{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DA3JI36F7ZOCO2XQYBJIEUJKKT","short_pith_number":"pith:DA3JI36F","canonical_record":{"source":{"id":"2303.15619","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-27T22:27:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8cb62f3f30057e8e4f7f2bbe142407eaa289f400e74ac4cb7fae7847ed12c095","abstract_canon_sha256":"dc2fc61f58bab28307d01a4af8622268bb0ab3c657aae18bd2ea3692ff3001cc"},"schema_version":"1.0"},"canonical_sha256":"1836946fc5fe5c276af0c05282512a54d321d70434f5a52ca6d88436a57d65dc","source":{"kind":"arxiv","id":"2303.15619","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.15619","created_at":"2026-06-03T01:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2303.15619v2","created_at":"2026-06-03T01:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15619","created_at":"2026-06-03T01:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"DA3JI36F7ZOC","created_at":"2026-06-03T01:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"DA3JI36F7ZOCO2XQ","created_at":"2026-06-03T01:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"DA3JI36F","created_at":"2026-06-03T01:05:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DA3JI36F7ZOCO2XQYBJIEUJKKT","target":"record","payload":{"canonical_record":{"source":{"id":"2303.15619","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-27T22:27:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8cb62f3f30057e8e4f7f2bbe142407eaa289f400e74ac4cb7fae7847ed12c095","abstract_canon_sha256":"dc2fc61f58bab28307d01a4af8622268bb0ab3c657aae18bd2ea3692ff3001cc"},"schema_version":"1.0"},"canonical_sha256":"1836946fc5fe5c276af0c05282512a54d321d70434f5a52ca6d88436a57d65dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:02.849475Z","signature_b64":"P0tj936UbHdBBx2EsubEblrtBqex6m9Crd18BPCPaeLvZE5ZPiiRAeoHnhkfwl+EgFX6D4zcElMgbBgvTqiHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1836946fc5fe5c276af0c05282512a54d321d70434f5a52ca6d88436a57d65dc","last_reissued_at":"2026-06-03T01:05:02.848997Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:02.848997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.15619","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ali+wZstR0OT+OE4hgNuousDhyEX+qGfv4pibT+/31dllaxDJjViates3fdKpgPEt1t1MQJcyAiBBqJHPMopCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T11:51:00.669866Z"},"content_sha256":"c1b3ded378aa426fc997f6c5a0c32dfc540cd73debddc03cdb276fd48af991fb","schema_version":"1.0","event_id":"sha256:c1b3ded378aa426fc997f6c5a0c32dfc540cd73debddc03cdb276fd48af991fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DA3JI36F7ZOCO2XQYBJIEUJKKT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Typhoon: Towards an Effective Task-Specific Masking Strategy for Pre-trained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bruce Changlong Xu, Hashem Elezabi, Muhammed Shahir Abdurrahman","submitted_at":"2023-03-27T22:27:23Z","abstract_excerpt":"The choice of \\emph{which} tokens to mask is a central, under-examined design decision in masked language modeling (MLM). Standard pretraining masks tokens uniformly at random, but several studies show that more informative masking targets can improve downstream performance. We study masking as a \\emph{task-adaptive} component of the fine-tuning pipeline and introduce \\textbf{Typhoon}, a masking strategy that uses the gradient of the task loss with respect to one-hot token inputs to estimate, online, how much each token type contributes to the objective. Typhoon maintains an exponential moving"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15619","kind":"arxiv","version":2},"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/2303.15619/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":"2026-06-03T01:05:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"buKXcW+R7qeOqopLhxinDINlmJWRyZ+lBFdKdDo6ohiWr3XfZ5ILvE3VWpFSY4u0/6wtgUzU5O7oU5nHXV/jDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T11:51:00.670252Z"},"content_sha256":"98e5c6a899d9c7b5a3737610a29be1f8d898cb9a876a49ae468ea0ddafb43b37","schema_version":"1.0","event_id":"sha256:98e5c6a899d9c7b5a3737610a29be1f8d898cb9a876a49ae468ea0ddafb43b37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DA3JI36F7ZOCO2XQYBJIEUJKKT/bundle.json","state_url":"https://pith.science/pith/DA3JI36F7ZOCO2XQYBJIEUJKKT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DA3JI36F7ZOCO2XQYBJIEUJKKT/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":"2026-06-26T11:51:00Z","links":{"resolver":"https://pith.science/pith/DA3JI36F7ZOCO2XQYBJIEUJKKT","bundle":"https://pith.science/pith/DA3JI36F7ZOCO2XQYBJIEUJKKT/bundle.json","state":"https://pith.science/pith/DA3JI36F7ZOCO2XQYBJIEUJKKT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DA3JI36F7ZOCO2XQYBJIEUJKKT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DA3JI36F7ZOCO2XQYBJIEUJKKT","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":"dc2fc61f58bab28307d01a4af8622268bb0ab3c657aae18bd2ea3692ff3001cc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-27T22:27:23Z","title_canon_sha256":"8cb62f3f30057e8e4f7f2bbe142407eaa289f400e74ac4cb7fae7847ed12c095"},"schema_version":"1.0","source":{"id":"2303.15619","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.15619","created_at":"2026-06-03T01:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2303.15619v2","created_at":"2026-06-03T01:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15619","created_at":"2026-06-03T01:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"DA3JI36F7ZOC","created_at":"2026-06-03T01:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"DA3JI36F7ZOCO2XQ","created_at":"2026-06-03T01:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"DA3JI36F","created_at":"2026-06-03T01:05:02Z"}],"graph_snapshots":[{"event_id":"sha256:98e5c6a899d9c7b5a3737610a29be1f8d898cb9a876a49ae468ea0ddafb43b37","target":"graph","created_at":"2026-06-03T01:05:02Z","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/2303.15619/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The choice of \\emph{which} tokens to mask is a central, under-examined design decision in masked language modeling (MLM). Standard pretraining masks tokens uniformly at random, but several studies show that more informative masking targets can improve downstream performance. We study masking as a \\emph{task-adaptive} component of the fine-tuning pipeline and introduce \\textbf{Typhoon}, a masking strategy that uses the gradient of the task loss with respect to one-hot token inputs to estimate, online, how much each token type contributes to the objective. Typhoon maintains an exponential moving","authors_text":"Bruce Changlong Xu, Hashem Elezabi, Muhammed Shahir Abdurrahman","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-27T22:27:23Z","title":"Typhoon: Towards an Effective Task-Specific Masking Strategy for Pre-trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15619","kind":"arxiv","version":2},"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:c1b3ded378aa426fc997f6c5a0c32dfc540cd73debddc03cdb276fd48af991fb","target":"record","created_at":"2026-06-03T01:05:02Z","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":"dc2fc61f58bab28307d01a4af8622268bb0ab3c657aae18bd2ea3692ff3001cc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-27T22:27:23Z","title_canon_sha256":"8cb62f3f30057e8e4f7f2bbe142407eaa289f400e74ac4cb7fae7847ed12c095"},"schema_version":"1.0","source":{"id":"2303.15619","kind":"arxiv","version":2}},"canonical_sha256":"1836946fc5fe5c276af0c05282512a54d321d70434f5a52ca6d88436a57d65dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1836946fc5fe5c276af0c05282512a54d321d70434f5a52ca6d88436a57d65dc","first_computed_at":"2026-06-03T01:05:02.848997Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:02.848997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P0tj936UbHdBBx2EsubEblrtBqex6m9Crd18BPCPaeLvZE5ZPiiRAeoHnhkfwl+EgFX6D4zcElMgbBgvTqiHCA==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:02.849475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.15619","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1b3ded378aa426fc997f6c5a0c32dfc540cd73debddc03cdb276fd48af991fb","sha256:98e5c6a899d9c7b5a3737610a29be1f8d898cb9a876a49ae468ea0ddafb43b37"],"state_sha256":"94b68fe9d293a6fb910fc9b486591133240b2f81bfc34061d65806a984486379"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/pGmoRpqeNVwJ54kOeWjriJEAXGNrujMzmErV5a5W9maGvAhtekkI5Aax0zkY//Bz0WAUDPLUhnTa2wOxLuTCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T11:51:00.672304Z","bundle_sha256":"5be2a905475412bb90fe39cb51b13c63e6371304c1e1513dd88ef4b0f986c542"}}