{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FFM3ZM7T4RF2BLTO32IOREOKIX","short_pith_number":"pith:FFM3ZM7T","canonical_record":{"source":{"id":"2305.10992","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T14:11:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"348c655a0d20c730b5672acacdbeac49ace749a5ec7dec63ae80b8a841cbaad8","abstract_canon_sha256":"de0c59e3459a464755b222eacceb3624a1c25c48772fd5e907d3a3e69216a1dc"},"schema_version":"1.0"},"canonical_sha256":"2959bcb3f3e44ba0ae6ede90e891ca45e6967f5a70b90dc648ca18dfaea9156c","source":{"kind":"arxiv","id":"2305.10992","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10992","created_at":"2026-07-05T06:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10992v1","created_at":"2026-07-05T06:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10992","created_at":"2026-07-05T06:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"FFM3ZM7T4RF2","created_at":"2026-07-05T06:11:29Z"},{"alias_kind":"pith_short_16","alias_value":"FFM3ZM7T4RF2BLTO","created_at":"2026-07-05T06:11:29Z"},{"alias_kind":"pith_short_8","alias_value":"FFM3ZM7T","created_at":"2026-07-05T06:11:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FFM3ZM7T4RF2BLTO32IOREOKIX","target":"record","payload":{"canonical_record":{"source":{"id":"2305.10992","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T14:11:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"348c655a0d20c730b5672acacdbeac49ace749a5ec7dec63ae80b8a841cbaad8","abstract_canon_sha256":"de0c59e3459a464755b222eacceb3624a1c25c48772fd5e907d3a3e69216a1dc"},"schema_version":"1.0"},"canonical_sha256":"2959bcb3f3e44ba0ae6ede90e891ca45e6967f5a70b90dc648ca18dfaea9156c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:29.138185Z","signature_b64":"SOsTaHwPttHv+NP8om1tmcwWtlgvmFj/R1mrHmmWyHdHYQimcSYN+jNAhXVLHpnBn7JDEr/RCcTSPvwqbroCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2959bcb3f3e44ba0ae6ede90e891ca45e6967f5a70b90dc648ca18dfaea9156c","last_reissued_at":"2026-07-05T06:11:29.137632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:29.137632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.10992","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":"2026-07-05T06:11:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yBoe1jOQQ3dCsu/lWzzaKLJ6MoW/8YcyLnTybkTB+kuDn0MtS/u3/uq/0vtp6809C41Dpl1lzi8XEioBqqSSCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T19:23:32.607864Z"},"content_sha256":"8abd9654d3a2827e65cfd45e29df533e6e65798d488845180694cf4ff92ea968","schema_version":"1.0","event_id":"sha256:8abd9654d3a2827e65cfd45e29df533e6e65798d488845180694cf4ff92ea968"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FFM3ZM7T4RF2BLTO32IOREOKIX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How does the task complexity of masked pretraining objectives affect downstream performance?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Atsuki Yamaguchi, Gaku Morio, Hiroaki Ozaki, Terufumi Morishita, Yasuhiro Sogawa","submitted_at":"2023-05-18T14:11:57Z","abstract_excerpt":"Masked language modeling (MLM) is a widely used self-supervised pretraining objective, where a model needs to predict an original token that is replaced with a mask given contexts. Although simpler and computationally efficient pretraining objectives, e.g., predicting the first character of a masked token, have recently shown comparable results to MLM, no objectives with a masking scheme actually outperform it in downstream tasks. Motivated by the assumption that their lack of complexity plays a vital role in the degradation, we validate whether more complex masked objectives can achieve bette"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10992","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/2305.10992/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":"2026-07-05T06:11:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d2AvqvpZaXE9CM00LZEMmYsg0tgsvGJaLkMqV5M+sfcBaQfP1z99CY2ehY/D9QUoiCVQrfSpHSvtAzQdA6CNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T19:23:32.608451Z"},"content_sha256":"d3e4df1782c4e02157bd930fe364249fa997b0277c4e62a2f20fd4335283e9df","schema_version":"1.0","event_id":"sha256:d3e4df1782c4e02157bd930fe364249fa997b0277c4e62a2f20fd4335283e9df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FFM3ZM7T4RF2BLTO32IOREOKIX/bundle.json","state_url":"https://pith.science/pith/FFM3ZM7T4RF2BLTO32IOREOKIX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FFM3ZM7T4RF2BLTO32IOREOKIX/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":"2026-08-16T19:23:32Z","links":{"resolver":"https://pith.science/pith/FFM3ZM7T4RF2BLTO32IOREOKIX","bundle":"https://pith.science/pith/FFM3ZM7T4RF2BLTO32IOREOKIX/bundle.json","state":"https://pith.science/pith/FFM3ZM7T4RF2BLTO32IOREOKIX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FFM3ZM7T4RF2BLTO32IOREOKIX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FFM3ZM7T4RF2BLTO32IOREOKIX","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":"de0c59e3459a464755b222eacceb3624a1c25c48772fd5e907d3a3e69216a1dc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T14:11:57Z","title_canon_sha256":"348c655a0d20c730b5672acacdbeac49ace749a5ec7dec63ae80b8a841cbaad8"},"schema_version":"1.0","source":{"id":"2305.10992","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10992","created_at":"2026-07-05T06:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10992v1","created_at":"2026-07-05T06:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10992","created_at":"2026-07-05T06:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"FFM3ZM7T4RF2","created_at":"2026-07-05T06:11:29Z"},{"alias_kind":"pith_short_16","alias_value":"FFM3ZM7T4RF2BLTO","created_at":"2026-07-05T06:11:29Z"},{"alias_kind":"pith_short_8","alias_value":"FFM3ZM7T","created_at":"2026-07-05T06:11:29Z"}],"graph_snapshots":[{"event_id":"sha256:d3e4df1782c4e02157bd930fe364249fa997b0277c4e62a2f20fd4335283e9df","target":"graph","created_at":"2026-07-05T06:11:29Z","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/2305.10992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Masked language modeling (MLM) is a widely used self-supervised pretraining objective, where a model needs to predict an original token that is replaced with a mask given contexts. Although simpler and computationally efficient pretraining objectives, e.g., predicting the first character of a masked token, have recently shown comparable results to MLM, no objectives with a masking scheme actually outperform it in downstream tasks. Motivated by the assumption that their lack of complexity plays a vital role in the degradation, we validate whether more complex masked objectives can achieve bette","authors_text":"Atsuki Yamaguchi, Gaku Morio, Hiroaki Ozaki, Terufumi Morishita, Yasuhiro Sogawa","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T14:11:57Z","title":"How does the task complexity of masked pretraining objectives affect downstream performance?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10992","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":"sha256:8abd9654d3a2827e65cfd45e29df533e6e65798d488845180694cf4ff92ea968","target":"record","created_at":"2026-07-05T06:11:29Z","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":"de0c59e3459a464755b222eacceb3624a1c25c48772fd5e907d3a3e69216a1dc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T14:11:57Z","title_canon_sha256":"348c655a0d20c730b5672acacdbeac49ace749a5ec7dec63ae80b8a841cbaad8"},"schema_version":"1.0","source":{"id":"2305.10992","kind":"arxiv","version":1}},"canonical_sha256":"2959bcb3f3e44ba0ae6ede90e891ca45e6967f5a70b90dc648ca18dfaea9156c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2959bcb3f3e44ba0ae6ede90e891ca45e6967f5a70b90dc648ca18dfaea9156c","first_computed_at":"2026-07-05T06:11:29.137632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:29.137632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SOsTaHwPttHv+NP8om1tmcwWtlgvmFj/R1mrHmmWyHdHYQimcSYN+jNAhXVLHpnBn7JDEr/RCcTSPvwqbroCDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:29.138185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10992","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8abd9654d3a2827e65cfd45e29df533e6e65798d488845180694cf4ff92ea968","sha256:d3e4df1782c4e02157bd930fe364249fa997b0277c4e62a2f20fd4335283e9df"],"state_sha256":"bd31767acf966f4464c23c8976dd6569ef48889290d240cc9f7a6a1daf3ee155"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7ymxmEIB75VsaxDHU+bCSzuzz5PzRQjFYe8ILgiFtqEzFiZT8bjjEam+ZnNbFz6n3zzYPy2KBkvc6rYVprewCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T19:23:32.614284Z","bundle_sha256":"38bb4de0893a2a31d53c49cffa2d9e9cde7840bff13bbcf8baa0365c09a80bcb"}}