{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4BUYPJOGK3YVYCP6PJMMV4E46Y","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":"4d740c07cad912c1e38eee211c458c2853966524eda178a448d1bb6559202560","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T15:04:00Z","title_canon_sha256":"bd85814fa1804594eb11719048fd0a8063583090691323290124e30b7df4a19d"},"schema_version":"1.0","source":{"id":"2410.02558","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02558","created_at":"2026-07-05T10:44:18Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02558v3","created_at":"2026-07-05T10:44:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02558","created_at":"2026-07-05T10:44:18Z"},{"alias_kind":"pith_short_12","alias_value":"4BUYPJOGK3YV","created_at":"2026-07-05T10:44:18Z"},{"alias_kind":"pith_short_16","alias_value":"4BUYPJOGK3YVYCP6","created_at":"2026-07-05T10:44:18Z"},{"alias_kind":"pith_short_8","alias_value":"4BUYPJOG","created_at":"2026-07-05T10:44:18Z"}],"graph_snapshots":[{"event_id":"sha256:11b072242c673d598837488b8445518d5c9573c7043f8ef79293047d7ea543e3","target":"graph","created_at":"2026-07-05T10:44:18Z","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/2410.02558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised constituency parsers organize phrases within a sentence into a tree-shaped syntactic constituent structure that reflects the organization of sentence semantics. However, the traditional objective of maximizing sentence log-likelihood (LL) does not explicitly account for the close relationship between the constituent structure and the semantics, resulting in a weak correlation between LL values and parsing accuracy. In this paper, we introduce a novel objective that trains parsers by maximizing SemInfo, the semantic information encoded in constituent structures. We introduce a bag-","authors_text":"Danushka Bollegala, Junjie Chen, Xiangheng He, Yusuke Miyao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T15:04:00Z","title":"Improving Unsupervised Constituency Parsing via Maximizing Semantic Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02558","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:e6098f58abf466de8362ac1dccf157d6652eb34574f726d6d533063afbd6b284","target":"record","created_at":"2026-07-05T10:44:18Z","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":"4d740c07cad912c1e38eee211c458c2853966524eda178a448d1bb6559202560","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T15:04:00Z","title_canon_sha256":"bd85814fa1804594eb11719048fd0a8063583090691323290124e30b7df4a19d"},"schema_version":"1.0","source":{"id":"2410.02558","kind":"arxiv","version":3}},"canonical_sha256":"e06987a5c656f15c09fe7a58caf09cf6222c6ce6fe5e4f139fb44885cdb76749","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e06987a5c656f15c09fe7a58caf09cf6222c6ce6fe5e4f139fb44885cdb76749","first_computed_at":"2026-07-05T10:44:18.287714Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:18.287714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"84y4jmXz2F5W+grSjGLiOlxxHvSJqctw0OCX5DxIH4nwEQrmHhMXEvMwVo1CWllKQ5obaS5eEvrKEYDYBIwBCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:18.288201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02558","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6098f58abf466de8362ac1dccf157d6652eb34574f726d6d533063afbd6b284","sha256:11b072242c673d598837488b8445518d5c9573c7043f8ef79293047d7ea543e3"],"state_sha256":"b3c951fcb4f0db3abda81a51c9bb0d1acfd7bd63c711a3495bc42ea9bb4b7402"}