{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:AZP6DGEYJMELXUATPXUI5ZKCM2","short_pith_number":"pith:AZP6DGEY","canonical_record":{"source":{"id":"1505.04420","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-05-17T17:26:36Z","cross_cats_sorted":[],"title_canon_sha256":"ba93e90cec5f9a212815c5ecaae1edf62651d3f9ded671893af36f0528b80d90","abstract_canon_sha256":"8a7e3cd232e64273cf4741c4fea0eb7f5bd6f029af26b2abe35a5493be08245c"},"schema_version":"1.0"},"canonical_sha256":"065fe198984b08bbd0137de88ee54266b24b8387749b47e9051dd4d32f00a1a0","source":{"kind":"arxiv","id":"1505.04420","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.04420","created_at":"2026-05-18T02:07:25Z"},{"alias_kind":"arxiv_version","alias_value":"1505.04420v1","created_at":"2026-05-18T02:07:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.04420","created_at":"2026-05-18T02:07:25Z"},{"alias_kind":"pith_short_12","alias_value":"AZP6DGEYJMEL","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"AZP6DGEYJMELXUAT","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"AZP6DGEY","created_at":"2026-05-18T12:29:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:AZP6DGEYJMELXUATPXUI5ZKCM2","target":"record","payload":{"canonical_record":{"source":{"id":"1505.04420","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-05-17T17:26:36Z","cross_cats_sorted":[],"title_canon_sha256":"ba93e90cec5f9a212815c5ecaae1edf62651d3f9ded671893af36f0528b80d90","abstract_canon_sha256":"8a7e3cd232e64273cf4741c4fea0eb7f5bd6f029af26b2abe35a5493be08245c"},"schema_version":"1.0"},"canonical_sha256":"065fe198984b08bbd0137de88ee54266b24b8387749b47e9051dd4d32f00a1a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:07:25.476614Z","signature_b64":"OZM4rv2V4GY1exDt1Kkdc/yPJuKcjBnAos91fvFMPheNBfchUIw5Mrz9A858zgtNms07dMxVEL/O5zhSWSpUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"065fe198984b08bbd0137de88ee54266b24b8387749b47e9051dd4d32f00a1a0","last_reissued_at":"2026-05-18T02:07:25.476156Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:07:25.476156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1505.04420","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:07:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aLcY2zS81n40YaMcy52I7tw1rPiKlHzFDQiELsmGF94ZRnGwsyDOAlSICkBnvtTDgjGKXPXD871OEy/WDRymCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T17:52:19.978573Z"},"content_sha256":"0cd4ff572d6a6597fa9200a24282c99dd6a6049b42f67c6d242a4e29174519a2","schema_version":"1.0","event_id":"sha256:0cd4ff572d6a6597fa9200a24282c99dd6a6049b42f67c6d242a4e29174519a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:AZP6DGEYJMELXUATPXUI5ZKCM2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CCG Parsing and Multiword Expressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Miryam de Lhoneux","submitted_at":"2015-05-17T17:26:36Z","abstract_excerpt":"This thesis presents a study about the integration of information about Multiword Expressions (MWEs) into parsing with Combinatory Categorial Grammar (CCG). We build on previous work which has shown the benefit of adding information about MWEs to syntactic parsing by implementing a similar pipeline with CCG parsing. More specifically, we collapse MWEs to one token in training and test data in CCGbank, a corpus which contains sentences annotated with CCG derivations. Our collapsing algorithm however can only deal with MWEs when they form a constituent in the data which is one of the limitations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.04420","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T02:07:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K4mo+mZw94jhstX/dgnJaK/YyHKCxdzU3/CK8t9kF9Ts0oTej/Jf7qbKajIKvLYrP4dXa7iiU0slffGkBEHyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T17:52:19.978966Z"},"content_sha256":"e1682c9f6e8db651f606fdc7905024ebeeea4789d5fce3783a7414df789d5ef1","schema_version":"1.0","event_id":"sha256:e1682c9f6e8db651f606fdc7905024ebeeea4789d5fce3783a7414df789d5ef1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZP6DGEYJMELXUATPXUI5ZKCM2/bundle.json","state_url":"https://pith.science/pith/AZP6DGEYJMELXUATPXUI5ZKCM2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZP6DGEYJMELXUATPXUI5ZKCM2/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":"2026-06-08T17:52:19Z","links":{"resolver":"https://pith.science/pith/AZP6DGEYJMELXUATPXUI5ZKCM2","bundle":"https://pith.science/pith/AZP6DGEYJMELXUATPXUI5ZKCM2/bundle.json","state":"https://pith.science/pith/AZP6DGEYJMELXUATPXUI5ZKCM2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZP6DGEYJMELXUATPXUI5ZKCM2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:AZP6DGEYJMELXUATPXUI5ZKCM2","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":"8a7e3cd232e64273cf4741c4fea0eb7f5bd6f029af26b2abe35a5493be08245c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-05-17T17:26:36Z","title_canon_sha256":"ba93e90cec5f9a212815c5ecaae1edf62651d3f9ded671893af36f0528b80d90"},"schema_version":"1.0","source":{"id":"1505.04420","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.04420","created_at":"2026-05-18T02:07:25Z"},{"alias_kind":"arxiv_version","alias_value":"1505.04420v1","created_at":"2026-05-18T02:07:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.04420","created_at":"2026-05-18T02:07:25Z"},{"alias_kind":"pith_short_12","alias_value":"AZP6DGEYJMEL","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"AZP6DGEYJMELXUAT","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"AZP6DGEY","created_at":"2026-05-18T12:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:e1682c9f6e8db651f606fdc7905024ebeeea4789d5fce3783a7414df789d5ef1","target":"graph","created_at":"2026-05-18T02:07:25Z","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"},"paper":{"abstract_excerpt":"This thesis presents a study about the integration of information about Multiword Expressions (MWEs) into parsing with Combinatory Categorial Grammar (CCG). We build on previous work which has shown the benefit of adding information about MWEs to syntactic parsing by implementing a similar pipeline with CCG parsing. More specifically, we collapse MWEs to one token in training and test data in CCGbank, a corpus which contains sentences annotated with CCG derivations. Our collapsing algorithm however can only deal with MWEs when they form a constituent in the data which is one of the limitations","authors_text":"Miryam de Lhoneux","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-05-17T17:26:36Z","title":"CCG Parsing and Multiword Expressions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.04420","kind":"arxiv","version":1},"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":"sha256:0cd4ff572d6a6597fa9200a24282c99dd6a6049b42f67c6d242a4e29174519a2","target":"record","created_at":"2026-05-18T02:07:25Z","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":"8a7e3cd232e64273cf4741c4fea0eb7f5bd6f029af26b2abe35a5493be08245c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-05-17T17:26:36Z","title_canon_sha256":"ba93e90cec5f9a212815c5ecaae1edf62651d3f9ded671893af36f0528b80d90"},"schema_version":"1.0","source":{"id":"1505.04420","kind":"arxiv","version":1}},"canonical_sha256":"065fe198984b08bbd0137de88ee54266b24b8387749b47e9051dd4d32f00a1a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"065fe198984b08bbd0137de88ee54266b24b8387749b47e9051dd4d32f00a1a0","first_computed_at":"2026-05-18T02:07:25.476156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:07:25.476156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OZM4rv2V4GY1exDt1Kkdc/yPJuKcjBnAos91fvFMPheNBfchUIw5Mrz9A858zgtNms07dMxVEL/O5zhSWSpUCA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:07:25.476614Z","signed_message":"canonical_sha256_bytes"},"source_id":"1505.04420","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cd4ff572d6a6597fa9200a24282c99dd6a6049b42f67c6d242a4e29174519a2","sha256:e1682c9f6e8db651f606fdc7905024ebeeea4789d5fce3783a7414df789d5ef1"],"state_sha256":"4917b64738de68a3af0a4368ce6bfb6dede0cdfa360c7893e283e276fb7463d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U8TUQb97qEiJfrU9VxCl2inwd3NNBofN2qBVhSG+UcUAxS0RxzeuyWknLcrwJ01znTtIatQuywpMUUc2ApGZBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T17:52:19.982280Z","bundle_sha256":"cd240fae0c1ad006d5690ab7d4469e6d7fdcb48bb615ef7f73e421c9d7a64a8b"}}