{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GGD7542JDMNPAVX6LW5FCS4WEV","short_pith_number":"pith:GGD7542J","schema_version":"1.0","canonical_sha256":"3187fef3491b1af056fe5dba514b9625653247554be2165571e082bf32726ab7","source":{"kind":"arxiv","id":"2211.14865","version":2},"attestation_state":"computed","paper":{"title":"Understanding BLOOM: An empirical study on diverse NLP tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Parag Pravin Dakle, Preethi Raghavan, SaiKrishna Rallabandi","submitted_at":"2022-11-27T15:48:14Z","abstract_excerpt":"We view the landscape of large language models (LLMs) through the lens of the recently released BLOOM model to understand the performance of BLOOM and other decoder-only LLMs compared to BERT-style encoder-only models. We achieve this by evaluating the smaller BLOOM model variants (\\textit{350m/560m} and \\textit{1b3/1b7}) on several NLP benchmark datasets and popular leaderboards. We make the following observations: (1) BLOOM performance does not scale with parameter size, unlike other LLMs like GPT and BERT. Experiments fine-tuning BLOOM models show that the 560m variant performs similarly to"},"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":"2211.14865","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-27T15:48:14Z","cross_cats_sorted":[],"title_canon_sha256":"06358c293e2a5f412a52280d382585c57661ede2f2f1873e9759a05c7c3a9334","abstract_canon_sha256":"27668a0e0cce8d01cd87551ca88ef3091f3aad31d52cea2934396beda5360d11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:28.421176Z","signature_b64":"rWeHrFTASiTukstLtJD0cN+goKpr94mby23LULRIyzyCGZcnbOwyXv7uinTQcvIvxSS1fSyiPB5BPr3W8ALfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3187fef3491b1af056fe5dba514b9625653247554be2165571e082bf32726ab7","last_reissued_at":"2026-07-05T05:51:28.420719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:28.420719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding BLOOM: An empirical study on diverse NLP tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Parag Pravin Dakle, Preethi Raghavan, SaiKrishna Rallabandi","submitted_at":"2022-11-27T15:48:14Z","abstract_excerpt":"We view the landscape of large language models (LLMs) through the lens of the recently released BLOOM model to understand the performance of BLOOM and other decoder-only LLMs compared to BERT-style encoder-only models. We achieve this by evaluating the smaller BLOOM model variants (\\textit{350m/560m} and \\textit{1b3/1b7}) on several NLP benchmark datasets and popular leaderboards. We make the following observations: (1) BLOOM performance does not scale with parameter size, unlike other LLMs like GPT and BERT. Experiments fine-tuning BLOOM models show that the 560m variant performs similarly to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.14865","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/2211.14865/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":"2211.14865","created_at":"2026-07-05T05:51:28.420780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.14865v2","created_at":"2026-07-05T05:51:28.420780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.14865","created_at":"2026-07-05T05:51:28.420780+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGD7542JDMNP","created_at":"2026-07-05T05:51:28.420780+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGD7542JDMNPAVX6","created_at":"2026-07-05T05:51:28.420780+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGD7542J","created_at":"2026-07-05T05:51:28.420780+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.05629","citing_title":"The Impact of Model Scaling on Seen and Unseen Language Performance","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGD7542JDMNPAVX6LW5FCS4WEV","json":"https://pith.science/pith/GGD7542JDMNPAVX6LW5FCS4WEV.json","graph_json":"https://pith.science/api/pith-number/GGD7542JDMNPAVX6LW5FCS4WEV/graph.json","events_json":"https://pith.science/api/pith-number/GGD7542JDMNPAVX6LW5FCS4WEV/events.json","paper":"https://pith.science/paper/GGD7542J"},"agent_actions":{"view_html":"https://pith.science/pith/GGD7542JDMNPAVX6LW5FCS4WEV","download_json":"https://pith.science/pith/GGD7542JDMNPAVX6LW5FCS4WEV.json","view_paper":"https://pith.science/paper/GGD7542J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.14865&json=true","fetch_graph":"https://pith.science/api/pith-number/GGD7542JDMNPAVX6LW5FCS4WEV/graph.json","fetch_events":"https://pith.science/api/pith-number/GGD7542JDMNPAVX6LW5FCS4WEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGD7542JDMNPAVX6LW5FCS4WEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGD7542JDMNPAVX6LW5FCS4WEV/action/storage_attestation","attest_author":"https://pith.science/pith/GGD7542JDMNPAVX6LW5FCS4WEV/action/author_attestation","sign_citation":"https://pith.science/pith/GGD7542JDMNPAVX6LW5FCS4WEV/action/citation_signature","submit_replication":"https://pith.science/pith/GGD7542JDMNPAVX6LW5FCS4WEV/action/replication_record"}},"created_at":"2026-07-05T05:51:28.420780+00:00","updated_at":"2026-07-05T05:51:28.420780+00:00"}