{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CYDPQ4D4YY6LIBEFVCCATQ7YXN","short_pith_number":"pith:CYDPQ4D4","canonical_record":{"source":{"id":"2105.05727","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-12T15:20:01Z","cross_cats_sorted":[],"title_canon_sha256":"b0ee9f47515d3daf741b3b6e4e71164e8b91ea44f0276e7b38f8dc7e0d0653c7","abstract_canon_sha256":"4a78bc6c24ef486c7151d33cfc8141e00bf4839d0d0f8d6b0f95be1a6917baf3"},"schema_version":"1.0"},"canonical_sha256":"1606f8707cc63cb40485a88409c3f8bb6abf959a269d467e2d947bbab736e8c5","source":{"kind":"arxiv","id":"2105.05727","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.05727","created_at":"2026-07-05T04:06:42Z"},{"alias_kind":"arxiv_version","alias_value":"2105.05727v4","created_at":"2026-07-05T04:06:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05727","created_at":"2026-07-05T04:06:42Z"},{"alias_kind":"pith_short_12","alias_value":"CYDPQ4D4YY6L","created_at":"2026-07-05T04:06:42Z"},{"alias_kind":"pith_short_16","alias_value":"CYDPQ4D4YY6LIBEF","created_at":"2026-07-05T04:06:42Z"},{"alias_kind":"pith_short_8","alias_value":"CYDPQ4D4","created_at":"2026-07-05T04:06:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CYDPQ4D4YY6LIBEFVCCATQ7YXN","target":"record","payload":{"canonical_record":{"source":{"id":"2105.05727","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-12T15:20:01Z","cross_cats_sorted":[],"title_canon_sha256":"b0ee9f47515d3daf741b3b6e4e71164e8b91ea44f0276e7b38f8dc7e0d0653c7","abstract_canon_sha256":"4a78bc6c24ef486c7151d33cfc8141e00bf4839d0d0f8d6b0f95be1a6917baf3"},"schema_version":"1.0"},"canonical_sha256":"1606f8707cc63cb40485a88409c3f8bb6abf959a269d467e2d947bbab736e8c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:42.058279Z","signature_b64":"7XwM+a4/4nBo4PSLXXoHzz896DzWmH/fKJDcKGHUNHux2zhOBuPk2beTY6LSnesPFjgHqUrvOLWKX06U5BjgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1606f8707cc63cb40485a88409c3f8bb6abf959a269d467e2d947bbab736e8c5","last_reissued_at":"2026-07-05T04:06:42.057825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:42.057825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.05727","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:06:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yC4k5QGGlUxtAKGFf5WDQH79beH+mflU8y1FpTUOeRau/LZHcb7J23lPldN80C3Vhg4ix1+f43Li4JttHuQADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T10:20:50.031533Z"},"content_sha256":"3901424abe040278268749830c10a1ffae4859158ccdb7d775a1005986c34d31","schema_version":"1.0","event_id":"sha256:3901424abe040278268749830c10a1ffae4859158ccdb7d775a1005986c34d31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CYDPQ4D4YY6LIBEFVCCATQ7YXN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BertGCN: Transductive Text Classification by Combining GCN and BERT","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Wu, Jiwei Li, Kun Kuang, Qinghong Han, Xiaofei Sun, Yuxian Meng, Yuxiao Lin","submitted_at":"2021-05-12T15:20:01Z","abstract_excerpt":"In this work, we propose BertGCN, a model that combines large scale pretraining and transductive learning for text classification. BertGCN constructs a heterogeneous graph over the dataset and represents documents as nodes using BERT representations. By jointly training the BERT and GCN modules within BertGCN, the proposed model is able to leverage the advantages of both worlds: large-scale pretraining which takes the advantage of the massive amount of raw data and transductive learning which jointly learns representations for both training data and unlabeled test data by propagating label inf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05727","kind":"arxiv","version":4},"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/2105.05727/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":"2026-07-05T04:06:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ATIRdvaQWsq1uTltcjzeSsjWmBimVdGWx5vnuKPO1XEJd8FPXqkrsyya+h6BWlccEfamtvHEm+RruwYWbd58CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T10:20:50.031906Z"},"content_sha256":"716e23db6b55e13875e8fa2afb0836ba6699ecbcdac54caea6a970cce97898ea","schema_version":"1.0","event_id":"sha256:716e23db6b55e13875e8fa2afb0836ba6699ecbcdac54caea6a970cce97898ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CYDPQ4D4YY6LIBEFVCCATQ7YXN/bundle.json","state_url":"https://pith.science/pith/CYDPQ4D4YY6LIBEFVCCATQ7YXN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CYDPQ4D4YY6LIBEFVCCATQ7YXN/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":"2026-07-18T10:20:50Z","links":{"resolver":"https://pith.science/pith/CYDPQ4D4YY6LIBEFVCCATQ7YXN","bundle":"https://pith.science/pith/CYDPQ4D4YY6LIBEFVCCATQ7YXN/bundle.json","state":"https://pith.science/pith/CYDPQ4D4YY6LIBEFVCCATQ7YXN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CYDPQ4D4YY6LIBEFVCCATQ7YXN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CYDPQ4D4YY6LIBEFVCCATQ7YXN","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":"4a78bc6c24ef486c7151d33cfc8141e00bf4839d0d0f8d6b0f95be1a6917baf3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-12T15:20:01Z","title_canon_sha256":"b0ee9f47515d3daf741b3b6e4e71164e8b91ea44f0276e7b38f8dc7e0d0653c7"},"schema_version":"1.0","source":{"id":"2105.05727","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.05727","created_at":"2026-07-05T04:06:42Z"},{"alias_kind":"arxiv_version","alias_value":"2105.05727v4","created_at":"2026-07-05T04:06:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05727","created_at":"2026-07-05T04:06:42Z"},{"alias_kind":"pith_short_12","alias_value":"CYDPQ4D4YY6L","created_at":"2026-07-05T04:06:42Z"},{"alias_kind":"pith_short_16","alias_value":"CYDPQ4D4YY6LIBEF","created_at":"2026-07-05T04:06:42Z"},{"alias_kind":"pith_short_8","alias_value":"CYDPQ4D4","created_at":"2026-07-05T04:06:42Z"}],"graph_snapshots":[{"event_id":"sha256:716e23db6b55e13875e8fa2afb0836ba6699ecbcdac54caea6a970cce97898ea","target":"graph","created_at":"2026-07-05T04:06:42Z","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/2105.05727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we propose BertGCN, a model that combines large scale pretraining and transductive learning for text classification. BertGCN constructs a heterogeneous graph over the dataset and represents documents as nodes using BERT representations. By jointly training the BERT and GCN modules within BertGCN, the proposed model is able to leverage the advantages of both worlds: large-scale pretraining which takes the advantage of the massive amount of raw data and transductive learning which jointly learns representations for both training data and unlabeled test data by propagating label inf","authors_text":"Fei Wu, Jiwei Li, Kun Kuang, Qinghong Han, Xiaofei Sun, Yuxian Meng, Yuxiao Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-12T15:20:01Z","title":"BertGCN: Transductive Text Classification by Combining GCN and BERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05727","kind":"arxiv","version":4},"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":"sha256:3901424abe040278268749830c10a1ffae4859158ccdb7d775a1005986c34d31","target":"record","created_at":"2026-07-05T04:06:42Z","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":"4a78bc6c24ef486c7151d33cfc8141e00bf4839d0d0f8d6b0f95be1a6917baf3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-12T15:20:01Z","title_canon_sha256":"b0ee9f47515d3daf741b3b6e4e71164e8b91ea44f0276e7b38f8dc7e0d0653c7"},"schema_version":"1.0","source":{"id":"2105.05727","kind":"arxiv","version":4}},"canonical_sha256":"1606f8707cc63cb40485a88409c3f8bb6abf959a269d467e2d947bbab736e8c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1606f8707cc63cb40485a88409c3f8bb6abf959a269d467e2d947bbab736e8c5","first_computed_at":"2026-07-05T04:06:42.057825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:42.057825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7XwM+a4/4nBo4PSLXXoHzz896DzWmH/fKJDcKGHUNHux2zhOBuPk2beTY6LSnesPFjgHqUrvOLWKX06U5BjgCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:42.058279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.05727","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3901424abe040278268749830c10a1ffae4859158ccdb7d775a1005986c34d31","sha256:716e23db6b55e13875e8fa2afb0836ba6699ecbcdac54caea6a970cce97898ea"],"state_sha256":"114b2890fcb881a6bcd51d43fe457ae8bc1b14a2eb08662068087bbdd32d6f2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p7vBrA5PKXJtrgoYHgXZ0oDRwZplAwUY8JXX9ZLOT4eg3KnTIa2dCIv4+qqp6yDcI9qflcMepFYy7791J3FCBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T10:20:50.033925Z","bundle_sha256":"6999ec017b04101124dbdd76c3fa633bcc4e52fd80833edb7b98903c8096a372"}}