{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4KEOMMGLRBFJMF2KEKAYCDH7UF","short_pith_number":"pith:4KEOMMGL","canonical_record":{"source":{"id":"2305.15275","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T16:00:54Z","cross_cats_sorted":[],"title_canon_sha256":"4300692a3647114b30caac08042293dc384afd9b8b1a5a3235f8654293451f80","abstract_canon_sha256":"5f5b570c49771495b8911870efee8a7427bae78e8d222f8c0c4e083ff0180d17"},"schema_version":"1.0"},"canonical_sha256":"e288e630cb884a96174a2281810cffa16f315eae733b49d09a254ca1bdef8794","source":{"kind":"arxiv","id":"2305.15275","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15275","created_at":"2026-07-05T06:13:33Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15275v1","created_at":"2026-07-05T06:13:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15275","created_at":"2026-07-05T06:13:33Z"},{"alias_kind":"pith_short_12","alias_value":"4KEOMMGLRBFJ","created_at":"2026-07-05T06:13:33Z"},{"alias_kind":"pith_short_16","alias_value":"4KEOMMGLRBFJMF2K","created_at":"2026-07-05T06:13:33Z"},{"alias_kind":"pith_short_8","alias_value":"4KEOMMGL","created_at":"2026-07-05T06:13:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4KEOMMGLRBFJMF2KEKAYCDH7UF","target":"record","payload":{"canonical_record":{"source":{"id":"2305.15275","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T16:00:54Z","cross_cats_sorted":[],"title_canon_sha256":"4300692a3647114b30caac08042293dc384afd9b8b1a5a3235f8654293451f80","abstract_canon_sha256":"5f5b570c49771495b8911870efee8a7427bae78e8d222f8c0c4e083ff0180d17"},"schema_version":"1.0"},"canonical_sha256":"e288e630cb884a96174a2281810cffa16f315eae733b49d09a254ca1bdef8794","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:33.245297Z","signature_b64":"C6dZo+pTZDuNtmRlFu+bbv8VPImuEr3UvHZringZaKrmm3ImRJbk9u37p5ADoZWcAG8JrVKuhA8h79Ag/TJNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e288e630cb884a96174a2281810cffa16f315eae733b49d09a254ca1bdef8794","last_reissued_at":"2026-07-05T06:13:33.244755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:33.244755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.15275","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":"2026-07-05T06:13:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gFbrPFea8bxuKrF5XDaHaKnM+PfOwTRtSWhcVTB9ifJ514R7dLwGXgxlfuJe3s0PesgiG7zm8nFQFNCprNZPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T21:25:21.952076Z"},"content_sha256":"80b43a64a8bc978e00b8b35114dc880bd5d3bf2d4bc7d4c2ee0bf4b6e294b4fa","schema_version":"1.0","event_id":"sha256:80b43a64a8bc978e00b8b35114dc880bd5d3bf2d4bc7d4c2ee0bf4b6e294b4fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4KEOMMGLRBFJMF2KEKAYCDH7UF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Evolution Learning for Discriminative Language Model Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Du, Dacheng Tao, Juhua Liu, Liang Ding, Qihuang Zhong","submitted_at":"2023-05-24T16:00:54Z","abstract_excerpt":"Masked language modeling, widely used in discriminative language model (e.g., BERT) pretraining, commonly adopts a random masking strategy. However, random masking does not consider the importance of the different words in the sentence meaning, where some of them are more worthy to be predicted. Therefore, various masking strategies (e.g., entity-level masking) are proposed, but most of them require expensive prior knowledge and generally train from scratch without reusing existing model weights. In this paper, we present Self-Evolution learning (SE), a simple and effective token masking and l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15275","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/2305.15275/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":"2026-07-05T06:13:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IihGjIMwb3CCNjDuQVRD6g7AdVKzB6ghXURMmba9ENhBY8fJ0P5N7sx1KwRQjoVosLp1ECfkXCk0zSZdOfr7Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T21:25:21.952595Z"},"content_sha256":"bfd5ee59dda7cf319b868cab2153da421d28d667ece147acc27ecd0597c99fe8","schema_version":"1.0","event_id":"sha256:bfd5ee59dda7cf319b868cab2153da421d28d667ece147acc27ecd0597c99fe8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4KEOMMGLRBFJMF2KEKAYCDH7UF/bundle.json","state_url":"https://pith.science/pith/4KEOMMGLRBFJMF2KEKAYCDH7UF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4KEOMMGLRBFJMF2KEKAYCDH7UF/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":"2026-08-14T21:25:21Z","links":{"resolver":"https://pith.science/pith/4KEOMMGLRBFJMF2KEKAYCDH7UF","bundle":"https://pith.science/pith/4KEOMMGLRBFJMF2KEKAYCDH7UF/bundle.json","state":"https://pith.science/pith/4KEOMMGLRBFJMF2KEKAYCDH7UF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4KEOMMGLRBFJMF2KEKAYCDH7UF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4KEOMMGLRBFJMF2KEKAYCDH7UF","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":"5f5b570c49771495b8911870efee8a7427bae78e8d222f8c0c4e083ff0180d17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T16:00:54Z","title_canon_sha256":"4300692a3647114b30caac08042293dc384afd9b8b1a5a3235f8654293451f80"},"schema_version":"1.0","source":{"id":"2305.15275","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15275","created_at":"2026-07-05T06:13:33Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15275v1","created_at":"2026-07-05T06:13:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15275","created_at":"2026-07-05T06:13:33Z"},{"alias_kind":"pith_short_12","alias_value":"4KEOMMGLRBFJ","created_at":"2026-07-05T06:13:33Z"},{"alias_kind":"pith_short_16","alias_value":"4KEOMMGLRBFJMF2K","created_at":"2026-07-05T06:13:33Z"},{"alias_kind":"pith_short_8","alias_value":"4KEOMMGL","created_at":"2026-07-05T06:13:33Z"}],"graph_snapshots":[{"event_id":"sha256:bfd5ee59dda7cf319b868cab2153da421d28d667ece147acc27ecd0597c99fe8","target":"graph","created_at":"2026-07-05T06:13:33Z","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/2305.15275/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Masked language modeling, widely used in discriminative language model (e.g., BERT) pretraining, commonly adopts a random masking strategy. However, random masking does not consider the importance of the different words in the sentence meaning, where some of them are more worthy to be predicted. Therefore, various masking strategies (e.g., entity-level masking) are proposed, but most of them require expensive prior knowledge and generally train from scratch without reusing existing model weights. In this paper, we present Self-Evolution learning (SE), a simple and effective token masking and l","authors_text":"Bo Du, Dacheng Tao, Juhua Liu, Liang Ding, Qihuang Zhong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T16:00:54Z","title":"Self-Evolution Learning for Discriminative Language Model Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15275","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":"sha256:80b43a64a8bc978e00b8b35114dc880bd5d3bf2d4bc7d4c2ee0bf4b6e294b4fa","target":"record","created_at":"2026-07-05T06:13:33Z","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":"5f5b570c49771495b8911870efee8a7427bae78e8d222f8c0c4e083ff0180d17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T16:00:54Z","title_canon_sha256":"4300692a3647114b30caac08042293dc384afd9b8b1a5a3235f8654293451f80"},"schema_version":"1.0","source":{"id":"2305.15275","kind":"arxiv","version":1}},"canonical_sha256":"e288e630cb884a96174a2281810cffa16f315eae733b49d09a254ca1bdef8794","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e288e630cb884a96174a2281810cffa16f315eae733b49d09a254ca1bdef8794","first_computed_at":"2026-07-05T06:13:33.244755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:33.244755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C6dZo+pTZDuNtmRlFu+bbv8VPImuEr3UvHZringZaKrmm3ImRJbk9u37p5ADoZWcAG8JrVKuhA8h79Ag/TJNDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:33.245297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.15275","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80b43a64a8bc978e00b8b35114dc880bd5d3bf2d4bc7d4c2ee0bf4b6e294b4fa","sha256:bfd5ee59dda7cf319b868cab2153da421d28d667ece147acc27ecd0597c99fe8"],"state_sha256":"61b9dfe33a04d399a6a4fdf93ab76a6eb35e3d13914c18fffac431427680e0f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tCfVVJ8U+RbbRAa9FOWfFhxON9ITAw9JVmaMwzyHWvyMDtE+1NWB9o+/UBKTC5q/M1B2IlUWm4Oz1zDhIHZpCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T21:25:21.956399Z","bundle_sha256":"66353970787b3206361d67f3fd035efb4d0a5669207f7a79d51c3356572f94df"}}