{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VFSHKEUCXM73QYW5K54MUIOKGY","short_pith_number":"pith:VFSHKEUC","canonical_record":{"source":{"id":"2101.07561","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-01-19T11:08:40Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"58470f47f1fe3d3ae4c8cd47ef8733c604ca016f5a3bbe01b8189bd966ae7d33","abstract_canon_sha256":"23adaa23128639264d1cf3f506f23aa690ed1fa9a05fcb5a0dcc553953c7cabc"},"schema_version":"1.0"},"canonical_sha256":"a964751282bb3fb862dd5778ca21ca362332cf754407d32a0a4a1a7ae7495a51","source":{"kind":"arxiv","id":"2101.07561","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.07561","created_at":"2026-07-05T05:01:14Z"},{"alias_kind":"arxiv_version","alias_value":"2101.07561v3","created_at":"2026-07-05T05:01:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.07561","created_at":"2026-07-05T05:01:14Z"},{"alias_kind":"pith_short_12","alias_value":"VFSHKEUCXM73","created_at":"2026-07-05T05:01:14Z"},{"alias_kind":"pith_short_16","alias_value":"VFSHKEUCXM73QYW5","created_at":"2026-07-05T05:01:14Z"},{"alias_kind":"pith_short_8","alias_value":"VFSHKEUC","created_at":"2026-07-05T05:01:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VFSHKEUCXM73QYW5K54MUIOKGY","target":"record","payload":{"canonical_record":{"source":{"id":"2101.07561","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-01-19T11:08:40Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"58470f47f1fe3d3ae4c8cd47ef8733c604ca016f5a3bbe01b8189bd966ae7d33","abstract_canon_sha256":"23adaa23128639264d1cf3f506f23aa690ed1fa9a05fcb5a0dcc553953c7cabc"},"schema_version":"1.0"},"canonical_sha256":"a964751282bb3fb862dd5778ca21ca362332cf754407d32a0a4a1a7ae7495a51","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:01:14.812864Z","signature_b64":"uUN0u2Ex8nBWP7qKv74B7+F2venQGs5um2yCw2ILBVIFUxhuL0hgVUu0CJyXOvbEPw5v5DCxq4FL80xnAZkzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a964751282bb3fb862dd5778ca21ca362332cf754407d32a0a4a1a7ae7495a51","last_reissued_at":"2026-07-05T05:01:14.812479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:01:14.812479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.07561","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:01:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4PhrBPPkuT1xyFo4ZsRww15NLjJBm6kJ5Ox0NG6ZtQMzuUTYKMJyGM2Kx8N/oW60XFjBtcO1/1FNyNDo3kkdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T17:29:51.786590Z"},"content_sha256":"ca20d32133394beb0ad792c77f62c586cd583b018be50ea106c26f036c77152e","schema_version":"1.0","event_id":"sha256:ca20d32133394beb0ad792c77f62c586cd583b018be50ea106c26f036c77152e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VFSHKEUCXM73QYW5K54MUIOKGY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Local Variation in Data: Sampling and Weighting Schemes for Supervised Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"David Lugato, Ga\\\"el Po\\\"ette, Paul Novello, Pietro Congedo","submitted_at":"2021-01-19T11:08:40Z","abstract_excerpt":"In the context of supervised learning of a function by a neural network, we claim and empirically verify that the neural network yields better results when the distribution of the data set focuses on regions where the function to learn is steep. We first traduce this assumption in a mathematically workable way using Taylor expansion and emphasize a new training distribution based on the derivatives of the function to learn. Then, theoretical derivations allow constructing a methodology that we call Variance Based Samples Weighting (VBSW). VBSW uses labels local variance to weight the training "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.07561","kind":"arxiv","version":3},"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/2101.07561/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":"2026-07-05T05:01:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u4U2PQf5cRWqETHbqkXQLoY14prwctMVVH2JAQ5t6yi/I8HKoZX98RhveWSZ5r1O1e5nVgeTXigS7RPaRK2ICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T17:29:51.786981Z"},"content_sha256":"57d128a870601b244b3a64e963776cdda0732e68fbc193d7ba0c2f3d3b6ef09f","schema_version":"1.0","event_id":"sha256:57d128a870601b244b3a64e963776cdda0732e68fbc193d7ba0c2f3d3b6ef09f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VFSHKEUCXM73QYW5K54MUIOKGY/bundle.json","state_url":"https://pith.science/pith/VFSHKEUCXM73QYW5K54MUIOKGY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VFSHKEUCXM73QYW5K54MUIOKGY/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":"2026-07-18T17:29:51Z","links":{"resolver":"https://pith.science/pith/VFSHKEUCXM73QYW5K54MUIOKGY","bundle":"https://pith.science/pith/VFSHKEUCXM73QYW5K54MUIOKGY/bundle.json","state":"https://pith.science/pith/VFSHKEUCXM73QYW5K54MUIOKGY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VFSHKEUCXM73QYW5K54MUIOKGY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VFSHKEUCXM73QYW5K54MUIOKGY","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":"23adaa23128639264d1cf3f506f23aa690ed1fa9a05fcb5a0dcc553953c7cabc","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-01-19T11:08:40Z","title_canon_sha256":"58470f47f1fe3d3ae4c8cd47ef8733c604ca016f5a3bbe01b8189bd966ae7d33"},"schema_version":"1.0","source":{"id":"2101.07561","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.07561","created_at":"2026-07-05T05:01:14Z"},{"alias_kind":"arxiv_version","alias_value":"2101.07561v3","created_at":"2026-07-05T05:01:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.07561","created_at":"2026-07-05T05:01:14Z"},{"alias_kind":"pith_short_12","alias_value":"VFSHKEUCXM73","created_at":"2026-07-05T05:01:14Z"},{"alias_kind":"pith_short_16","alias_value":"VFSHKEUCXM73QYW5","created_at":"2026-07-05T05:01:14Z"},{"alias_kind":"pith_short_8","alias_value":"VFSHKEUC","created_at":"2026-07-05T05:01:14Z"}],"graph_snapshots":[{"event_id":"sha256:57d128a870601b244b3a64e963776cdda0732e68fbc193d7ba0c2f3d3b6ef09f","target":"graph","created_at":"2026-07-05T05:01:14Z","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/2101.07561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the context of supervised learning of a function by a neural network, we claim and empirically verify that the neural network yields better results when the distribution of the data set focuses on regions where the function to learn is steep. We first traduce this assumption in a mathematically workable way using Taylor expansion and emphasize a new training distribution based on the derivatives of the function to learn. Then, theoretical derivations allow constructing a methodology that we call Variance Based Samples Weighting (VBSW). VBSW uses labels local variance to weight the training ","authors_text":"David Lugato, Ga\\\"el Po\\\"ette, Paul Novello, Pietro Congedo","cross_cats":["cs.LG","math.ST","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-01-19T11:08:40Z","title":"Leveraging Local Variation in Data: Sampling and Weighting Schemes for Supervised Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.07561","kind":"arxiv","version":3},"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:ca20d32133394beb0ad792c77f62c586cd583b018be50ea106c26f036c77152e","target":"record","created_at":"2026-07-05T05:01:14Z","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":"23adaa23128639264d1cf3f506f23aa690ed1fa9a05fcb5a0dcc553953c7cabc","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-01-19T11:08:40Z","title_canon_sha256":"58470f47f1fe3d3ae4c8cd47ef8733c604ca016f5a3bbe01b8189bd966ae7d33"},"schema_version":"1.0","source":{"id":"2101.07561","kind":"arxiv","version":3}},"canonical_sha256":"a964751282bb3fb862dd5778ca21ca362332cf754407d32a0a4a1a7ae7495a51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a964751282bb3fb862dd5778ca21ca362332cf754407d32a0a4a1a7ae7495a51","first_computed_at":"2026-07-05T05:01:14.812479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:01:14.812479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uUN0u2Ex8nBWP7qKv74B7+F2venQGs5um2yCw2ILBVIFUxhuL0hgVUu0CJyXOvbEPw5v5DCxq4FL80xnAZkzBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:01:14.812864Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.07561","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca20d32133394beb0ad792c77f62c586cd583b018be50ea106c26f036c77152e","sha256:57d128a870601b244b3a64e963776cdda0732e68fbc193d7ba0c2f3d3b6ef09f"],"state_sha256":"e0237948ee6dbee53e438fc222db84267c0fcdc26419f94d84a1aa6717494c03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QFBIyftnat6k7DTU9Yq7yflCLyNulUEJuxM3WVj+vxrnmjdmQL39dG1F5loQCSZBMCrHBdjFcMc7o3/FoqH8Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T17:29:51.789226Z","bundle_sha256":"e80d8c9bd0a8cad587230f94d7ec88cf4f45e1158c5015eecaa1a8bed6d17251"}}