{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2AXX55FEQS3SNLEBA3M2GN7UZK","short_pith_number":"pith:2AXX55FE","schema_version":"1.0","canonical_sha256":"d02f7ef4a484b726ac8106d9a337f4ca9c5935e660efb56c6f295d540e512ae8","source":{"kind":"arxiv","id":"2305.04522","version":1},"attestation_state":"computed","paper":{"title":"Event Knowledge Incorporation with Posterior Regularization for Event-Centric Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gabriele Pergola, Junru Lu, Lin Gui, Yulan He","submitted_at":"2023-05-08T07:45:12Z","abstract_excerpt":"We propose a simple yet effective strategy to incorporate event knowledge extracted from event trigger annotations via posterior regularization to improve the event reasoning capability of mainstream question-answering (QA) models for event-centric QA. In particular, we define event-related knowledge constraints based on the event trigger annotations in the QA datasets, and subsequently use them to regularize the posterior answer output probabilities from the backbone pre-trained language models used in the QA setting. We explore two different posterior regularization strategies for extractive"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.04522","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-08T07:45:12Z","cross_cats_sorted":[],"title_canon_sha256":"3e724a143b1f9f39e9edeaff2b46eb4dc182e8c85a206a406fd21d6688098e42","abstract_canon_sha256":"444107c1e38a29d3aa508146a796bc7590988f3ac39e41ac7ce9c21543317804"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:50.858404Z","signature_b64":"X+OYNDb6uPfvQpleJB5npuu1k3P0e95LORQjw1dJpBBg8Gs/qLq1uMhG3MQLt4rO2PHEQ59RCbu0+C7b4sGdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d02f7ef4a484b726ac8106d9a337f4ca9c5935e660efb56c6f295d540e512ae8","last_reissued_at":"2026-07-05T06:07:50.857983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:50.857983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Event Knowledge Incorporation with Posterior Regularization for Event-Centric Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gabriele Pergola, Junru Lu, Lin Gui, Yulan He","submitted_at":"2023-05-08T07:45:12Z","abstract_excerpt":"We propose a simple yet effective strategy to incorporate event knowledge extracted from event trigger annotations via posterior regularization to improve the event reasoning capability of mainstream question-answering (QA) models for event-centric QA. In particular, we define event-related knowledge constraints based on the event trigger annotations in the QA datasets, and subsequently use them to regularize the posterior answer output probabilities from the backbone pre-trained language models used in the QA setting. We explore two different posterior regularization strategies for extractive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04522","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.04522/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.04522","created_at":"2026-07-05T06:07:50.858040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.04522v1","created_at":"2026-07-05T06:07:50.858040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04522","created_at":"2026-07-05T06:07:50.858040+00:00"},{"alias_kind":"pith_short_12","alias_value":"2AXX55FEQS3S","created_at":"2026-07-05T06:07:50.858040+00:00"},{"alias_kind":"pith_short_16","alias_value":"2AXX55FEQS3SNLEB","created_at":"2026-07-05T06:07:50.858040+00:00"},{"alias_kind":"pith_short_8","alias_value":"2AXX55FE","created_at":"2026-07-05T06:07:50.858040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08666","citing_title":"LLaVA-c: Continual Improved Visual Instruction Tuning","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2AXX55FEQS3SNLEBA3M2GN7UZK","json":"https://pith.science/pith/2AXX55FEQS3SNLEBA3M2GN7UZK.json","graph_json":"https://pith.science/api/pith-number/2AXX55FEQS3SNLEBA3M2GN7UZK/graph.json","events_json":"https://pith.science/api/pith-number/2AXX55FEQS3SNLEBA3M2GN7UZK/events.json","paper":"https://pith.science/paper/2AXX55FE"},"agent_actions":{"view_html":"https://pith.science/pith/2AXX55FEQS3SNLEBA3M2GN7UZK","download_json":"https://pith.science/pith/2AXX55FEQS3SNLEBA3M2GN7UZK.json","view_paper":"https://pith.science/paper/2AXX55FE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.04522&json=true","fetch_graph":"https://pith.science/api/pith-number/2AXX55FEQS3SNLEBA3M2GN7UZK/graph.json","fetch_events":"https://pith.science/api/pith-number/2AXX55FEQS3SNLEBA3M2GN7UZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2AXX55FEQS3SNLEBA3M2GN7UZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2AXX55FEQS3SNLEBA3M2GN7UZK/action/storage_attestation","attest_author":"https://pith.science/pith/2AXX55FEQS3SNLEBA3M2GN7UZK/action/author_attestation","sign_citation":"https://pith.science/pith/2AXX55FEQS3SNLEBA3M2GN7UZK/action/citation_signature","submit_replication":"https://pith.science/pith/2AXX55FEQS3SNLEBA3M2GN7UZK/action/replication_record"}},"created_at":"2026-07-05T06:07:50.858040+00:00","updated_at":"2026-07-05T06:07:50.858040+00:00"}