{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZVYYPAKVJ7CADRSPYJLYT7MNFZ","short_pith_number":"pith:ZVYYPAKV","canonical_record":{"source":{"id":"2106.13715","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-25T15:51:55Z","cross_cats_sorted":[],"title_canon_sha256":"9eedc17e90046ae49c58a4df47811b7014946b9e9b3262fa5a9f9d277192be71","abstract_canon_sha256":"b998f75f835d406e14b25adddc904bee39701d72526685074c27e043d1f06ef2"},"schema_version":"1.0"},"canonical_sha256":"cd718781554fc401c64fc25789fd8d2e70d73cbd3bac4682095c9250b1f62f98","source":{"kind":"arxiv","id":"2106.13715","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13715","created_at":"2026-07-05T02:52:25Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13715v1","created_at":"2026-07-05T02:52:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13715","created_at":"2026-07-05T02:52:25Z"},{"alias_kind":"pith_short_12","alias_value":"ZVYYPAKVJ7CA","created_at":"2026-07-05T02:52:25Z"},{"alias_kind":"pith_short_16","alias_value":"ZVYYPAKVJ7CADRSP","created_at":"2026-07-05T02:52:25Z"},{"alias_kind":"pith_short_8","alias_value":"ZVYYPAKV","created_at":"2026-07-05T02:52:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZVYYPAKVJ7CADRSPYJLYT7MNFZ","target":"record","payload":{"canonical_record":{"source":{"id":"2106.13715","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-25T15:51:55Z","cross_cats_sorted":[],"title_canon_sha256":"9eedc17e90046ae49c58a4df47811b7014946b9e9b3262fa5a9f9d277192be71","abstract_canon_sha256":"b998f75f835d406e14b25adddc904bee39701d72526685074c27e043d1f06ef2"},"schema_version":"1.0"},"canonical_sha256":"cd718781554fc401c64fc25789fd8d2e70d73cbd3bac4682095c9250b1f62f98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:25.391836Z","signature_b64":"hFLXCACI/3bL2bLymqN0BMKk9DhiXGCtyCxuZ7zWiows1g2I5zO1Q+tvIeEKPw/DHqTT6zs+FmNQj1gIx/AaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd718781554fc401c64fc25789fd8d2e70d73cbd3bac4682095c9250b1f62f98","last_reissued_at":"2026-07-05T02:52:25.391417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:25.391417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.13715","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":"2026-07-05T02:52:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mHdROZIVzcX4iKvMaIITF53Vc2i6XSsv3WdNn6qel1YQGav4mxRwShxHpKzEfK47IvwxdNIkvXYjlD9IWgi0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:38:48.808593Z"},"content_sha256":"85061332b3629cd8da610460c2f9feedca52bfdd6c02dabe2a6b3e9c5e12abbf","schema_version":"1.0","event_id":"sha256:85061332b3629cd8da610460c2f9feedca52bfdd6c02dabe2a6b3e9c5e12abbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZVYYPAKVJ7CADRSPYJLYT7MNFZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Sample Replacements for ELECTRA Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Hangbo Bao, Ke Xu, Li Dong, Yaru Hao","submitted_at":"2021-06-25T15:51:55Z","abstract_excerpt":"ELECTRA pretrains a discriminator to detect replaced tokens, where the replacements are sampled from a generator trained with masked language modeling. Despite the compelling performance, ELECTRA suffers from the following two issues. First, there is no direct feedback loop from discriminator to generator, which renders replacement sampling inefficient. Second, the generator's prediction tends to be over-confident along with training, making replacements biased to correct tokens. In this paper, we propose two methods to improve replacement sampling for ELECTRA pre-training. Specifically, we au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13715","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/2106.13715/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":"2026-07-05T02:52:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hvmgVH+deE7chf2rT1m0lohwsMerJQ4M3ZHnETewjK4gi1GlMmextpLCJW2FF5dat6UnYOv7w9VVwh3rdcZ3BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:38:48.809205Z"},"content_sha256":"ee477438be374a8093e70f293beedddebefadc2e1cb148b253bdc2f810ea2e46","schema_version":"1.0","event_id":"sha256:ee477438be374a8093e70f293beedddebefadc2e1cb148b253bdc2f810ea2e46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZVYYPAKVJ7CADRSPYJLYT7MNFZ/bundle.json","state_url":"https://pith.science/pith/ZVYYPAKVJ7CADRSPYJLYT7MNFZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZVYYPAKVJ7CADRSPYJLYT7MNFZ/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":"2026-07-07T02:38:48Z","links":{"resolver":"https://pith.science/pith/ZVYYPAKVJ7CADRSPYJLYT7MNFZ","bundle":"https://pith.science/pith/ZVYYPAKVJ7CADRSPYJLYT7MNFZ/bundle.json","state":"https://pith.science/pith/ZVYYPAKVJ7CADRSPYJLYT7MNFZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZVYYPAKVJ7CADRSPYJLYT7MNFZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZVYYPAKVJ7CADRSPYJLYT7MNFZ","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":"b998f75f835d406e14b25adddc904bee39701d72526685074c27e043d1f06ef2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-25T15:51:55Z","title_canon_sha256":"9eedc17e90046ae49c58a4df47811b7014946b9e9b3262fa5a9f9d277192be71"},"schema_version":"1.0","source":{"id":"2106.13715","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13715","created_at":"2026-07-05T02:52:25Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13715v1","created_at":"2026-07-05T02:52:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13715","created_at":"2026-07-05T02:52:25Z"},{"alias_kind":"pith_short_12","alias_value":"ZVYYPAKVJ7CA","created_at":"2026-07-05T02:52:25Z"},{"alias_kind":"pith_short_16","alias_value":"ZVYYPAKVJ7CADRSP","created_at":"2026-07-05T02:52:25Z"},{"alias_kind":"pith_short_8","alias_value":"ZVYYPAKV","created_at":"2026-07-05T02:52:25Z"}],"graph_snapshots":[{"event_id":"sha256:ee477438be374a8093e70f293beedddebefadc2e1cb148b253bdc2f810ea2e46","target":"graph","created_at":"2026-07-05T02:52:25Z","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/2106.13715/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"ELECTRA pretrains a discriminator to detect replaced tokens, where the replacements are sampled from a generator trained with masked language modeling. Despite the compelling performance, ELECTRA suffers from the following two issues. First, there is no direct feedback loop from discriminator to generator, which renders replacement sampling inefficient. Second, the generator's prediction tends to be over-confident along with training, making replacements biased to correct tokens. In this paper, we propose two methods to improve replacement sampling for ELECTRA pre-training. Specifically, we au","authors_text":"Furu Wei, Hangbo Bao, Ke Xu, Li Dong, Yaru Hao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-25T15:51:55Z","title":"Learning to Sample Replacements for ELECTRA Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13715","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":"sha256:85061332b3629cd8da610460c2f9feedca52bfdd6c02dabe2a6b3e9c5e12abbf","target":"record","created_at":"2026-07-05T02:52:25Z","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":"b998f75f835d406e14b25adddc904bee39701d72526685074c27e043d1f06ef2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-25T15:51:55Z","title_canon_sha256":"9eedc17e90046ae49c58a4df47811b7014946b9e9b3262fa5a9f9d277192be71"},"schema_version":"1.0","source":{"id":"2106.13715","kind":"arxiv","version":1}},"canonical_sha256":"cd718781554fc401c64fc25789fd8d2e70d73cbd3bac4682095c9250b1f62f98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd718781554fc401c64fc25789fd8d2e70d73cbd3bac4682095c9250b1f62f98","first_computed_at":"2026-07-05T02:52:25.391417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:25.391417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hFLXCACI/3bL2bLymqN0BMKk9DhiXGCtyCxuZ7zWiows1g2I5zO1Q+tvIeEKPw/DHqTT6zs+FmNQj1gIx/AaCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:25.391836Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.13715","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85061332b3629cd8da610460c2f9feedca52bfdd6c02dabe2a6b3e9c5e12abbf","sha256:ee477438be374a8093e70f293beedddebefadc2e1cb148b253bdc2f810ea2e46"],"state_sha256":"57151ad3abdf2c9ae979c052bd8e42937ad2aefa595693c3b40fc7fc23ceaa83"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QgG1VCaBE28ifLD+XhZij6ihJS0gm3W3R1e+EehYFH1XtbxioAcQnKN28I6YJbAusc2my+aepqnegE3mwzyUCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T02:38:48.812534Z","bundle_sha256":"5a0f13356bad16ee837656f9968d37027dec4fe16ccf343aa2fcf4c79969c1f2"}}