{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3IXZN4AVGNKFZCTFUAEEP27Z2Q","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":"0aea5237cbc828c4f32a0143303395bd5f55b10097ba61c214f3d14c3f054ec9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T06:54:47Z","title_canon_sha256":"9f3f5368f09d00e34211d7767c0ea990ff7e3a4cadaa78ac333ad8595c5042e4"},"schema_version":"1.0","source":{"id":"2403.08293","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.08293","created_at":"2026-07-05T08:32:38Z"},{"alias_kind":"arxiv_version","alias_value":"2403.08293v3","created_at":"2026-07-05T08:32:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08293","created_at":"2026-07-05T08:32:38Z"},{"alias_kind":"pith_short_12","alias_value":"3IXZN4AVGNKF","created_at":"2026-07-05T08:32:38Z"},{"alias_kind":"pith_short_16","alias_value":"3IXZN4AVGNKFZCTF","created_at":"2026-07-05T08:32:38Z"},{"alias_kind":"pith_short_8","alias_value":"3IXZN4AV","created_at":"2026-07-05T08:32:38Z"}],"graph_snapshots":[{"event_id":"sha256:30f36a1b3b89d16e93cd453834db0e8956df7b2c1e5e876b6f20f4093f83e703","target":"graph","created_at":"2026-07-05T08:32:38Z","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/2403.08293/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A syntactic language model (SLM) incrementally generates a sentence with its syntactic tree in a left-to-right manner. We present Generative Pretrained Structured Transformers (GPST), an unsupervised SLM at scale capable of being pre-trained from scratch on raw texts with high parallelism. GPST circumvents the limitations of previous SLMs such as relying on gold trees and sequential training. It consists of two components, a usual SLM supervised by a uni-directional language modeling loss, and an additional composition model, which induces syntactic parse trees and computes constituent represe","authors_text":"Kewei Tu, Pengyu Ji, Qingyang Zhu, Wei Wu, Xiang Hu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T06:54:47Z","title":"Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08293","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:b06bea5b6205dfa49b3cb5b2447c32d4a4f6b2d593ba3a3e96d0f27bda1891d6","target":"record","created_at":"2026-07-05T08:32:38Z","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":"0aea5237cbc828c4f32a0143303395bd5f55b10097ba61c214f3d14c3f054ec9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T06:54:47Z","title_canon_sha256":"9f3f5368f09d00e34211d7767c0ea990ff7e3a4cadaa78ac333ad8595c5042e4"},"schema_version":"1.0","source":{"id":"2403.08293","kind":"arxiv","version":3}},"canonical_sha256":"da2f96f01533545c8a65a00847ebf9d408a18c2311344309da4701dac2a10f51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da2f96f01533545c8a65a00847ebf9d408a18c2311344309da4701dac2a10f51","first_computed_at":"2026-07-05T08:32:38.365420Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:38.365420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"of3DNeCDvQ5WaJlwStPxhRd+KtvaryRUDzPZrNVX519Y4xTO9pQHS13IcPjMFbabKbFxHgY0ss+t7HmVIBlfBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:38.365943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.08293","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b06bea5b6205dfa49b3cb5b2447c32d4a4f6b2d593ba3a3e96d0f27bda1891d6","sha256:30f36a1b3b89d16e93cd453834db0e8956df7b2c1e5e876b6f20f4093f83e703"],"state_sha256":"dd3abdc94a09606b6049b6c5ecf49cc09960de0e11382688e528008da384a30f"}