62b35490","last_reissued_at":"2026-07-05T10:55:46.441082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:46.441082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.20651","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":"2026-07-05T10:55:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FUCLkHHzJxJmlSeP5LNVhjVHgkyRrWRAWNLovyClcQuAGJtBXSA3ba6exBvchhh3xVtFsUDUguM2Lg0sCB0YCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:51:38.515948Z"},"content_sha256":"3f934529cff0bc31dc185ae3e7d557db059691c5e016d111deaf9cf4fbf88705","schema_version":"1.0","event_id":"sha256:3f934529cff0bc31dc185ae3e7d557db059691c5e016d111deaf9cf4fbf88705"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IEYAMPH3TNP22AKLWB5B5RPKK2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning and Generalization with Mixture Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Arya Mazumdar, Avishek Ghosh, Harsh Vardhan","submitted_at":"2025-04-29T11:21:15Z","abstract_excerpt":"In many, if not most, machine learning applications the training data is naturally heterogeneous (e.g. federated learning, adversarial attacks and domain adaptation in neural net training). Data heterogeneity is identified as one of the major challenges in modern day large-scale learning. A classical way to represent heterogeneous data is via a mixture model. In this paper, we study generalization performance and statistical rates when data is sampled from a mixture distribution. We first characterize the heterogeneity of the mixture in terms of the pairwise total variation distance of the sub"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20651","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/2504.20651/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":"2026-07-05T10:55:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZC4FluhFZGVpod4T5lXWuBjS5VaGARLyINfxOR5vnu41AsNyEIgmy1pTzxXi1XFPgT/etqPS3bskM0DtP3fSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:51:38.516456Z"},"content_sha256":"0862f9e00aa5d0bf0d52bd6ec7577926bda25436261f20d91ca411f29d8a8e77","schema_version":"1.0","event_id":"sha256:0862f9e00aa5d0bf0d52bd6ec7577926bda25436261f20d91ca411f29d8a8e77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IEYAMPH3TNP22AKLWB5B5RPKK2/bundle.json","state_url":"https://pith.science/pith/IEYAMPH3TNP22AKLWB5B5RPKK2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IEYAMPH3TNP22AKLWB5B5RPKK2/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":"2026-08-22T08:51:38Z","links":{"resolver":"https://pith.science/pith/IEYAMPH3TNP22AKLWB5B5RPKK2","bundle":"https://pith.science/pith/IEYAMPH3TNP22AKLWB5B5RPKK2/bundle.json","state":"https://pith.science/pith/IEYAMPH3TNP22AKLWB5B5RPKK2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IEYAMPH3TNP22AKLWB5B5RPKK2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IEYAMPH3TNP22AKLWB5B5RPKK2","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":"67fe48a8653821f4d3ec9b371438a442a29b3c271ff10f485e51945f11b69a4c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-04-29T11:21:15Z","title_canon_sha256":"a898bfd7e66db07691f3ff34b07eec918a71e7221e6d7a1d5a23ec679943b150"},"schema_version":"1.0","source":{"id":"2504.20651","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20651","created_at":"2026-07-05T10:55:46Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20651v1","created_at":"2026-07-05T10:55:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20651","created_at":"2026-07-05T10:55:46Z"},{"alias_kind":"pith_short_12","alias_value":"IEYAMPH3TNP2","created_at":"2026-07-05T10:55:46Z"},{"alias_kind":"pith_short_16","alias_value":"IEYAMPH3TNP22AKL","created_at":"2026-07-05T10:55:46Z"},{"alias_kind":"pith_short_8","alias_value":"IEYAMPH3","created_at":"2026-07-05T10:55:46Z"}],"graph_snapshots":[{"event_id":"sha256:0862f9e00aa5d0bf0d52bd6ec7577926bda25436261f20d91ca411f29d8a8e77","target":"graph","created_at":"2026-07-05T10:55:46Z","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/2504.20651/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many, if not most, machine learning applications the training data is naturally heterogeneous (e.g. federated learning, adversarial attacks and domain adaptation in neural net training). Data heterogeneity is identified as one of the major challenges in modern day large-scale learning. A classical way to represent heterogeneous data is via a mixture model. In this paper, we study generalization performance and statistical rates when data is sampled from a mixture distribution. We first characterize the heterogeneity of the mixture in terms of the pairwise total variation distance of the sub","authors_text":"Arya Mazumdar, Avishek Ghosh, Harsh Vardhan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-04-29T11:21:15Z","title":"Learning and Generalization with Mixture Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20651","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":"sha256:3f934529cff0bc31dc185ae3e7d557db059691c5e016d111deaf9cf4fbf88705","target":"record","created_at":"2026-07-05T10:55:46Z","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":"67fe48a8653821f4d3ec9b371438a442a29b3c271ff10f485e51945f11b69a4c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-04-29T11:21:15Z","title_canon_sha256":"a898bfd7e66db07691f3ff34b07eec918a71e7221e6d7a1d5a23ec679943b150"},"schema_version":"1.0","source":{"id":"2504.20651","kind":"arxiv","version":1}},"canonical_sha256":"4130063cfb9b5fad014bb07a1ec5ea5699775e6f5dfe0fc9723d216d62b35490","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4130063cfb9b5fad014bb07a1ec5ea5699775e6f5dfe0fc9723d216d62b35490","first_computed_at":"2026-07-05T10:55:46.441082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:46.441082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DVPJEhCPnFJVJ8H75hT1vduxp9JWaHWFnC3qDoMsAE9xpJMWiyX2kXcI3yB46fDynqaekhPjB9Kwjiw2jc8sAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:46.441579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.20651","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f934529cff0bc31dc185ae3e7d557db059691c5e016d111deaf9cf4fbf88705","sha256:0862f9e00aa5d0bf0d52bd6ec7577926bda25436261f20d91ca411f29d8a8e77"],"state_sha256":"6516a80a5d144927db209a3090b00014ac4b0c30f1fd9afcbcf29f9e44e89f7b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GR0cyS6LEVFnX2hWOAEtGRzxOHiSE5MMbOKKDWSBw7nAjDNUCr8+9V89A56FhbrJURb9sEL2deSgC3tw1MtHCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T08:51:38.520795Z","bundle_sha256":"33d4375e18831fba25c2571080862a43940a42d14bcd5db2d436fd85a7307aeb"}}