{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L6SF66M36VPMB2RWNPXOZDTY3R","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":"20fdf37a1746adaa8a9e8f3e9839e04302dc0684f90bda8e0b58ff300c44d446","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T06:53:36Z","title_canon_sha256":"248741609753405ad20b0111d56a78b8f39fae82e7f506119631d045b2c29123"},"schema_version":"1.0","source":{"id":"2406.16356","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16356","created_at":"2026-07-05T08:35:57Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16356v1","created_at":"2026-07-05T08:35:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16356","created_at":"2026-07-05T08:35:57Z"},{"alias_kind":"pith_short_12","alias_value":"L6SF66M36VPM","created_at":"2026-07-05T08:35:57Z"},{"alias_kind":"pith_short_16","alias_value":"L6SF66M36VPMB2RW","created_at":"2026-07-05T08:35:57Z"},{"alias_kind":"pith_short_8","alias_value":"L6SF66M3","created_at":"2026-07-05T08:35:57Z"}],"graph_snapshots":[{"event_id":"sha256:027c843602edb665f9cd01121664a3951433f52db8266a9f513eaa51f56fe8d4","target":"graph","created_at":"2026-07-05T08:35:57Z","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/2406.16356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction-tuned Large Language Models (LLMs) have achieved remarkable performance across various benchmark tasks. While providing instructions to LLMs for guiding their generations is user-friendly, assessing their instruction-following capabilities is still unclarified due to a lack of evaluation metrics. In this paper, we focus on evaluating the instruction-following ability of LLMs in the context of story-ending generation, which requires diverse and context-specific instructions. We propose an automatic evaluation pipeline that utilizes a machine reading comprehension (MRC) model to dete","authors_text":"Junki Ohmura, Rem Hida, Toshiyuki Sekiya","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T06:53:36Z","title":"Evaluation of Instruction-Following Ability for Large Language Models on Story-Ending Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16356","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:a96e5e2e00f0697e2278977c89c1ae60ddce863ae30cc32ec5c433379d55520b","target":"record","created_at":"2026-07-05T08:35:57Z","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":"20fdf37a1746adaa8a9e8f3e9839e04302dc0684f90bda8e0b58ff300c44d446","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T06:53:36Z","title_canon_sha256":"248741609753405ad20b0111d56a78b8f39fae82e7f506119631d045b2c29123"},"schema_version":"1.0","source":{"id":"2406.16356","kind":"arxiv","version":1}},"canonical_sha256":"5fa45f799bf55ec0ea366beeec8e78dc58406d93e1b2b34272590a384d95c4ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fa45f799bf55ec0ea366beeec8e78dc58406d93e1b2b34272590a384d95c4ac","first_computed_at":"2026-07-05T08:35:57.255807Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:57.255807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k6gnWvzcdz22sYITMH6mqUNKXG9dWmz2fk3EIpfSzX4g9cYWoCgFzYnQcnkpTmg2xQQLhPXKEhhzgH5K+CSVCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:57.256296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.16356","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a96e5e2e00f0697e2278977c89c1ae60ddce863ae30cc32ec5c433379d55520b","sha256:027c843602edb665f9cd01121664a3951433f52db8266a9f513eaa51f56fe8d4"],"state_sha256":"b0fb49d49a6e9a6303e37a19f3152261ccebceb597dea9db8d2b88476d1d77f0"}