{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MMPQANW5GVCJJKY6PG4DMBSQZ3","short_pith_number":"pith:MMPQANW5","canonical_record":{"source":{"id":"2109.01048","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-02T16:05:24Z","cross_cats_sorted":[],"title_canon_sha256":"241e7308d1ce2a593934946778e2e3f28e647adcce66c524861c74be32ec95fa","abstract_canon_sha256":"f0d06511f712f5b62dfbeb5e8a3c352f398a759d5ec0303727afc3dd108ffb17"},"schema_version":"1.0"},"canonical_sha256":"631f0036dd354494ab1e79b8360650cec93c8284c30c9756c1dd78a47ee409e9","source":{"kind":"arxiv","id":"2109.01048","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.01048","created_at":"2026-07-05T07:58:41Z"},{"alias_kind":"arxiv_version","alias_value":"2109.01048v3","created_at":"2026-07-05T07:58:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01048","created_at":"2026-07-05T07:58:41Z"},{"alias_kind":"pith_short_12","alias_value":"MMPQANW5GVCJ","created_at":"2026-07-05T07:58:41Z"},{"alias_kind":"pith_short_16","alias_value":"MMPQANW5GVCJJKY6","created_at":"2026-07-05T07:58:41Z"},{"alias_kind":"pith_short_8","alias_value":"MMPQANW5","created_at":"2026-07-05T07:58:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MMPQANW5GVCJJKY6PG4DMBSQZ3","target":"record","payload":{"canonical_record":{"source":{"id":"2109.01048","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-02T16:05:24Z","cross_cats_sorted":[],"title_canon_sha256":"241e7308d1ce2a593934946778e2e3f28e647adcce66c524861c74be32ec95fa","abstract_canon_sha256":"f0d06511f712f5b62dfbeb5e8a3c352f398a759d5ec0303727afc3dd108ffb17"},"schema_version":"1.0"},"canonical_sha256":"631f0036dd354494ab1e79b8360650cec93c8284c30c9756c1dd78a47ee409e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:41.898905Z","signature_b64":"F2vz/8PlQilwsWA+mc7qMGFNsSq0cujerYnnpNK94H3PSMk4PV1IB7wEB51LoxvB6YzyBSjx4f7bZm8chdCxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"631f0036dd354494ab1e79b8360650cec93c8284c30c9756c1dd78a47ee409e9","last_reissued_at":"2026-07-05T07:58:41.898377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:41.898377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.01048","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:58:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uzB3bdMt9nUM48qPXzXZG93klHmh8u1nhuCI54n6D3wSHlgaLZM3ad92uLZrcl/ANFfI+Dl6On+m9tt5yiOFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:42:45.920154Z"},"content_sha256":"50381cb5262343b8cf3a52d6db7adc71d16202c6f2dd2c81757c104ef0898623","schema_version":"1.0","event_id":"sha256:50381cb5262343b8cf3a52d6db7adc71d16202c6f2dd2c81757c104ef0898623"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MMPQANW5GVCJJKY6PG4DMBSQZ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pre-training Language Model Incorporating Domain-specific Heterogeneous Knowledge into A Unified Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Peng, Hongyin Zhu, Jinghui Xiao, Juanzi Li, Lei Hou, Zhiheng Lyu","submitted_at":"2021-09-02T16:05:24Z","abstract_excerpt":"Existing technologies expand BERT from different perspectives, e.g. designing different pre-training tasks, different semantic granularities, and different model architectures. Few models consider expanding BERT from different text formats. In this paper, we propose a heterogeneous knowledge language model (\\textbf{HKLM}), a unified pre-trained language model (PLM) for all forms of text, including unstructured text, semi-structured text, and well-structured text. To capture the corresponding relations among these multi-format knowledge, our approach uses masked language model objective to lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01048","kind":"arxiv","version":3},"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/2109.01048/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":"2026-07-05T07:58:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E8F6BROKPS0Rt74aOlZXh0AepjXyfcTY34facbLJo7mxmG9aDaB4r6RUAHibo2EZRZqil/nxlA5gyOinO+fuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:42:45.920548Z"},"content_sha256":"79a690c6d965f3df9609f9126674e2cff70c6c87eec3bff16e28e72255ca0a6c","schema_version":"1.0","event_id":"sha256:79a690c6d965f3df9609f9126674e2cff70c6c87eec3bff16e28e72255ca0a6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MMPQANW5GVCJJKY6PG4DMBSQZ3/bundle.json","state_url":"https://pith.science/pith/MMPQANW5GVCJJKY6PG4DMBSQZ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MMPQANW5GVCJJKY6PG4DMBSQZ3/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":"2026-07-06T10:42:45Z","links":{"resolver":"https://pith.science/pith/MMPQANW5GVCJJKY6PG4DMBSQZ3","bundle":"https://pith.science/pith/MMPQANW5GVCJJKY6PG4DMBSQZ3/bundle.json","state":"https://pith.science/pith/MMPQANW5GVCJJKY6PG4DMBSQZ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MMPQANW5GVCJJKY6PG4DMBSQZ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MMPQANW5GVCJJKY6PG4DMBSQZ3","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":"f0d06511f712f5b62dfbeb5e8a3c352f398a759d5ec0303727afc3dd108ffb17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-02T16:05:24Z","title_canon_sha256":"241e7308d1ce2a593934946778e2e3f28e647adcce66c524861c74be32ec95fa"},"schema_version":"1.0","source":{"id":"2109.01048","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.01048","created_at":"2026-07-05T07:58:41Z"},{"alias_kind":"arxiv_version","alias_value":"2109.01048v3","created_at":"2026-07-05T07:58:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01048","created_at":"2026-07-05T07:58:41Z"},{"alias_kind":"pith_short_12","alias_value":"MMPQANW5GVCJ","created_at":"2026-07-05T07:58:41Z"},{"alias_kind":"pith_short_16","alias_value":"MMPQANW5GVCJJKY6","created_at":"2026-07-05T07:58:41Z"},{"alias_kind":"pith_short_8","alias_value":"MMPQANW5","created_at":"2026-07-05T07:58:41Z"}],"graph_snapshots":[{"event_id":"sha256:79a690c6d965f3df9609f9126674e2cff70c6c87eec3bff16e28e72255ca0a6c","target":"graph","created_at":"2026-07-05T07:58:41Z","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/2109.01048/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing technologies expand BERT from different perspectives, e.g. designing different pre-training tasks, different semantic granularities, and different model architectures. Few models consider expanding BERT from different text formats. In this paper, we propose a heterogeneous knowledge language model (\\textbf{HKLM}), a unified pre-trained language model (PLM) for all forms of text, including unstructured text, semi-structured text, and well-structured text. To capture the corresponding relations among these multi-format knowledge, our approach uses masked language model objective to lear","authors_text":"Hao Peng, Hongyin Zhu, Jinghui Xiao, Juanzi Li, Lei Hou, Zhiheng Lyu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-02T16:05:24Z","title":"Pre-training Language Model Incorporating Domain-specific Heterogeneous Knowledge into A Unified Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01048","kind":"arxiv","version":3},"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":"sha256:50381cb5262343b8cf3a52d6db7adc71d16202c6f2dd2c81757c104ef0898623","target":"record","created_at":"2026-07-05T07:58:41Z","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":"f0d06511f712f5b62dfbeb5e8a3c352f398a759d5ec0303727afc3dd108ffb17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-02T16:05:24Z","title_canon_sha256":"241e7308d1ce2a593934946778e2e3f28e647adcce66c524861c74be32ec95fa"},"schema_version":"1.0","source":{"id":"2109.01048","kind":"arxiv","version":3}},"canonical_sha256":"631f0036dd354494ab1e79b8360650cec93c8284c30c9756c1dd78a47ee409e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"631f0036dd354494ab1e79b8360650cec93c8284c30c9756c1dd78a47ee409e9","first_computed_at":"2026-07-05T07:58:41.898377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:41.898377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F2vz/8PlQilwsWA+mc7qMGFNsSq0cujerYnnpNK94H3PSMk4PV1IB7wEB51LoxvB6YzyBSjx4f7bZm8chdCxBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:41.898905Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.01048","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50381cb5262343b8cf3a52d6db7adc71d16202c6f2dd2c81757c104ef0898623","sha256:79a690c6d965f3df9609f9126674e2cff70c6c87eec3bff16e28e72255ca0a6c"],"state_sha256":"0cd04fdf2abeea5b198db18cb2a29d9b52cf32342d5a30de030dc1d99a467962"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RJ0fUyVOL0gql7sTl6i6/BHEJOXoW9Lg4qaJo6J8knpVTFdxRlCHXnji74svNFJkQevL512D/Bud+DDLY0ezAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T10:42:45.922531Z","bundle_sha256":"e064fb562c9330a4d1feef71d777ca2ff99762ba156ff6e41c2dd6d2750a562c"}}