{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MJMJWE3BDKJFXEBYOEJ64NOULD","short_pith_number":"pith:MJMJWE3B","canonical_record":{"source":{"id":"2410.04579","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-06T18:29:46Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"582e0304e76441bc47c5dae3e3b75fe592e1e7dd66140203bb7983e218afc45d","abstract_canon_sha256":"30d91f5465d4dec15f32fc77c5328eb2754467c891ac7c201683dfa9124e18df"},"schema_version":"1.0"},"canonical_sha256":"62589b13611a925b90387113ee35d458d9815c0f298a649ef01153172249cec2","source":{"kind":"arxiv","id":"2410.04579","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04579","created_at":"2026-07-05T10:27:16Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04579v5","created_at":"2026-07-05T10:27:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04579","created_at":"2026-07-05T10:27:16Z"},{"alias_kind":"pith_short_12","alias_value":"MJMJWE3BDKJF","created_at":"2026-07-05T10:27:16Z"},{"alias_kind":"pith_short_16","alias_value":"MJMJWE3BDKJFXEBY","created_at":"2026-07-05T10:27:16Z"},{"alias_kind":"pith_short_8","alias_value":"MJMJWE3B","created_at":"2026-07-05T10:27:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MJMJWE3BDKJFXEBYOEJ64NOULD","target":"record","payload":{"canonical_record":{"source":{"id":"2410.04579","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-06T18:29:46Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"582e0304e76441bc47c5dae3e3b75fe592e1e7dd66140203bb7983e218afc45d","abstract_canon_sha256":"30d91f5465d4dec15f32fc77c5328eb2754467c891ac7c201683dfa9124e18df"},"schema_version":"1.0"},"canonical_sha256":"62589b13611a925b90387113ee35d458d9815c0f298a649ef01153172249cec2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:16.819402Z","signature_b64":"PEdXBRV3cqlMZAfDw3sVZg40/VRHY0qyS5sxMMVmwXVD4g9GY8XqHG4bbSvhE/eK++ToZ9F1p3LsLjCpszq7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62589b13611a925b90387113ee35d458d9815c0f298a649ef01153172249cec2","last_reissued_at":"2026-07-05T10:27:16.818579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:16.818579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.04579","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:27:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hNq4763DNGRqq1Nna3tdUoWng6megx0aCL163pRR/tA8rIGlJISJsFEc64dD0E2oOnbfee83Q0JwSWQsqH6NDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:38:05.672343Z"},"content_sha256":"b59dd1d0beb4e032ba48a087246190d926de29e005d1a7968793650abae461de","schema_version":"1.0","event_id":"sha256:b59dd1d0beb4e032ba48a087246190d926de29e005d1a7968793650abae461de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MJMJWE3BDKJFXEBYOEJ64NOULD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Upsample or Upweight? Balanced Training on Heavily Imbalanced Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Daniel Khashabi, Haoran Xu, Kenton Murray, Tianjian Li, Weiting Tan","submitted_at":"2024-10-06T18:29:46Z","abstract_excerpt":"Data abundance across different domains exhibits a long-tailed distribution: few domains have abundant data, while most face data scarcity. Our work focuses on a multilingual setting, where available data is heavily skewed towards high-resource languages. Two common strategies to address this disparity are upsampling low-resource data (Temperature Sampling) and upweighting low-resource loss (Scalarization). These methods are often assumed to be equivalent, but this equivalence has not been rigorously established, prompting our investigation.\n  Through theoretical and empirical analysis, we ide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04579","kind":"arxiv","version":5},"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/2410.04579/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":"2026-07-05T10:27:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SqgbSk56CFu86k5qYo2XJBEqLDRU9A3xgZtJ5bAPyPV8e4XkOwvRBShFINdzJgyUH1F+iSjuVIz3Y1Tcjb6PCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:38:05.672720Z"},"content_sha256":"b4a7dd49a043007da7b7a518e5fd4688d4ad0f8ec82275b014c4994816689946","schema_version":"1.0","event_id":"sha256:b4a7dd49a043007da7b7a518e5fd4688d4ad0f8ec82275b014c4994816689946"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MJMJWE3BDKJFXEBYOEJ64NOULD/bundle.json","state_url":"https://pith.science/pith/MJMJWE3BDKJFXEBYOEJ64NOULD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MJMJWE3BDKJFXEBYOEJ64NOULD/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":"2026-07-07T14:38:05Z","links":{"resolver":"https://pith.science/pith/MJMJWE3BDKJFXEBYOEJ64NOULD","bundle":"https://pith.science/pith/MJMJWE3BDKJFXEBYOEJ64NOULD/bundle.json","state":"https://pith.science/pith/MJMJWE3BDKJFXEBYOEJ64NOULD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MJMJWE3BDKJFXEBYOEJ64NOULD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MJMJWE3BDKJFXEBYOEJ64NOULD","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":"30d91f5465d4dec15f32fc77c5328eb2754467c891ac7c201683dfa9124e18df","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-06T18:29:46Z","title_canon_sha256":"582e0304e76441bc47c5dae3e3b75fe592e1e7dd66140203bb7983e218afc45d"},"schema_version":"1.0","source":{"id":"2410.04579","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04579","created_at":"2026-07-05T10:27:16Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04579v5","created_at":"2026-07-05T10:27:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04579","created_at":"2026-07-05T10:27:16Z"},{"alias_kind":"pith_short_12","alias_value":"MJMJWE3BDKJF","created_at":"2026-07-05T10:27:16Z"},{"alias_kind":"pith_short_16","alias_value":"MJMJWE3BDKJFXEBY","created_at":"2026-07-05T10:27:16Z"},{"alias_kind":"pith_short_8","alias_value":"MJMJWE3B","created_at":"2026-07-05T10:27:16Z"}],"graph_snapshots":[{"event_id":"sha256:b4a7dd49a043007da7b7a518e5fd4688d4ad0f8ec82275b014c4994816689946","target":"graph","created_at":"2026-07-05T10:27:16Z","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/2410.04579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data abundance across different domains exhibits a long-tailed distribution: few domains have abundant data, while most face data scarcity. Our work focuses on a multilingual setting, where available data is heavily skewed towards high-resource languages. Two common strategies to address this disparity are upsampling low-resource data (Temperature Sampling) and upweighting low-resource loss (Scalarization). These methods are often assumed to be equivalent, but this equivalence has not been rigorously established, prompting our investigation.\n  Through theoretical and empirical analysis, we ide","authors_text":"Daniel Khashabi, Haoran Xu, Kenton Murray, Tianjian Li, Weiting Tan","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-06T18:29:46Z","title":"Upsample or Upweight? Balanced Training on Heavily Imbalanced Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04579","kind":"arxiv","version":5},"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:b59dd1d0beb4e032ba48a087246190d926de29e005d1a7968793650abae461de","target":"record","created_at":"2026-07-05T10:27:16Z","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":"30d91f5465d4dec15f32fc77c5328eb2754467c891ac7c201683dfa9124e18df","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-06T18:29:46Z","title_canon_sha256":"582e0304e76441bc47c5dae3e3b75fe592e1e7dd66140203bb7983e218afc45d"},"schema_version":"1.0","source":{"id":"2410.04579","kind":"arxiv","version":5}},"canonical_sha256":"62589b13611a925b90387113ee35d458d9815c0f298a649ef01153172249cec2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62589b13611a925b90387113ee35d458d9815c0f298a649ef01153172249cec2","first_computed_at":"2026-07-05T10:27:16.818579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:16.818579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PEdXBRV3cqlMZAfDw3sVZg40/VRHY0qyS5sxMMVmwXVD4g9GY8XqHG4bbSvhE/eK++ToZ9F1p3LsLjCpszq7Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:16.819402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04579","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b59dd1d0beb4e032ba48a087246190d926de29e005d1a7968793650abae461de","sha256:b4a7dd49a043007da7b7a518e5fd4688d4ad0f8ec82275b014c4994816689946"],"state_sha256":"c9f96d4bd7142069f44637fb09f54188be3433fff605309d356976067f18950e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qFCT8oTwZYkObN8UJydOBPyfB/+GQCAGqC+WAg9wgz9JoDc67bGLArhGBVxFb6+1pb2sNKjNYbVKktshubf3Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:38:05.674624Z","bundle_sha256":"534a37299f6b8d5e5d26c4b65db4803b41cee464f0c402abda254c5defa82762"}}