{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XJH7MLGBHE33QA7KZT7YDAJ7BZ","short_pith_number":"pith:XJH7MLGB","canonical_record":{"source":{"id":"2103.02062","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-02T22:23:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"499f1ce6289d88a9870ea5dabd66bf428126fb68e0c51cac13a5ce84f1ed63d9","abstract_canon_sha256":"d6ef4b60197cd057e2832a031c3c7bb1eed6b2d24540c8323cbaa41d36509a57"},"schema_version":"1.0"},"canonical_sha256":"ba4ff62cc13937b803eaccff81813f0e44b94da32a8fb8cd7ad753c656b9fc20","source":{"kind":"arxiv","id":"2103.02062","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.02062","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"arxiv_version","alias_value":"2103.02062v2","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.02062","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"pith_short_12","alias_value":"XJH7MLGBHE33","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"pith_short_16","alias_value":"XJH7MLGBHE33QA7K","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"pith_short_8","alias_value":"XJH7MLGB","created_at":"2026-07-05T02:48:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XJH7MLGBHE33QA7KZT7YDAJ7BZ","target":"record","payload":{"canonical_record":{"source":{"id":"2103.02062","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-02T22:23:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"499f1ce6289d88a9870ea5dabd66bf428126fb68e0c51cac13a5ce84f1ed63d9","abstract_canon_sha256":"d6ef4b60197cd057e2832a031c3c7bb1eed6b2d24540c8323cbaa41d36509a57"},"schema_version":"1.0"},"canonical_sha256":"ba4ff62cc13937b803eaccff81813f0e44b94da32a8fb8cd7ad753c656b9fc20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:21.764919Z","signature_b64":"eYqlB8B02+Z7rjH6SHJbrmyMxdYhEI2mdmm6B/0jJeeAszbUN77TrJ3IozFNoqFXH7kbJSpsqWJlxHCbksZ9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba4ff62cc13937b803eaccff81813f0e44b94da32a8fb8cd7ad753c656b9fc20","last_reissued_at":"2026-07-05T02:48:21.764494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:21.764494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.02062","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":"2026-07-05T02:48:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UZ6kU9wp28YVgmgWHgL8dlC3QzJu91crlDkbSpS8AOIJVFbb4ERyzdfVDaZtCGtv+agAGOySVJSP6M7ZIII4DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T08:53:53.354674Z"},"content_sha256":"4019b2a973b054c620364021f5b93f18281083cc1d0472efc8eab1343b0986f1","schema_version":"1.0","event_id":"sha256:4019b2a973b054c620364021f5b93f18281083cc1d0472efc8eab1343b0986f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XJH7MLGBHE33QA7KZT7YDAJ7BZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variance Reduced Training with Stratified Sampling for Forecasting Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher De Sa, Dean Foster, Lifan Chen, Youngsuk Park, Yucheng Lu, Yuyang Wang","submitted_at":"2021-03-02T22:23:27Z","abstract_excerpt":"In large-scale time series forecasting, one often encounters the situation where the temporal patterns of time series, while drifting over time, differ from one another in the same dataset. In this paper, we provably show under such heterogeneity, training a forecasting model with commonly used stochastic optimizers (e.g. SGD) potentially suffers large variance on gradient estimation, and thus incurs long-time training. We show that this issue can be efficiently alleviated via stratification, which allows the optimizer to sample from pre-grouped time series strata. For better trading-off gradi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.02062","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/2103.02062/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":"2026-07-05T02:48:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O2xM08r2xYOuEM+fHI3C4yS2xuJRYN1wdvbYuDJ7h0RUht2Gwd7wqDuj94yI5HEk1T4K6tlA3JQCDvh/3flVCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T08:53:53.356081Z"},"content_sha256":"9d8ec5d121771660526bcc76d094f4410da99c95ac23241288285a5e976c9b42","schema_version":"1.0","event_id":"sha256:9d8ec5d121771660526bcc76d094f4410da99c95ac23241288285a5e976c9b42"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XJH7MLGBHE33QA7KZT7YDAJ7BZ/bundle.json","state_url":"https://pith.science/pith/XJH7MLGBHE33QA7KZT7YDAJ7BZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XJH7MLGBHE33QA7KZT7YDAJ7BZ/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":"2026-08-17T08:53:53Z","links":{"resolver":"https://pith.science/pith/XJH7MLGBHE33QA7KZT7YDAJ7BZ","bundle":"https://pith.science/pith/XJH7MLGBHE33QA7KZT7YDAJ7BZ/bundle.json","state":"https://pith.science/pith/XJH7MLGBHE33QA7KZT7YDAJ7BZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XJH7MLGBHE33QA7KZT7YDAJ7BZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XJH7MLGBHE33QA7KZT7YDAJ7BZ","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":"d6ef4b60197cd057e2832a031c3c7bb1eed6b2d24540c8323cbaa41d36509a57","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-02T22:23:27Z","title_canon_sha256":"499f1ce6289d88a9870ea5dabd66bf428126fb68e0c51cac13a5ce84f1ed63d9"},"schema_version":"1.0","source":{"id":"2103.02062","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.02062","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"arxiv_version","alias_value":"2103.02062v2","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.02062","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"pith_short_12","alias_value":"XJH7MLGBHE33","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"pith_short_16","alias_value":"XJH7MLGBHE33QA7K","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"pith_short_8","alias_value":"XJH7MLGB","created_at":"2026-07-05T02:48:21Z"}],"graph_snapshots":[{"event_id":"sha256:9d8ec5d121771660526bcc76d094f4410da99c95ac23241288285a5e976c9b42","target":"graph","created_at":"2026-07-05T02:48:21Z","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/2103.02062/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In large-scale time series forecasting, one often encounters the situation where the temporal patterns of time series, while drifting over time, differ from one another in the same dataset. In this paper, we provably show under such heterogeneity, training a forecasting model with commonly used stochastic optimizers (e.g. SGD) potentially suffers large variance on gradient estimation, and thus incurs long-time training. We show that this issue can be efficiently alleviated via stratification, which allows the optimizer to sample from pre-grouped time series strata. For better trading-off gradi","authors_text":"Christopher De Sa, Dean Foster, Lifan Chen, Youngsuk Park, Yucheng Lu, Yuyang Wang","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-02T22:23:27Z","title":"Variance Reduced Training with Stratified Sampling for Forecasting Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.02062","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":"sha256:4019b2a973b054c620364021f5b93f18281083cc1d0472efc8eab1343b0986f1","target":"record","created_at":"2026-07-05T02:48:21Z","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":"d6ef4b60197cd057e2832a031c3c7bb1eed6b2d24540c8323cbaa41d36509a57","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-02T22:23:27Z","title_canon_sha256":"499f1ce6289d88a9870ea5dabd66bf428126fb68e0c51cac13a5ce84f1ed63d9"},"schema_version":"1.0","source":{"id":"2103.02062","kind":"arxiv","version":2}},"canonical_sha256":"ba4ff62cc13937b803eaccff81813f0e44b94da32a8fb8cd7ad753c656b9fc20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba4ff62cc13937b803eaccff81813f0e44b94da32a8fb8cd7ad753c656b9fc20","first_computed_at":"2026-07-05T02:48:21.764494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:21.764494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eYqlB8B02+Z7rjH6SHJbrmyMxdYhEI2mdmm6B/0jJeeAszbUN77TrJ3IozFNoqFXH7kbJSpsqWJlxHCbksZ9CA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:21.764919Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.02062","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4019b2a973b054c620364021f5b93f18281083cc1d0472efc8eab1343b0986f1","sha256:9d8ec5d121771660526bcc76d094f4410da99c95ac23241288285a5e976c9b42"],"state_sha256":"62fed9f4bc1832636031970248aa2da62fb49137533c55b209503b6dc4a365f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lsKYXlNE1XMraMSeNVEzks021rEYJqq0n3FTlxwKnK/eMGu6aFoq7ZFSxpTZEEhF6U/HqxXfifphNXHC3Q/FBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T08:53:53.375968Z","bundle_sha256":"fd9f9e07a8b2cb159e8badeb8288cc880a12a640cc2156ca4bcd012e68380278"}}