{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ERQEPOA43UF36HFPG6J4DLEV67","short_pith_number":"pith:ERQEPOA4","canonical_record":{"source":{"id":"2103.11795","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-13T06:19:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ec88cc780366541610111b7115056f9fbcb93f5110af8e9c7ee7b498897ba4b4","abstract_canon_sha256":"4db3374832dd23ca4d3da25db27db849af6d769ebc7e43f3c450aa2f0c75efaa"},"schema_version":"1.0"},"canonical_sha256":"246047b81cdd0bbf1caf3793c1ac95f7e3ff0f63aa04460baaff5089ade290f1","source":{"kind":"arxiv","id":"2103.11795","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.11795","created_at":"2026-07-05T02:25:12Z"},{"alias_kind":"arxiv_version","alias_value":"2103.11795v1","created_at":"2026-07-05T02:25:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11795","created_at":"2026-07-05T02:25:12Z"},{"alias_kind":"pith_short_12","alias_value":"ERQEPOA43UF3","created_at":"2026-07-05T02:25:12Z"},{"alias_kind":"pith_short_16","alias_value":"ERQEPOA43UF36HFP","created_at":"2026-07-05T02:25:12Z"},{"alias_kind":"pith_short_8","alias_value":"ERQEPOA4","created_at":"2026-07-05T02:25:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ERQEPOA43UF36HFPG6J4DLEV67","target":"record","payload":{"canonical_record":{"source":{"id":"2103.11795","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-13T06:19:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ec88cc780366541610111b7115056f9fbcb93f5110af8e9c7ee7b498897ba4b4","abstract_canon_sha256":"4db3374832dd23ca4d3da25db27db849af6d769ebc7e43f3c450aa2f0c75efaa"},"schema_version":"1.0"},"canonical_sha256":"246047b81cdd0bbf1caf3793c1ac95f7e3ff0f63aa04460baaff5089ade290f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:25:12.337049Z","signature_b64":"loNGeLvbMfYVEYBnJuAilhOAN+18tTJNRjYd/mGmYGHe7SxFqSLV7ivEl6JyANH2snsdLNZmXAPIQ44gVZ/uBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"246047b81cdd0bbf1caf3793c1ac95f7e3ff0f63aa04460baaff5089ade290f1","last_reissued_at":"2026-07-05T02:25:12.336656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:25:12.336656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.11795","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":"2026-07-05T02:25:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/PEZ+Rebs2qz9xXnfrY4xXtyFCVIxk5huDO1i4eKfSyNkXqpTirSSauAbIa2WiQOIYBLAWb9ocucFKDv9iDkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:10:46.948736Z"},"content_sha256":"4a4a384413b41911a8beef28ce76a7bc8969bc42be29b01cb4ddec4a02ff11f2","schema_version":"1.0","event_id":"sha256:4a4a384413b41911a8beef28ce76a7bc8969bc42be29b01cb4ddec4a02ff11f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ERQEPOA43UF36HFPG6J4DLEV67","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Simpson's Bias in NLP Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fei Yuan, Huang Bojun, Longtu Zhang, Yaobo Liang","submitted_at":"2021-03-13T06:19:37Z","abstract_excerpt":"In most machine learning tasks, we evaluate a model $M$ on a given data population $S$ by measuring a population-level metric $F(S;M)$. Examples of such evaluation metric $F$ include precision/recall for (binary) recognition, the F1 score for multi-class classification, and the BLEU metric for language generation. On the other hand, the model $M$ is trained by optimizing a sample-level loss $G(S_t;M)$ at each learning step $t$, where $S_t$ is a subset of $S$ (a.k.a. the mini-batch). Popular choices of $G$ include cross-entropy loss, the Dice loss, and sentence-level BLEU scores. A fundamental "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11795","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/2103.11795/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":"2026-07-05T02:25:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bh/rTLVjDLgzCkM3iziN52cOj+D4M9ZzuKcd//CZJxzIo3yhBeulstkKQULrUZWXLxFyNK3RPXIvKm/EWlfjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:10:46.949242Z"},"content_sha256":"fc084451c668e9f6e22f44aa445391c21c7f50043cb7bb223033f762e9701579","schema_version":"1.0","event_id":"sha256:fc084451c668e9f6e22f44aa445391c21c7f50043cb7bb223033f762e9701579"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ERQEPOA43UF36HFPG6J4DLEV67/bundle.json","state_url":"https://pith.science/pith/ERQEPOA43UF36HFPG6J4DLEV67/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ERQEPOA43UF36HFPG6J4DLEV67/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":"2026-08-06T19:10:46Z","links":{"resolver":"https://pith.science/pith/ERQEPOA43UF36HFPG6J4DLEV67","bundle":"https://pith.science/pith/ERQEPOA43UF36HFPG6J4DLEV67/bundle.json","state":"https://pith.science/pith/ERQEPOA43UF36HFPG6J4DLEV67/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ERQEPOA43UF36HFPG6J4DLEV67/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ERQEPOA43UF36HFPG6J4DLEV67","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":"4db3374832dd23ca4d3da25db27db849af6d769ebc7e43f3c450aa2f0c75efaa","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-13T06:19:37Z","title_canon_sha256":"ec88cc780366541610111b7115056f9fbcb93f5110af8e9c7ee7b498897ba4b4"},"schema_version":"1.0","source":{"id":"2103.11795","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.11795","created_at":"2026-07-05T02:25:12Z"},{"alias_kind":"arxiv_version","alias_value":"2103.11795v1","created_at":"2026-07-05T02:25:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11795","created_at":"2026-07-05T02:25:12Z"},{"alias_kind":"pith_short_12","alias_value":"ERQEPOA43UF3","created_at":"2026-07-05T02:25:12Z"},{"alias_kind":"pith_short_16","alias_value":"ERQEPOA43UF36HFP","created_at":"2026-07-05T02:25:12Z"},{"alias_kind":"pith_short_8","alias_value":"ERQEPOA4","created_at":"2026-07-05T02:25:12Z"}],"graph_snapshots":[{"event_id":"sha256:fc084451c668e9f6e22f44aa445391c21c7f50043cb7bb223033f762e9701579","target":"graph","created_at":"2026-07-05T02:25:12Z","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/2103.11795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In most machine learning tasks, we evaluate a model $M$ on a given data population $S$ by measuring a population-level metric $F(S;M)$. Examples of such evaluation metric $F$ include precision/recall for (binary) recognition, the F1 score for multi-class classification, and the BLEU metric for language generation. On the other hand, the model $M$ is trained by optimizing a sample-level loss $G(S_t;M)$ at each learning step $t$, where $S_t$ is a subset of $S$ (a.k.a. the mini-batch). Popular choices of $G$ include cross-entropy loss, the Dice loss, and sentence-level BLEU scores. A fundamental ","authors_text":"Fei Yuan, Huang Bojun, Longtu Zhang, Yaobo Liang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-13T06:19:37Z","title":"Simpson's Bias in NLP Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11795","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":"sha256:4a4a384413b41911a8beef28ce76a7bc8969bc42be29b01cb4ddec4a02ff11f2","target":"record","created_at":"2026-07-05T02:25:12Z","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":"4db3374832dd23ca4d3da25db27db849af6d769ebc7e43f3c450aa2f0c75efaa","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-13T06:19:37Z","title_canon_sha256":"ec88cc780366541610111b7115056f9fbcb93f5110af8e9c7ee7b498897ba4b4"},"schema_version":"1.0","source":{"id":"2103.11795","kind":"arxiv","version":1}},"canonical_sha256":"246047b81cdd0bbf1caf3793c1ac95f7e3ff0f63aa04460baaff5089ade290f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"246047b81cdd0bbf1caf3793c1ac95f7e3ff0f63aa04460baaff5089ade290f1","first_computed_at":"2026-07-05T02:25:12.336656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:25:12.336656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"loNGeLvbMfYVEYBnJuAilhOAN+18tTJNRjYd/mGmYGHe7SxFqSLV7ivEl6JyANH2snsdLNZmXAPIQ44gVZ/uBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:25:12.337049Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.11795","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a4a384413b41911a8beef28ce76a7bc8969bc42be29b01cb4ddec4a02ff11f2","sha256:fc084451c668e9f6e22f44aa445391c21c7f50043cb7bb223033f762e9701579"],"state_sha256":"43c3b9c14578e8355f72d1a5de6429f8f26fd4fc392c1c859cdf6e267b1ac1ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6B8PyoxpSBOtx8Z2kuzYyhVKvEZRwx43UmSvRhdrZaxZS/V8xZxjFVcvPi3dKFkR65Dl4H6Sv/DcecZcnenZDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:10:46.953598Z","bundle_sha256":"4f401dcc095b646b3700434381e58a0cd558376e8c957ce7865d24ff3e7c2f2c"}}