{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WQOEH5XCFFV2MB5G3CZSWH5VJY","short_pith_number":"pith:WQOEH5XC","canonical_record":{"source":{"id":"2104.07204","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-15T02:36:49Z","cross_cats_sorted":[],"title_canon_sha256":"724d8912a58f7465421e049196c52ccd655cb0feeb5eade8e12586613286668c","abstract_canon_sha256":"81db396b647758de63e23a26f953932e9c81c6da463267f6abb9c7dd9b43b293"},"schema_version":"1.0"},"canonical_sha256":"b41c43f6e2296ba607a6d8b32b1fb54e267a69b3a60f63e5d326bef7a7f7d0ff","source":{"kind":"arxiv","id":"2104.07204","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.07204","created_at":"2026-07-05T02:44:06Z"},{"alias_kind":"arxiv_version","alias_value":"2104.07204v2","created_at":"2026-07-05T02:44:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07204","created_at":"2026-07-05T02:44:06Z"},{"alias_kind":"pith_short_12","alias_value":"WQOEH5XCFFV2","created_at":"2026-07-05T02:44:06Z"},{"alias_kind":"pith_short_16","alias_value":"WQOEH5XCFFV2MB5G","created_at":"2026-07-05T02:44:06Z"},{"alias_kind":"pith_short_8","alias_value":"WQOEH5XC","created_at":"2026-07-05T02:44:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WQOEH5XCFFV2MB5G3CZSWH5VJY","target":"record","payload":{"canonical_record":{"source":{"id":"2104.07204","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-15T02:36:49Z","cross_cats_sorted":[],"title_canon_sha256":"724d8912a58f7465421e049196c52ccd655cb0feeb5eade8e12586613286668c","abstract_canon_sha256":"81db396b647758de63e23a26f953932e9c81c6da463267f6abb9c7dd9b43b293"},"schema_version":"1.0"},"canonical_sha256":"b41c43f6e2296ba607a6d8b32b1fb54e267a69b3a60f63e5d326bef7a7f7d0ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:06.153845Z","signature_b64":"JXR8THu6sfDsvdYScigEVy7Fs5I2F4CIXva48tfkpcUhaeM9kW/m/XaWI05nv9pw++j8+xG+Qe9khSsTHETZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b41c43f6e2296ba607a6d8b32b1fb54e267a69b3a60f63e5d326bef7a7f7d0ff","last_reissued_at":"2026-07-05T02:44:06.153409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:06.153409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.07204","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":"2026-07-05T02:44:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6XLXzlm0JUHY0n3uqw55YfV81N7+IEsCtaYzrBjxG1VdZlKylTdXolt46exIFI73HWe1XBYr9Jyvj/Sg6Q38CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:43:54.095782Z"},"content_sha256":"13ba847ab673d5d00a89ebcc8db768dc1d0eacd3749fbd7cb431bac6e01b318d","schema_version":"1.0","event_id":"sha256:13ba847ab673d5d00a89ebcc8db768dc1d0eacd3749fbd7cb431bac6e01b318d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WQOEH5XCFFV2MB5G3CZSWH5VJY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongyan Zhao, Songfang Huang, Yansong Feng, Yijia Liu, Yuxuan Lai","submitted_at":"2021-04-15T02:36:49Z","abstract_excerpt":"Chinese pre-trained language models usually process text as a sequence of characters, while ignoring more coarse granularity, e.g., words. In this work, we propose a novel pre-training paradigm for Chinese -- Lattice-BERT, which explicitly incorporates word representations along with characters, thus can model a sentence in a multi-granularity manner. Specifically, we construct a lattice graph from the characters and words in a sentence and feed all these text units into transformers. We design a lattice position attention mechanism to exploit the lattice structures in self-attention layers. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07204","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/2104.07204/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":"2026-07-05T02:44:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FDaCU88HHoYp7+ilg5LAexhSagPPpRzKDqKY6XKI27NMAI0Osx40mjWsrPZGuq/GaVnu5yVw2FstZJOYTNQNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:43:54.096309Z"},"content_sha256":"6da3e17b228eab7b0ab9ee6a999b9faca6021a5c8573a27dfcac87e7df7890a6","schema_version":"1.0","event_id":"sha256:6da3e17b228eab7b0ab9ee6a999b9faca6021a5c8573a27dfcac87e7df7890a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WQOEH5XCFFV2MB5G3CZSWH5VJY/bundle.json","state_url":"https://pith.science/pith/WQOEH5XCFFV2MB5G3CZSWH5VJY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WQOEH5XCFFV2MB5G3CZSWH5VJY/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":"2026-08-09T16:43:54Z","links":{"resolver":"https://pith.science/pith/WQOEH5XCFFV2MB5G3CZSWH5VJY","bundle":"https://pith.science/pith/WQOEH5XCFFV2MB5G3CZSWH5VJY/bundle.json","state":"https://pith.science/pith/WQOEH5XCFFV2MB5G3CZSWH5VJY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WQOEH5XCFFV2MB5G3CZSWH5VJY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WQOEH5XCFFV2MB5G3CZSWH5VJY","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":"81db396b647758de63e23a26f953932e9c81c6da463267f6abb9c7dd9b43b293","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-15T02:36:49Z","title_canon_sha256":"724d8912a58f7465421e049196c52ccd655cb0feeb5eade8e12586613286668c"},"schema_version":"1.0","source":{"id":"2104.07204","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.07204","created_at":"2026-07-05T02:44:06Z"},{"alias_kind":"arxiv_version","alias_value":"2104.07204v2","created_at":"2026-07-05T02:44:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07204","created_at":"2026-07-05T02:44:06Z"},{"alias_kind":"pith_short_12","alias_value":"WQOEH5XCFFV2","created_at":"2026-07-05T02:44:06Z"},{"alias_kind":"pith_short_16","alias_value":"WQOEH5XCFFV2MB5G","created_at":"2026-07-05T02:44:06Z"},{"alias_kind":"pith_short_8","alias_value":"WQOEH5XC","created_at":"2026-07-05T02:44:06Z"}],"graph_snapshots":[{"event_id":"sha256:6da3e17b228eab7b0ab9ee6a999b9faca6021a5c8573a27dfcac87e7df7890a6","target":"graph","created_at":"2026-07-05T02:44:06Z","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/2104.07204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chinese pre-trained language models usually process text as a sequence of characters, while ignoring more coarse granularity, e.g., words. In this work, we propose a novel pre-training paradigm for Chinese -- Lattice-BERT, which explicitly incorporates word representations along with characters, thus can model a sentence in a multi-granularity manner. Specifically, we construct a lattice graph from the characters and words in a sentence and feed all these text units into transformers. We design a lattice position attention mechanism to exploit the lattice structures in self-attention layers. W","authors_text":"Dongyan Zhao, Songfang Huang, Yansong Feng, Yijia Liu, Yuxuan Lai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-15T02:36:49Z","title":"Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07204","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":"sha256:13ba847ab673d5d00a89ebcc8db768dc1d0eacd3749fbd7cb431bac6e01b318d","target":"record","created_at":"2026-07-05T02:44:06Z","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":"81db396b647758de63e23a26f953932e9c81c6da463267f6abb9c7dd9b43b293","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-15T02:36:49Z","title_canon_sha256":"724d8912a58f7465421e049196c52ccd655cb0feeb5eade8e12586613286668c"},"schema_version":"1.0","source":{"id":"2104.07204","kind":"arxiv","version":2}},"canonical_sha256":"b41c43f6e2296ba607a6d8b32b1fb54e267a69b3a60f63e5d326bef7a7f7d0ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b41c43f6e2296ba607a6d8b32b1fb54e267a69b3a60f63e5d326bef7a7f7d0ff","first_computed_at":"2026-07-05T02:44:06.153409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:44:06.153409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JXR8THu6sfDsvdYScigEVy7Fs5I2F4CIXva48tfkpcUhaeM9kW/m/XaWI05nv9pw++j8+xG+Qe9khSsTHETZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:44:06.153845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.07204","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13ba847ab673d5d00a89ebcc8db768dc1d0eacd3749fbd7cb431bac6e01b318d","sha256:6da3e17b228eab7b0ab9ee6a999b9faca6021a5c8573a27dfcac87e7df7890a6"],"state_sha256":"f40f6bdf66bae0a048e26b408a0eeaeba2aae309ccf1c168ac2a0e8d40b62626"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ud/mH2t7eHiGWSW7V32uPvZlrlNYDt0basCVpcAoqqtHTMFgQvPMXxKU9RsihkfOq9Pz6YXbd7EopSCpnEWnCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T16:43:54.102073Z","bundle_sha256":"05eaa26d99a49834bb9dd995f9982cf20f38c06ab3121e634e64f62acb8c1cc9"}}