{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WRTKN46KDBPT2AN3URSEUBPGNS","short_pith_number":"pith:WRTKN46K","canonical_record":{"source":{"id":"2502.11393","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T03:24:02Z","cross_cats_sorted":[],"title_canon_sha256":"9f6f41108da71d04fdab91a19ae8bdfc5aa1a4d333c3ac352c023c595c73e326","abstract_canon_sha256":"56fb27aca9e15334a1a0fb9fd10b07dac05ebe3de19b2570a929be3fe929cef9"},"schema_version":"1.0"},"canonical_sha256":"b466a6f3ca185f3d01bba4644a05e66cae392a6c7144bd7e59bf3fe60a969875","source":{"kind":"arxiv","id":"2502.11393","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11393","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11393v2","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11393","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"WRTKN46KDBPT","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_16","alias_value":"WRTKN46KDBPT2AN3","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_8","alias_value":"WRTKN46K","created_at":"2026-07-05T11:09:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WRTKN46KDBPT2AN3URSEUBPGNS","target":"record","payload":{"canonical_record":{"source":{"id":"2502.11393","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T03:24:02Z","cross_cats_sorted":[],"title_canon_sha256":"9f6f41108da71d04fdab91a19ae8bdfc5aa1a4d333c3ac352c023c595c73e326","abstract_canon_sha256":"56fb27aca9e15334a1a0fb9fd10b07dac05ebe3de19b2570a929be3fe929cef9"},"schema_version":"1.0"},"canonical_sha256":"b466a6f3ca185f3d01bba4644a05e66cae392a6c7144bd7e59bf3fe60a969875","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:08.443551Z","signature_b64":"6n7m4BT87fuDmOnG9ZyXW6bcKBC3E4M1NAvl51W941XlqHJPsJgqA791E8uWeXoucur+tV0XE351ljaxzSQxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b466a6f3ca185f3d01bba4644a05e66cae392a6c7144bd7e59bf3fe60a969875","last_reissued_at":"2026-07-05T11:09:08.443113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:08.443113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.11393","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4SlKEda/ha2c5Es7EDe0c7YqGCMXZZdCiwTh+vHHw+n0WYsTwMC7dQ67p1znTCJhkJC7bPY5+dICAz5CCRmFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:57:49.873553Z"},"content_sha256":"2ab57230167a42a7ad835d97be6db48a1a29250292e8c7ee8f5f9173f53a1202","schema_version":"1.0","event_id":"sha256:2ab57230167a42a7ad835d97be6db48a1a29250292e8c7ee8f5f9173f53a1202"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WRTKN46KDBPT2AN3URSEUBPGNS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dayiheng Liu, Fuli Feng, Junyang Lin, Keqin Bao, Moxin Li, Rui Men, Wenjie Wang, Xiaoyuan Li, Yichang Zhang","submitted_at":"2025-02-17T03:24:02Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable capabilities in commonsense reasoning; however, some variations in questions can trigger incorrect responses. Do these models truly understand commonsense knowledge, or just memorize expression patterns? To investigate this question, we present the first extensive robustness evaluation of LLMs in commonsense reasoning. We introduce HellaSwag-Pro, a large-scale bilingual benchmark consisting of 11,200 cases, by designing and compiling seven types of question variants. To construct this benchmark, we propose a two-stage method to develop Chinese"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11393","kind":"arxiv","version":2},"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/2502.11393/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":"2026-07-05T11:09:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xBtnIRlBqpcZQc2gy0Rl/E4Q8o14rKJTXEtCcXwqj49aXUzgRTaTvAChEIasjU93w6A1ORNZ//JbVMV89mqGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:57:49.874056Z"},"content_sha256":"2d833aae88f5a601fc2388c0fc09ad85f10bc7bdabee1b19c8cee0a736d238f7","schema_version":"1.0","event_id":"sha256:2d833aae88f5a601fc2388c0fc09ad85f10bc7bdabee1b19c8cee0a736d238f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WRTKN46KDBPT2AN3URSEUBPGNS/bundle.json","state_url":"https://pith.science/pith/WRTKN46KDBPT2AN3URSEUBPGNS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WRTKN46KDBPT2AN3URSEUBPGNS/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":"2026-08-08T12:57:49Z","links":{"resolver":"https://pith.science/pith/WRTKN46KDBPT2AN3URSEUBPGNS","bundle":"https://pith.science/pith/WRTKN46KDBPT2AN3URSEUBPGNS/bundle.json","state":"https://pith.science/pith/WRTKN46KDBPT2AN3URSEUBPGNS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WRTKN46KDBPT2AN3URSEUBPGNS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WRTKN46KDBPT2AN3URSEUBPGNS","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":"56fb27aca9e15334a1a0fb9fd10b07dac05ebe3de19b2570a929be3fe929cef9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T03:24:02Z","title_canon_sha256":"9f6f41108da71d04fdab91a19ae8bdfc5aa1a4d333c3ac352c023c595c73e326"},"schema_version":"1.0","source":{"id":"2502.11393","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11393","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11393v2","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11393","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"WRTKN46KDBPT","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_16","alias_value":"WRTKN46KDBPT2AN3","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_8","alias_value":"WRTKN46K","created_at":"2026-07-05T11:09:08Z"}],"graph_snapshots":[{"event_id":"sha256:2d833aae88f5a601fc2388c0fc09ad85f10bc7bdabee1b19c8cee0a736d238f7","target":"graph","created_at":"2026-07-05T11:09:08Z","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/2502.11393/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown remarkable capabilities in commonsense reasoning; however, some variations in questions can trigger incorrect responses. Do these models truly understand commonsense knowledge, or just memorize expression patterns? To investigate this question, we present the first extensive robustness evaluation of LLMs in commonsense reasoning. We introduce HellaSwag-Pro, a large-scale bilingual benchmark consisting of 11,200 cases, by designing and compiling seven types of question variants. To construct this benchmark, we propose a two-stage method to develop Chinese","authors_text":"Dayiheng Liu, Fuli Feng, Junyang Lin, Keqin Bao, Moxin Li, Rui Men, Wenjie Wang, Xiaoyuan Li, Yichang Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T03:24:02Z","title":"HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11393","kind":"arxiv","version":2},"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":"sha256:2ab57230167a42a7ad835d97be6db48a1a29250292e8c7ee8f5f9173f53a1202","target":"record","created_at":"2026-07-05T11:09:08Z","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":"56fb27aca9e15334a1a0fb9fd10b07dac05ebe3de19b2570a929be3fe929cef9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T03:24:02Z","title_canon_sha256":"9f6f41108da71d04fdab91a19ae8bdfc5aa1a4d333c3ac352c023c595c73e326"},"schema_version":"1.0","source":{"id":"2502.11393","kind":"arxiv","version":2}},"canonical_sha256":"b466a6f3ca185f3d01bba4644a05e66cae392a6c7144bd7e59bf3fe60a969875","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b466a6f3ca185f3d01bba4644a05e66cae392a6c7144bd7e59bf3fe60a969875","first_computed_at":"2026-07-05T11:09:08.443113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:08.443113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6n7m4BT87fuDmOnG9ZyXW6bcKBC3E4M1NAvl51W941XlqHJPsJgqA791E8uWeXoucur+tV0XE351ljaxzSQxCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:08.443551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.11393","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ab57230167a42a7ad835d97be6db48a1a29250292e8c7ee8f5f9173f53a1202","sha256:2d833aae88f5a601fc2388c0fc09ad85f10bc7bdabee1b19c8cee0a736d238f7"],"state_sha256":"21bb728e48bf4be8f73c42056ee658c96739001f0542b85019f9767eccbc726b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Hrx5H8u/tn/1U6edCRG3uTR10b53AFLeYhyRCRjUDxyaIv+ruxo/LS00LRZN5hpb8I/hWZP6n1vRZbRLlyWDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:57:49.878567Z","bundle_sha256":"7f805a6a0ae8708a7f228b2588fcd2044e7ae797d3fc1227f998d7251575b878"}}