{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GU6OWWMIGQ5BNDQUWCJ3O5N2ME","short_pith_number":"pith:GU6OWWMI","canonical_record":{"source":{"id":"2011.09159","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-18T08:52:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e45c45d29ddbd54e065e6856262f50e948bf7d0893375d6ca41671f68049769f","abstract_canon_sha256":"1fb2626428eb4514ae66abfa9b8e35377b0553c81c3a057862e216b7edcf8c8c"},"schema_version":"1.0"},"canonical_sha256":"353ceb5988343a168e14b093b775ba6110c695c9040940343ffac91b95eb4a8c","source":{"kind":"arxiv","id":"2011.09159","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.09159","created_at":"2026-07-05T01:52:41Z"},{"alias_kind":"arxiv_version","alias_value":"2011.09159v1","created_at":"2026-07-05T01:52:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09159","created_at":"2026-07-05T01:52:41Z"},{"alias_kind":"pith_short_12","alias_value":"GU6OWWMIGQ5B","created_at":"2026-07-05T01:52:41Z"},{"alias_kind":"pith_short_16","alias_value":"GU6OWWMIGQ5BNDQU","created_at":"2026-07-05T01:52:41Z"},{"alias_kind":"pith_short_8","alias_value":"GU6OWWMI","created_at":"2026-07-05T01:52:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GU6OWWMIGQ5BNDQUWCJ3O5N2ME","target":"record","payload":{"canonical_record":{"source":{"id":"2011.09159","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-18T08:52:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e45c45d29ddbd54e065e6856262f50e948bf7d0893375d6ca41671f68049769f","abstract_canon_sha256":"1fb2626428eb4514ae66abfa9b8e35377b0553c81c3a057862e216b7edcf8c8c"},"schema_version":"1.0"},"canonical_sha256":"353ceb5988343a168e14b093b775ba6110c695c9040940343ffac91b95eb4a8c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:52:41.181962Z","signature_b64":"L+sQBAmcOg3HuKh9LjxsdaFFLq+IbmOxsANfi6WwbI/629p6aq9GStlEwo/eoAQu326zT0EdSRXdCeOwA3E4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"353ceb5988343a168e14b093b775ba6110c695c9040940343ffac91b95eb4a8c","last_reissued_at":"2026-07-05T01:52:41.181611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:52:41.181611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.09159","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":"2026-07-05T01:52:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2mt1c4lEOtVcW1FT0doCReQeFz19PYQhXI+0qvSedw+M0MmGBZypefH7h1YU8DTm2lMUrd+inUZ4JI1e7MW0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:39:02.246896Z"},"content_sha256":"70451c6a841b100a395942349f5bbce4515e69378842591ced670bcaa6cb7c27","schema_version":"1.0","event_id":"sha256:70451c6a841b100a395942349f5bbce4515e69378842591ced670bcaa6cb7c27"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GU6OWWMIGQ5BNDQUWCJ3O5N2ME","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Fine-tuned Commonsense Language Models Really Generalize?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ke Shen, Mayank Kejriwal","submitted_at":"2020-11-18T08:52:49Z","abstract_excerpt":"Recently, transformer-based methods such as RoBERTa and GPT-3 have led to significant experimental advances in natural language processing tasks such as question answering and commonsense reasoning. The latter is typically evaluated through multiple benchmarks framed as multiple-choice instances of the former. According to influential leaderboards hosted by the Allen Institute (evaluating state-of-the-art performance on commonsense reasoning benchmarks), models based on such transformer methods are approaching human-like performance and have average accuracy well over 80% on many benchmarks. S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09159","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/2011.09159/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":"2026-07-05T01:52:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HQmX624gepBYfa/ld0qdGqiPU4BfieM6gP20FqhkVWMkdOlBd5ts66qBzhXleEfuurB9ApC3KwHKz1ihoCTDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:39:02.247283Z"},"content_sha256":"ba3bfae81bb0f0c76bafaffdc112673b8b9d940a692df0f7317802f6d116dce1","schema_version":"1.0","event_id":"sha256:ba3bfae81bb0f0c76bafaffdc112673b8b9d940a692df0f7317802f6d116dce1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GU6OWWMIGQ5BNDQUWCJ3O5N2ME/bundle.json","state_url":"https://pith.science/pith/GU6OWWMIGQ5BNDQUWCJ3O5N2ME/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GU6OWWMIGQ5BNDQUWCJ3O5N2ME/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":"2026-08-03T22:39:02Z","links":{"resolver":"https://pith.science/pith/GU6OWWMIGQ5BNDQUWCJ3O5N2ME","bundle":"https://pith.science/pith/GU6OWWMIGQ5BNDQUWCJ3O5N2ME/bundle.json","state":"https://pith.science/pith/GU6OWWMIGQ5BNDQUWCJ3O5N2ME/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GU6OWWMIGQ5BNDQUWCJ3O5N2ME/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GU6OWWMIGQ5BNDQUWCJ3O5N2ME","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":"1fb2626428eb4514ae66abfa9b8e35377b0553c81c3a057862e216b7edcf8c8c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-18T08:52:49Z","title_canon_sha256":"e45c45d29ddbd54e065e6856262f50e948bf7d0893375d6ca41671f68049769f"},"schema_version":"1.0","source":{"id":"2011.09159","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.09159","created_at":"2026-07-05T01:52:41Z"},{"alias_kind":"arxiv_version","alias_value":"2011.09159v1","created_at":"2026-07-05T01:52:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09159","created_at":"2026-07-05T01:52:41Z"},{"alias_kind":"pith_short_12","alias_value":"GU6OWWMIGQ5B","created_at":"2026-07-05T01:52:41Z"},{"alias_kind":"pith_short_16","alias_value":"GU6OWWMIGQ5BNDQU","created_at":"2026-07-05T01:52:41Z"},{"alias_kind":"pith_short_8","alias_value":"GU6OWWMI","created_at":"2026-07-05T01:52:41Z"}],"graph_snapshots":[{"event_id":"sha256:ba3bfae81bb0f0c76bafaffdc112673b8b9d940a692df0f7317802f6d116dce1","target":"graph","created_at":"2026-07-05T01:52:41Z","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/2011.09159/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, transformer-based methods such as RoBERTa and GPT-3 have led to significant experimental advances in natural language processing tasks such as question answering and commonsense reasoning. The latter is typically evaluated through multiple benchmarks framed as multiple-choice instances of the former. According to influential leaderboards hosted by the Allen Institute (evaluating state-of-the-art performance on commonsense reasoning benchmarks), models based on such transformer methods are approaching human-like performance and have average accuracy well over 80% on many benchmarks. S","authors_text":"Ke Shen, Mayank Kejriwal","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-18T08:52:49Z","title":"Do Fine-tuned Commonsense Language Models Really Generalize?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09159","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":"sha256:70451c6a841b100a395942349f5bbce4515e69378842591ced670bcaa6cb7c27","target":"record","created_at":"2026-07-05T01:52:41Z","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":"1fb2626428eb4514ae66abfa9b8e35377b0553c81c3a057862e216b7edcf8c8c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-18T08:52:49Z","title_canon_sha256":"e45c45d29ddbd54e065e6856262f50e948bf7d0893375d6ca41671f68049769f"},"schema_version":"1.0","source":{"id":"2011.09159","kind":"arxiv","version":1}},"canonical_sha256":"353ceb5988343a168e14b093b775ba6110c695c9040940343ffac91b95eb4a8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"353ceb5988343a168e14b093b775ba6110c695c9040940343ffac91b95eb4a8c","first_computed_at":"2026-07-05T01:52:41.181611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:52:41.181611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L+sQBAmcOg3HuKh9LjxsdaFFLq+IbmOxsANfi6WwbI/629p6aq9GStlEwo/eoAQu326zT0EdSRXdCeOwA3E4BA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:52:41.181962Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.09159","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70451c6a841b100a395942349f5bbce4515e69378842591ced670bcaa6cb7c27","sha256:ba3bfae81bb0f0c76bafaffdc112673b8b9d940a692df0f7317802f6d116dce1"],"state_sha256":"138c93db84fe128ec0739314f8cc53ca9e2c539dabfb6accb0a08463d6e56d24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mKJxDkwDjZu4UilsV0kwDV8plDDCcNaWPqj6FzEFMxLSjs4g4QkI2e/Gt4E1GrK1Rmb0a3W7PEgRH61xYFROCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:39:02.249890Z","bundle_sha256":"d52c19caa59aed1a5ed4f525585e4b3ddabb80dadb4dd026dd4b87f324add86b"}}