{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3IXZN4AVGNKFZCTFUAEEP27Z2Q","short_pith_number":"pith:3IXZN4AV","canonical_record":{"source":{"id":"2403.08293","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T06:54:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9f3f5368f09d00e34211d7767c0ea990ff7e3a4cadaa78ac333ad8595c5042e4","abstract_canon_sha256":"0aea5237cbc828c4f32a0143303395bd5f55b10097ba61c214f3d14c3f054ec9"},"schema_version":"1.0"},"canonical_sha256":"da2f96f01533545c8a65a00847ebf9d408a18c2311344309da4701dac2a10f51","source":{"kind":"arxiv","id":"2403.08293","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3IXZN4AVGNKFZCTFUAEEP27Z2Q","target":"record","payload":{"canonical_record":{"source":{"id":"2403.08293","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T06:54:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9f3f5368f09d00e34211d7767c0ea990ff7e3a4cadaa78ac333ad8595c5042e4","abstract_canon_sha256":"0aea5237cbc828c4f32a0143303395bd5f55b10097ba61c214f3d14c3f054ec9"},"schema_version":"1.0"},"canonical_sha256":"da2f96f01533545c8a65a00847ebf9d408a18c2311344309da4701dac2a10f51","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:38.365943Z","signature_b64":"of3DNeCDvQ5WaJlwStPxhRd+KtvaryRUDzPZrNVX519Y4xTO9pQHS13IcPjMFbabKbFxHgY0ss+t7HmVIBlfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da2f96f01533545c8a65a00847ebf9d408a18c2311344309da4701dac2a10f51","last_reissued_at":"2026-07-05T08:32:38.365420Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:38.365420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.08293","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":"2026-07-05T08:32:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DjxP9MbebGfmH9j5uvUqPzmBva41MHe+EMdI12f+9/ruPErvYi7esgU4A8pRC6EtmzcEWwYfXWnhUsQ6hAj2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T03:54:15.229734Z"},"content_sha256":"b06bea5b6205dfa49b3cb5b2447c32d4a4f6b2d593ba3a3e96d0f27bda1891d6","schema_version":"1.0","event_id":"sha256:b06bea5b6205dfa49b3cb5b2447c32d4a4f6b2d593ba3a3e96d0f27bda1891d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3IXZN4AVGNKFZCTFUAEEP27Z2Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kewei Tu, Pengyu Ji, Qingyang Zhu, Wei Wu, Xiang Hu","submitted_at":"2024-03-13T06:54:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08293","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/2403.08293/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":"2026-07-05T08:32:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6yIHJ2Cv3wkzrwSgdU/KpdNOfh0Kwz+H1BO9sFJvg0PMGGIzK7j7VBQtkhARGZ1hO08Nr1MC8ymoaVdG+jdZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T03:54:15.230109Z"},"content_sha256":"30f36a1b3b89d16e93cd453834db0e8956df7b2c1e5e876b6f20f4093f83e703","schema_version":"1.0","event_id":"sha256:30f36a1b3b89d16e93cd453834db0e8956df7b2c1e5e876b6f20f4093f83e703"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3IXZN4AVGNKFZCTFUAEEP27Z2Q/bundle.json","state_url":"https://pith.science/pith/3IXZN4AVGNKFZCTFUAEEP27Z2Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3IXZN4AVGNKFZCTFUAEEP27Z2Q/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":"2026-08-20T03:54:15Z","links":{"resolver":"https://pith.science/pith/3IXZN4AVGNKFZCTFUAEEP27Z2Q","bundle":"https://pith.science/pith/3IXZN4AVGNKFZCTFUAEEP27Z2Q/bundle.json","state":"https://pith.science/pith/3IXZN4AVGNKFZCTFUAEEP27Z2Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3IXZN4AVGNKFZCTFUAEEP27Z2Q/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"731RuYq7NUVlUnM5J0Jn/Cm8TzkhNXAFd/m+rPJuT4+JxeMTepd6Qi0GKsPRlHxgFtjKQoGzlYfJtCq4lVjQCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T03:54:15.232456Z","bundle_sha256":"b12970b56f7016a91fa89e0cc4089c1a915c298ae27be644e94ebe356d5caaf5"}}