{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:AFOREMA532YXCSJCDRDFIH5FGA","short_pith_number":"pith:AFOREMA5","canonical_record":{"source":{"id":"2212.08286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-16T05:15:41Z","cross_cats_sorted":[],"title_canon_sha256":"a9b69e13a6f3be0c3900995b69758069ab2714bf12c6384c1b5026f5bef9109c","abstract_canon_sha256":"0904ab2bc284ae85ba3dd1fd5a1736a8a87bfae3656750a8efb132ac4ccf2058"},"schema_version":"1.0"},"canonical_sha256":"015d12301ddeb17149221c46541fa5301fc51e6e0d9922df54e79c10bace044f","source":{"kind":"arxiv","id":"2212.08286","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08286","created_at":"2026-07-05T06:55:38Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08286v2","created_at":"2026-07-05T06:55:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08286","created_at":"2026-07-05T06:55:38Z"},{"alias_kind":"pith_short_12","alias_value":"AFOREMA532YX","created_at":"2026-07-05T06:55:38Z"},{"alias_kind":"pith_short_16","alias_value":"AFOREMA532YXCSJC","created_at":"2026-07-05T06:55:38Z"},{"alias_kind":"pith_short_8","alias_value":"AFOREMA5","created_at":"2026-07-05T06:55:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:AFOREMA532YXCSJCDRDFIH5FGA","target":"record","payload":{"canonical_record":{"source":{"id":"2212.08286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-16T05:15:41Z","cross_cats_sorted":[],"title_canon_sha256":"a9b69e13a6f3be0c3900995b69758069ab2714bf12c6384c1b5026f5bef9109c","abstract_canon_sha256":"0904ab2bc284ae85ba3dd1fd5a1736a8a87bfae3656750a8efb132ac4ccf2058"},"schema_version":"1.0"},"canonical_sha256":"015d12301ddeb17149221c46541fa5301fc51e6e0d9922df54e79c10bace044f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:38.543619Z","signature_b64":"IodhvRxVekwzu2+PT6JAOC1SsCeixPJuXjrcRbvAdpp4uuArtXmkwRrbNL7JZLZR0FCvBKb4kgoP5hXqtktFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"015d12301ddeb17149221c46541fa5301fc51e6e0d9922df54e79c10bace044f","last_reissued_at":"2026-07-05T06:55:38.543121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:38.543121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.08286","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":"2026-07-05T06:55:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jm05r3VBowZ80k+NHRgqV+eOp7PHbWiSpUapRNj5jnnfflT84nCz+3G0v6aBI49yte7/mbxE0YCZxZ6GpLgODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T10:30:12.736892Z"},"content_sha256":"ae504176cd2b3d10ac17047187ea59808725a1bbea081a15ea2ef89504b7e912","schema_version":"1.0","event_id":"sha256:ae504176cd2b3d10ac17047187ea59808725a1bbea081a15ea2ef89504b7e912"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:AFOREMA532YXCSJCDRDFIH5FGA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ALERT: Adapting Language Models to Reasoning Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Asli Celikyilmaz, Badr AlKhamissi, Gargi Ghosh, Mona Diab, Olga Golovneva, Ping Yu, Siddharth Verma, Tianlu Wang, Zhijing Jin","submitted_at":"2022-12-16T05:15:41Z","abstract_excerpt":"Current large language models can perform reasonably well on complex tasks that require step-by-step reasoning with few-shot learning. Are these models applying reasoning skills they have learnt during pre-training and reason outside of their training context, or are they simply memorizing their training corpus at finer granularity and have learnt to better understand their context? To tease apart these possibilities, we introduce ALERT, a benchmark and suite of analyses for assessing language models' reasoning ability comparing pre-trained and finetuned models on complex tasks that require re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08286","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/2212.08286/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":"2026-07-05T06:55:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v2mPUOSVA96b+46xFQz5m9C7cqZvos7QLLR9cnPpbyh9ptL4c7SOOYK32y/9KYYxbv/EKRsCbpef7O2OGcUIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T10:30:12.737385Z"},"content_sha256":"8a17af116624cbc545a055047da71d3359c8d573fe807bbb730ef51ab71316be","schema_version":"1.0","event_id":"sha256:8a17af116624cbc545a055047da71d3359c8d573fe807bbb730ef51ab71316be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AFOREMA532YXCSJCDRDFIH5FGA/bundle.json","state_url":"https://pith.science/pith/AFOREMA532YXCSJCDRDFIH5FGA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AFOREMA532YXCSJCDRDFIH5FGA/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":"2026-08-20T10:30:12Z","links":{"resolver":"https://pith.science/pith/AFOREMA532YXCSJCDRDFIH5FGA","bundle":"https://pith.science/pith/AFOREMA532YXCSJCDRDFIH5FGA/bundle.json","state":"https://pith.science/pith/AFOREMA532YXCSJCDRDFIH5FGA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AFOREMA532YXCSJCDRDFIH5FGA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AFOREMA532YXCSJCDRDFIH5FGA","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":"0904ab2bc284ae85ba3dd1fd5a1736a8a87bfae3656750a8efb132ac4ccf2058","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-16T05:15:41Z","title_canon_sha256":"a9b69e13a6f3be0c3900995b69758069ab2714bf12c6384c1b5026f5bef9109c"},"schema_version":"1.0","source":{"id":"2212.08286","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08286","created_at":"2026-07-05T06:55:38Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08286v2","created_at":"2026-07-05T06:55:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08286","created_at":"2026-07-05T06:55:38Z"},{"alias_kind":"pith_short_12","alias_value":"AFOREMA532YX","created_at":"2026-07-05T06:55:38Z"},{"alias_kind":"pith_short_16","alias_value":"AFOREMA532YXCSJC","created_at":"2026-07-05T06:55:38Z"},{"alias_kind":"pith_short_8","alias_value":"AFOREMA5","created_at":"2026-07-05T06:55:38Z"}],"graph_snapshots":[{"event_id":"sha256:8a17af116624cbc545a055047da71d3359c8d573fe807bbb730ef51ab71316be","target":"graph","created_at":"2026-07-05T06:55:38Z","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/2212.08286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current large language models can perform reasonably well on complex tasks that require step-by-step reasoning with few-shot learning. Are these models applying reasoning skills they have learnt during pre-training and reason outside of their training context, or are they simply memorizing their training corpus at finer granularity and have learnt to better understand their context? To tease apart these possibilities, we introduce ALERT, a benchmark and suite of analyses for assessing language models' reasoning ability comparing pre-trained and finetuned models on complex tasks that require re","authors_text":"Asli Celikyilmaz, Badr AlKhamissi, Gargi Ghosh, Mona Diab, Olga Golovneva, Ping Yu, Siddharth Verma, Tianlu Wang, Zhijing Jin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-16T05:15:41Z","title":"ALERT: Adapting Language Models to Reasoning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08286","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:ae504176cd2b3d10ac17047187ea59808725a1bbea081a15ea2ef89504b7e912","target":"record","created_at":"2026-07-05T06:55:38Z","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":"0904ab2bc284ae85ba3dd1fd5a1736a8a87bfae3656750a8efb132ac4ccf2058","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-16T05:15:41Z","title_canon_sha256":"a9b69e13a6f3be0c3900995b69758069ab2714bf12c6384c1b5026f5bef9109c"},"schema_version":"1.0","source":{"id":"2212.08286","kind":"arxiv","version":2}},"canonical_sha256":"015d12301ddeb17149221c46541fa5301fc51e6e0d9922df54e79c10bace044f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"015d12301ddeb17149221c46541fa5301fc51e6e0d9922df54e79c10bace044f","first_computed_at":"2026-07-05T06:55:38.543121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:55:38.543121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IodhvRxVekwzu2+PT6JAOC1SsCeixPJuXjrcRbvAdpp4uuArtXmkwRrbNL7JZLZR0FCvBKb4kgoP5hXqtktFAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:55:38.543619Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.08286","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae504176cd2b3d10ac17047187ea59808725a1bbea081a15ea2ef89504b7e912","sha256:8a17af116624cbc545a055047da71d3359c8d573fe807bbb730ef51ab71316be"],"state_sha256":"01bb05ba26a12804628d39ed2d3da3d6b23352ec9598fb05fb0966c8532f8069"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hlackT6mbpDZN6tzN1CHfgYNCv4scTF5D5HKOrGsl0snKQbu/u3ME705ozy+iDSv2rR4Go16zHuNRIv7v9h/Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T10:30:12.741259Z","bundle_sha256":"2495e6b973639454b52eb70604f5c094e0c84e09cad2d184c733743c379a8c34"}}