{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:JPLGWNIRSXI3ACAUTVAVMXIA4K","short_pith_number":"pith:JPLGWNIR","canonical_record":{"source":{"id":"2104.10516","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-21T13:15:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6c903bcac8309b614f002fb2ce515e85fb8264dfd098133590ef868346e2beec","abstract_canon_sha256":"45d11b18c56419a782404f1fe5f00343876f9fee0c6423c0398f031517fb23e6"},"schema_version":"1.0"},"canonical_sha256":"4bd66b351195d1b008149d41565d00e2aaf70662ed23fae42551315eb24289a6","source":{"kind":"arxiv","id":"2104.10516","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.10516","created_at":"2026-07-05T02:34:03Z"},{"alias_kind":"arxiv_version","alias_value":"2104.10516v1","created_at":"2026-07-05T02:34:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.10516","created_at":"2026-07-05T02:34:03Z"},{"alias_kind":"pith_short_12","alias_value":"JPLGWNIRSXI3","created_at":"2026-07-05T02:34:03Z"},{"alias_kind":"pith_short_16","alias_value":"JPLGWNIRSXI3ACAU","created_at":"2026-07-05T02:34:03Z"},{"alias_kind":"pith_short_8","alias_value":"JPLGWNIR","created_at":"2026-07-05T02:34:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:JPLGWNIRSXI3ACAUTVAVMXIA4K","target":"record","payload":{"canonical_record":{"source":{"id":"2104.10516","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-21T13:15:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6c903bcac8309b614f002fb2ce515e85fb8264dfd098133590ef868346e2beec","abstract_canon_sha256":"45d11b18c56419a782404f1fe5f00343876f9fee0c6423c0398f031517fb23e6"},"schema_version":"1.0"},"canonical_sha256":"4bd66b351195d1b008149d41565d00e2aaf70662ed23fae42551315eb24289a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:34:03.301904Z","signature_b64":"tMHP2r1nZJeFt1Z8i5WmDYVWv+WsN+nQrQ8kx/5dMW9VZLk28ILEAIFmnDHAah1Q9L9FwLkwRiBrdWz8Ug/yBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bd66b351195d1b008149d41565d00e2aaf70662ed23fae42551315eb24289a6","last_reissued_at":"2026-07-05T02:34:03.301465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:34:03.301465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.10516","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":"2026-07-05T02:34:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3LjHLiBvD3FpzIy2OswoCbT2EP6H26CJQZdEOduEQRCWvjvV5TsDp2OkLWqOJBrPxNIsqNuEU/Fih8kGH8ZHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T23:14:23.133484Z"},"content_sha256":"e6746c801b272888b65b57560d7b94fa41a0ad9423e237de9cc99caf1e8bd0be","schema_version":"1.0","event_id":"sha256:e6746c801b272888b65b57560d7b94fa41a0ad9423e237de9cc99caf1e8bd0be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:JPLGWNIRSXI3ACAUTVAVMXIA4K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving BERT Pretraining with Syntactic Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Gijs Wijnholds, Giorgos Tziafas, Konstantinos Kogkalidis, Michael Moortgat","submitted_at":"2021-04-21T13:15:58Z","abstract_excerpt":"Bidirectional masked Transformers have become the core theme in the current NLP landscape. Despite their impressive benchmarks, a recurring theme in recent research has been to question such models' capacity for syntactic generalization. In this work, we seek to address this question by adding a supervised, token-level supertagging objective to standard unsupervised pretraining, enabling the explicit incorporation of syntactic biases into the network's training dynamics. Our approach is straightforward to implement, induces a marginal computational overhead and is general enough to adapt to a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.10516","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/2104.10516/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":"2026-07-05T02:34:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6jlPjcXOpSu0jwytfikt/GOtDRv9ebklfzKt0+LHvgN4I90LsiSHvc/w+1oSWr0QR3JVkm8IuFZbqe9Scrz+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T23:14:23.133866Z"},"content_sha256":"07cbf5308f641ba2c458ff0770ae308e6a3640bcc49a91f2805a58974a568c96","schema_version":"1.0","event_id":"sha256:07cbf5308f641ba2c458ff0770ae308e6a3640bcc49a91f2805a58974a568c96"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JPLGWNIRSXI3ACAUTVAVMXIA4K/bundle.json","state_url":"https://pith.science/pith/JPLGWNIRSXI3ACAUTVAVMXIA4K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JPLGWNIRSXI3ACAUTVAVMXIA4K/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":"2026-07-09T23:14:23Z","links":{"resolver":"https://pith.science/pith/JPLGWNIRSXI3ACAUTVAVMXIA4K","bundle":"https://pith.science/pith/JPLGWNIRSXI3ACAUTVAVMXIA4K/bundle.json","state":"https://pith.science/pith/JPLGWNIRSXI3ACAUTVAVMXIA4K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JPLGWNIRSXI3ACAUTVAVMXIA4K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JPLGWNIRSXI3ACAUTVAVMXIA4K","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":"45d11b18c56419a782404f1fe5f00343876f9fee0c6423c0398f031517fb23e6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-21T13:15:58Z","title_canon_sha256":"6c903bcac8309b614f002fb2ce515e85fb8264dfd098133590ef868346e2beec"},"schema_version":"1.0","source":{"id":"2104.10516","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.10516","created_at":"2026-07-05T02:34:03Z"},{"alias_kind":"arxiv_version","alias_value":"2104.10516v1","created_at":"2026-07-05T02:34:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.10516","created_at":"2026-07-05T02:34:03Z"},{"alias_kind":"pith_short_12","alias_value":"JPLGWNIRSXI3","created_at":"2026-07-05T02:34:03Z"},{"alias_kind":"pith_short_16","alias_value":"JPLGWNIRSXI3ACAU","created_at":"2026-07-05T02:34:03Z"},{"alias_kind":"pith_short_8","alias_value":"JPLGWNIR","created_at":"2026-07-05T02:34:03Z"}],"graph_snapshots":[{"event_id":"sha256:07cbf5308f641ba2c458ff0770ae308e6a3640bcc49a91f2805a58974a568c96","target":"graph","created_at":"2026-07-05T02:34:03Z","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/2104.10516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bidirectional masked Transformers have become the core theme in the current NLP landscape. Despite their impressive benchmarks, a recurring theme in recent research has been to question such models' capacity for syntactic generalization. In this work, we seek to address this question by adding a supervised, token-level supertagging objective to standard unsupervised pretraining, enabling the explicit incorporation of syntactic biases into the network's training dynamics. Our approach is straightforward to implement, induces a marginal computational overhead and is general enough to adapt to a ","authors_text":"Gijs Wijnholds, Giorgos Tziafas, Konstantinos Kogkalidis, Michael Moortgat","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-21T13:15:58Z","title":"Improving BERT Pretraining with Syntactic Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.10516","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:e6746c801b272888b65b57560d7b94fa41a0ad9423e237de9cc99caf1e8bd0be","target":"record","created_at":"2026-07-05T02:34:03Z","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":"45d11b18c56419a782404f1fe5f00343876f9fee0c6423c0398f031517fb23e6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-21T13:15:58Z","title_canon_sha256":"6c903bcac8309b614f002fb2ce515e85fb8264dfd098133590ef868346e2beec"},"schema_version":"1.0","source":{"id":"2104.10516","kind":"arxiv","version":1}},"canonical_sha256":"4bd66b351195d1b008149d41565d00e2aaf70662ed23fae42551315eb24289a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bd66b351195d1b008149d41565d00e2aaf70662ed23fae42551315eb24289a6","first_computed_at":"2026-07-05T02:34:03.301465Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:34:03.301465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tMHP2r1nZJeFt1Z8i5WmDYVWv+WsN+nQrQ8kx/5dMW9VZLk28ILEAIFmnDHAah1Q9L9FwLkwRiBrdWz8Ug/yBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:34:03.301904Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.10516","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6746c801b272888b65b57560d7b94fa41a0ad9423e237de9cc99caf1e8bd0be","sha256:07cbf5308f641ba2c458ff0770ae308e6a3640bcc49a91f2805a58974a568c96"],"state_sha256":"2206155e0f928d93c6fefab016ce290bebde3171f53f71a4b91b9cadfa38e385"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hx2qnD5R5wfDoT+69/e2Rza+30o1m2xnfxjtQOnbP5mFeH19ngA9irAGmeyk+JFEq/GSQ2fXFSxN1RCQ1tUfCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T23:14:23.135771Z","bundle_sha256":"58bf9b351426cf1a15aa2617cf7d53e99f7201738c3938538528ae430e6da82a"}}