{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:IK5I46TZLPZN2KIAZYLQQR74M6","short_pith_number":"pith:IK5I46TZ","canonical_record":{"source":{"id":"2205.10475","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-21T00:58:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1ca9b7b2406da2b8fa82c4aa29db090aed0c26a0d70de11370977fe8df0bb978","abstract_canon_sha256":"2fcbf60a2c01807c7ef96090290a77fd080cdcb386ae02a96ae33c541fb2cc57"},"schema_version":"1.0"},"canonical_sha256":"42ba8e7a795bf2dd2900ce170847fc6794a568e3d45049aecef770f16db64f7f","source":{"kind":"arxiv","id":"2205.10475","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.10475","created_at":"2026-07-05T05:47:58Z"},{"alias_kind":"arxiv_version","alias_value":"2205.10475v2","created_at":"2026-07-05T05:47:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10475","created_at":"2026-07-05T05:47:58Z"},{"alias_kind":"pith_short_12","alias_value":"IK5I46TZLPZN","created_at":"2026-07-05T05:47:58Z"},{"alias_kind":"pith_short_16","alias_value":"IK5I46TZLPZN2KIA","created_at":"2026-07-05T05:47:58Z"},{"alias_kind":"pith_short_8","alias_value":"IK5I46TZ","created_at":"2026-07-05T05:47:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:IK5I46TZLPZN2KIAZYLQQR74M6","target":"record","payload":{"canonical_record":{"source":{"id":"2205.10475","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-21T00:58:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1ca9b7b2406da2b8fa82c4aa29db090aed0c26a0d70de11370977fe8df0bb978","abstract_canon_sha256":"2fcbf60a2c01807c7ef96090290a77fd080cdcb386ae02a96ae33c541fb2cc57"},"schema_version":"1.0"},"canonical_sha256":"42ba8e7a795bf2dd2900ce170847fc6794a568e3d45049aecef770f16db64f7f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:58.794097Z","signature_b64":"yQOuoZ6kohqs1qJCXpYcqNfrMwAsOLqV2UAVCyaIIm6VYFkCXSgsPttMUdWlgMhPjvqiQqf6u9rwI6UrVQknCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42ba8e7a795bf2dd2900ce170847fc6794a568e3d45049aecef770f16db64f7f","last_reissued_at":"2026-07-05T05:47:58.793540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:58.793540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.10475","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":"2026-07-05T05:47:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GRLq95HGbwRJTR5ZGej9zmBQy0efhZ4ss+Sw7JB5gsO4hs9gpR9cryPatLrnJBUvtG7fUjrUivhrkYgsix1xBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:46:35.845979Z"},"content_sha256":"562245cf5c23c9d717fa21081a3aa2f12038790ee52ef501ce931699bee80daa","schema_version":"1.0","event_id":"sha256:562245cf5c23c9d717fa21081a3aa2f12038790ee52ef501ce931699bee80daa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:IK5I46TZLPZN2KIAZYLQQR74M6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeepStruct: Pretraining of Language Models for Structure Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenguang Wang, Dawn Song, Haoyun Hong, Jie Tang, Xiao Liu, Zui Chen","submitted_at":"2022-05-21T00:58:22Z","abstract_excerpt":"We introduce a method for improving the structural understanding abilities of language models. Unlike previous approaches that finetune the models with task-specific augmentation, we pretrain language models on a collection of task-agnostic corpora to generate structures from text. Our structure pretraining enables zero-shot transfer of the learned knowledge that models have about the structure tasks. We study the performance of this approach on 28 datasets, spanning 10 structure prediction tasks including open information extraction, joint entity and relation extraction, named entity recognit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10475","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/2205.10475/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":"2026-07-05T05:47:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sCrIQQBug9H76dial5ClMg+SMymSPY2N7lNqeYM3k7FHQIHdnGzhLdWPVEg9hNwqaBJ0dx1gOEu+dbXUEnm3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:46:35.846444Z"},"content_sha256":"9bccc5614803d8a0761e4da9a98ea6688081e76850edd4fc3eb49f57ff2db80e","schema_version":"1.0","event_id":"sha256:9bccc5614803d8a0761e4da9a98ea6688081e76850edd4fc3eb49f57ff2db80e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IK5I46TZLPZN2KIAZYLQQR74M6/bundle.json","state_url":"https://pith.science/pith/IK5I46TZLPZN2KIAZYLQQR74M6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IK5I46TZLPZN2KIAZYLQQR74M6/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":"2026-08-06T11:46:35Z","links":{"resolver":"https://pith.science/pith/IK5I46TZLPZN2KIAZYLQQR74M6","bundle":"https://pith.science/pith/IK5I46TZLPZN2KIAZYLQQR74M6/bundle.json","state":"https://pith.science/pith/IK5I46TZLPZN2KIAZYLQQR74M6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IK5I46TZLPZN2KIAZYLQQR74M6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IK5I46TZLPZN2KIAZYLQQR74M6","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":"2fcbf60a2c01807c7ef96090290a77fd080cdcb386ae02a96ae33c541fb2cc57","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-21T00:58:22Z","title_canon_sha256":"1ca9b7b2406da2b8fa82c4aa29db090aed0c26a0d70de11370977fe8df0bb978"},"schema_version":"1.0","source":{"id":"2205.10475","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.10475","created_at":"2026-07-05T05:47:58Z"},{"alias_kind":"arxiv_version","alias_value":"2205.10475v2","created_at":"2026-07-05T05:47:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10475","created_at":"2026-07-05T05:47:58Z"},{"alias_kind":"pith_short_12","alias_value":"IK5I46TZLPZN","created_at":"2026-07-05T05:47:58Z"},{"alias_kind":"pith_short_16","alias_value":"IK5I46TZLPZN2KIA","created_at":"2026-07-05T05:47:58Z"},{"alias_kind":"pith_short_8","alias_value":"IK5I46TZ","created_at":"2026-07-05T05:47:58Z"}],"graph_snapshots":[{"event_id":"sha256:9bccc5614803d8a0761e4da9a98ea6688081e76850edd4fc3eb49f57ff2db80e","target":"graph","created_at":"2026-07-05T05:47:58Z","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/2205.10475/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a method for improving the structural understanding abilities of language models. Unlike previous approaches that finetune the models with task-specific augmentation, we pretrain language models on a collection of task-agnostic corpora to generate structures from text. Our structure pretraining enables zero-shot transfer of the learned knowledge that models have about the structure tasks. We study the performance of this approach on 28 datasets, spanning 10 structure prediction tasks including open information extraction, joint entity and relation extraction, named entity recognit","authors_text":"Chenguang Wang, Dawn Song, Haoyun Hong, Jie Tang, Xiao Liu, Zui Chen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-21T00:58:22Z","title":"DeepStruct: Pretraining of Language Models for Structure Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10475","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":"sha256:562245cf5c23c9d717fa21081a3aa2f12038790ee52ef501ce931699bee80daa","target":"record","created_at":"2026-07-05T05:47:58Z","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":"2fcbf60a2c01807c7ef96090290a77fd080cdcb386ae02a96ae33c541fb2cc57","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-21T00:58:22Z","title_canon_sha256":"1ca9b7b2406da2b8fa82c4aa29db090aed0c26a0d70de11370977fe8df0bb978"},"schema_version":"1.0","source":{"id":"2205.10475","kind":"arxiv","version":2}},"canonical_sha256":"42ba8e7a795bf2dd2900ce170847fc6794a568e3d45049aecef770f16db64f7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42ba8e7a795bf2dd2900ce170847fc6794a568e3d45049aecef770f16db64f7f","first_computed_at":"2026-07-05T05:47:58.793540Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:58.793540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yQOuoZ6kohqs1qJCXpYcqNfrMwAsOLqV2UAVCyaIIm6VYFkCXSgsPttMUdWlgMhPjvqiQqf6u9rwI6UrVQknCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:58.794097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.10475","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:562245cf5c23c9d717fa21081a3aa2f12038790ee52ef501ce931699bee80daa","sha256:9bccc5614803d8a0761e4da9a98ea6688081e76850edd4fc3eb49f57ff2db80e"],"state_sha256":"56d58f53ffe44729b900b94d8ffdae731424fef44bb452b6f05a26c2340f7faf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Brcrlh+wsoJbylgxJXk4taTWy9JoLaw0ymXKmXPAsoPEthTxgm7cTjT0kiDVB2aSNxVi/XhEfDEgPo6DxabDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T11:46:35.850950Z","bundle_sha256":"ac2e6ea0a3cde3fc2b26a3b765e063e70ab7d40627fcf42e92e36d545ca9ee98"}}