{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BRSHMTG7YT6GPACSIDBIQEHNLO","short_pith_number":"pith:BRSHMTG7","canonical_record":{"source":{"id":"2410.19456","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T10:30:21Z","cross_cats_sorted":[],"title_canon_sha256":"4f6e8766875d1050aadf1b7e7ba42e076c24d45789fe92cb3e6a1954baa3803c","abstract_canon_sha256":"dfe47c30257ae4e193ceee01bd86cc538cd8ff906751a1a1f99990ebf230daed"},"schema_version":"1.0"},"canonical_sha256":"0c64764cdfc4fc67805240c28810ed5bbfec94476d6b706cce566e468e4eddab","source":{"kind":"arxiv","id":"2410.19456","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19456","created_at":"2026-07-05T09:42:31Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19456v2","created_at":"2026-07-05T09:42:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19456","created_at":"2026-07-05T09:42:31Z"},{"alias_kind":"pith_short_12","alias_value":"BRSHMTG7YT6G","created_at":"2026-07-05T09:42:31Z"},{"alias_kind":"pith_short_16","alias_value":"BRSHMTG7YT6GPACS","created_at":"2026-07-05T09:42:31Z"},{"alias_kind":"pith_short_8","alias_value":"BRSHMTG7","created_at":"2026-07-05T09:42:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BRSHMTG7YT6GPACSIDBIQEHNLO","target":"record","payload":{"canonical_record":{"source":{"id":"2410.19456","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T10:30:21Z","cross_cats_sorted":[],"title_canon_sha256":"4f6e8766875d1050aadf1b7e7ba42e076c24d45789fe92cb3e6a1954baa3803c","abstract_canon_sha256":"dfe47c30257ae4e193ceee01bd86cc538cd8ff906751a1a1f99990ebf230daed"},"schema_version":"1.0"},"canonical_sha256":"0c64764cdfc4fc67805240c28810ed5bbfec94476d6b706cce566e468e4eddab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:31.525428Z","signature_b64":"TQcNuD7Yb/o49OK9eHtw6lN2wL9OvwL1zSj+1j1pb7E8SaEY3eeZR0gRBgi6dAvwsEWnzH7e2sBovddpZLU8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c64764cdfc4fc67805240c28810ed5bbfec94476d6b706cce566e468e4eddab","last_reissued_at":"2026-07-05T09:42:31.524857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:31.524857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.19456","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":"2026-07-05T09:42:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TNg87xvUoIKOk8SV9ap3zmCFFxIUbtX2yGKoKMv/1TIUjbyOCwbpQvOEAmW0vrb+vz2MC+SwbyIV75IsV4EzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:18:22.540542Z"},"content_sha256":"5a719d3bef9790061faa9da4e90f7b2d91d28f2678d69942317552ffd785168b","schema_version":"1.0","event_id":"sha256:5a719d3bef9790061faa9da4e90f7b2d91d28f2678d69942317552ffd785168b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BRSHMTG7YT6GPACSIDBIQEHNLO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Computational Bottlenecks of Training Small-scale Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fartash Faghri, Iman Mirzadeh, Keivan Alizadeh, Mehrdad Farajtabar, Mohammad Hossein Sekhavat, Moin Nabi, Saleh Ashkboos","submitted_at":"2024-10-25T10:30:21Z","abstract_excerpt":"While large language models (LLMs) dominate the AI landscape, Small-scale large Language Models (SLMs) are gaining attention due to cost and efficiency demands from consumers. However, there is limited research on the training behavior and computational requirements of SLMs. In this study, we explore the computational bottlenecks of training SLMs (up to 2B parameters) by examining the effects of various hyperparameters and configurations, including GPU type, batch size, model size, communication protocol, attention type, and the number of GPUs. We assess these factors on popular cloud services"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19456","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/2410.19456/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":"2026-07-05T09:42:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JS022SwJg8FZL6uyKpo7f+MTwCNyvjOM1rYOBHLJ+z875lvrWrF/jr5XgpN/TddCu924o6wqR7Gc6wJ5fdOtCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:18:22.541076Z"},"content_sha256":"056ccf06e0f3964b8461a4d36d8d7e8d6f0cc3f20fdefd01034db2d759a499e4","schema_version":"1.0","event_id":"sha256:056ccf06e0f3964b8461a4d36d8d7e8d6f0cc3f20fdefd01034db2d759a499e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BRSHMTG7YT6GPACSIDBIQEHNLO/bundle.json","state_url":"https://pith.science/pith/BRSHMTG7YT6GPACSIDBIQEHNLO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BRSHMTG7YT6GPACSIDBIQEHNLO/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":"2026-08-07T06:18:22Z","links":{"resolver":"https://pith.science/pith/BRSHMTG7YT6GPACSIDBIQEHNLO","bundle":"https://pith.science/pith/BRSHMTG7YT6GPACSIDBIQEHNLO/bundle.json","state":"https://pith.science/pith/BRSHMTG7YT6GPACSIDBIQEHNLO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BRSHMTG7YT6GPACSIDBIQEHNLO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BRSHMTG7YT6GPACSIDBIQEHNLO","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":"dfe47c30257ae4e193ceee01bd86cc538cd8ff906751a1a1f99990ebf230daed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T10:30:21Z","title_canon_sha256":"4f6e8766875d1050aadf1b7e7ba42e076c24d45789fe92cb3e6a1954baa3803c"},"schema_version":"1.0","source":{"id":"2410.19456","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19456","created_at":"2026-07-05T09:42:31Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19456v2","created_at":"2026-07-05T09:42:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19456","created_at":"2026-07-05T09:42:31Z"},{"alias_kind":"pith_short_12","alias_value":"BRSHMTG7YT6G","created_at":"2026-07-05T09:42:31Z"},{"alias_kind":"pith_short_16","alias_value":"BRSHMTG7YT6GPACS","created_at":"2026-07-05T09:42:31Z"},{"alias_kind":"pith_short_8","alias_value":"BRSHMTG7","created_at":"2026-07-05T09:42:31Z"}],"graph_snapshots":[{"event_id":"sha256:056ccf06e0f3964b8461a4d36d8d7e8d6f0cc3f20fdefd01034db2d759a499e4","target":"graph","created_at":"2026-07-05T09:42:31Z","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/2410.19456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large language models (LLMs) dominate the AI landscape, Small-scale large Language Models (SLMs) are gaining attention due to cost and efficiency demands from consumers. However, there is limited research on the training behavior and computational requirements of SLMs. In this study, we explore the computational bottlenecks of training SLMs (up to 2B parameters) by examining the effects of various hyperparameters and configurations, including GPU type, batch size, model size, communication protocol, attention type, and the number of GPUs. We assess these factors on popular cloud services","authors_text":"Fartash Faghri, Iman Mirzadeh, Keivan Alizadeh, Mehrdad Farajtabar, Mohammad Hossein Sekhavat, Moin Nabi, Saleh Ashkboos","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T10:30:21Z","title":"Computational Bottlenecks of Training Small-scale Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19456","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":"sha256:5a719d3bef9790061faa9da4e90f7b2d91d28f2678d69942317552ffd785168b","target":"record","created_at":"2026-07-05T09:42:31Z","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":"dfe47c30257ae4e193ceee01bd86cc538cd8ff906751a1a1f99990ebf230daed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T10:30:21Z","title_canon_sha256":"4f6e8766875d1050aadf1b7e7ba42e076c24d45789fe92cb3e6a1954baa3803c"},"schema_version":"1.0","source":{"id":"2410.19456","kind":"arxiv","version":2}},"canonical_sha256":"0c64764cdfc4fc67805240c28810ed5bbfec94476d6b706cce566e468e4eddab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c64764cdfc4fc67805240c28810ed5bbfec94476d6b706cce566e468e4eddab","first_computed_at":"2026-07-05T09:42:31.524857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:31.524857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TQcNuD7Yb/o49OK9eHtw6lN2wL9OvwL1zSj+1j1pb7E8SaEY3eeZR0gRBgi6dAvwsEWnzH7e2sBovddpZLU8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:31.525428Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.19456","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a719d3bef9790061faa9da4e90f7b2d91d28f2678d69942317552ffd785168b","sha256:056ccf06e0f3964b8461a4d36d8d7e8d6f0cc3f20fdefd01034db2d759a499e4"],"state_sha256":"44c323f8950bb9d7468c192e9b1e84ca5b7479d9356751d2eef92bf81cc0e42a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IAlLI4HLeUq3R4qKFkIcaGIQ4UAuqMu6Bz3DIxqHbXy02QmnnETx1HaNkvULL0aW0J8MB6U/A2dOlZQOKFiXAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:18:22.546563Z","bundle_sha256":"9864663ad5d2a4fa39c39a50f6980af7539d434860c746c0cb3ad44af51dee6d"}}