{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HCBEYOSL2BVAHJ77WEFZCSUOUG","short_pith_number":"pith:HCBEYOSL","schema_version":"1.0","canonical_sha256":"38824c3a4bd06a03a7ffb10b914a8ea1a2b40e3962865616201b195aa603e57f","source":{"kind":"arxiv","id":"2407.00996","version":3},"attestation_state":"computed","paper":{"title":"Can Small Language Models Learn, Unlearn, and Retain Noise Patterns?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Deepak Subramani, Nicy Scaria, Silvester John Joseph Kennedy","submitted_at":"2024-07-01T06:22:38Z","abstract_excerpt":"With the growing need for efficient language models in resource-constrained environments, Small Language Models (SLMs) have emerged as compact and practical alternatives to Large Language Models (LLMs). While studies have explored noise handling in LLMs, little is known about how SLMs handle noise, a critical factor for their reliable real-world deployment. This study investigates the ability of SLMs with parameters between 1 and 3 billion to learn, retain, and subsequently eliminate different types of noise (word flip, character flip, transliteration, irrelevant content, and contradictory inf"},"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":"2407.00996","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T06:22:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e0edfb0381acc5749a12227a4e6e392c0d33f0f2d1843b8c389374f15c558840","abstract_canon_sha256":"dedc06c34c907977a0bc600697760d43d232c9877400fca0d941c862444482b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:59.729119Z","signature_b64":"Um3WGDrPxLRY8B3MNjy0YLo6arKBLc5DVT/ggKhbzCP2aZoh9nhY00CuzZ457+I21XiXSuqayRmCK2P+dZ4gBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38824c3a4bd06a03a7ffb10b914a8ea1a2b40e3962865616201b195aa603e57f","last_reissued_at":"2026-07-05T11:09:59.728621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:59.728621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Small Language Models Learn, Unlearn, and Retain Noise Patterns?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Deepak Subramani, Nicy Scaria, Silvester John Joseph Kennedy","submitted_at":"2024-07-01T06:22:38Z","abstract_excerpt":"With the growing need for efficient language models in resource-constrained environments, Small Language Models (SLMs) have emerged as compact and practical alternatives to Large Language Models (LLMs). While studies have explored noise handling in LLMs, little is known about how SLMs handle noise, a critical factor for their reliable real-world deployment. This study investigates the ability of SLMs with parameters between 1 and 3 billion to learn, retain, and subsequently eliminate different types of noise (word flip, character flip, transliteration, irrelevant content, and contradictory inf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00996","kind":"arxiv","version":3},"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/2407.00996/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":"2407.00996","created_at":"2026-07-05T11:09:59.728680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00996v3","created_at":"2026-07-05T11:09:59.728680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00996","created_at":"2026-07-05T11:09:59.728680+00:00"},{"alias_kind":"pith_short_12","alias_value":"HCBEYOSL2BVA","created_at":"2026-07-05T11:09:59.728680+00:00"},{"alias_kind":"pith_short_16","alias_value":"HCBEYOSL2BVAHJ77","created_at":"2026-07-05T11:09:59.728680+00:00"},{"alias_kind":"pith_short_8","alias_value":"HCBEYOSL","created_at":"2026-07-05T11:09:59.728680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07907","citing_title":"Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HCBEYOSL2BVAHJ77WEFZCSUOUG","json":"https://pith.science/pith/HCBEYOSL2BVAHJ77WEFZCSUOUG.json","graph_json":"https://pith.science/api/pith-number/HCBEYOSL2BVAHJ77WEFZCSUOUG/graph.json","events_json":"https://pith.science/api/pith-number/HCBEYOSL2BVAHJ77WEFZCSUOUG/events.json","paper":"https://pith.science/paper/HCBEYOSL"},"agent_actions":{"view_html":"https://pith.science/pith/HCBEYOSL2BVAHJ77WEFZCSUOUG","download_json":"https://pith.science/pith/HCBEYOSL2BVAHJ77WEFZCSUOUG.json","view_paper":"https://pith.science/paper/HCBEYOSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00996&json=true","fetch_graph":"https://pith.science/api/pith-number/HCBEYOSL2BVAHJ77WEFZCSUOUG/graph.json","fetch_events":"https://pith.science/api/pith-number/HCBEYOSL2BVAHJ77WEFZCSUOUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HCBEYOSL2BVAHJ77WEFZCSUOUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HCBEYOSL2BVAHJ77WEFZCSUOUG/action/storage_attestation","attest_author":"https://pith.science/pith/HCBEYOSL2BVAHJ77WEFZCSUOUG/action/author_attestation","sign_citation":"https://pith.science/pith/HCBEYOSL2BVAHJ77WEFZCSUOUG/action/citation_signature","submit_replication":"https://pith.science/pith/HCBEYOSL2BVAHJ77WEFZCSUOUG/action/replication_record"}},"created_at":"2026-07-05T11:09:59.728680+00:00","updated_at":"2026-07-05T11:09:59.728680+00:00"}