{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KKPCJMQ54PLLWJ3WMCFJG2PV2A","short_pith_number":"pith:KKPCJMQ5","canonical_record":{"source":{"id":"2411.08968","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-13T19:02:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9a1338de3d83269da4b904f404db4358c5b99866eee54e75e14d9e0262e67a9a","abstract_canon_sha256":"e4e96fe4231f02d5a265a101a6af77a954164fed75fd061d5fb4cd4eaa50d3bd"},"schema_version":"1.0"},"canonical_sha256":"529e24b21de3d6bb2776608a9369f5d01fa61ffe0473714e9daf7d8c678bfd27","source":{"kind":"arxiv","id":"2411.08968","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08968","created_at":"2026-07-05T09:35:17Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08968v1","created_at":"2026-07-05T09:35:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08968","created_at":"2026-07-05T09:35:17Z"},{"alias_kind":"pith_short_12","alias_value":"KKPCJMQ54PLL","created_at":"2026-07-05T09:35:17Z"},{"alias_kind":"pith_short_16","alias_value":"KKPCJMQ54PLLWJ3W","created_at":"2026-07-05T09:35:17Z"},{"alias_kind":"pith_short_8","alias_value":"KKPCJMQ5","created_at":"2026-07-05T09:35:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KKPCJMQ54PLLWJ3WMCFJG2PV2A","target":"record","payload":{"canonical_record":{"source":{"id":"2411.08968","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-13T19:02:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9a1338de3d83269da4b904f404db4358c5b99866eee54e75e14d9e0262e67a9a","abstract_canon_sha256":"e4e96fe4231f02d5a265a101a6af77a954164fed75fd061d5fb4cd4eaa50d3bd"},"schema_version":"1.0"},"canonical_sha256":"529e24b21de3d6bb2776608a9369f5d01fa61ffe0473714e9daf7d8c678bfd27","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:17.616289Z","signature_b64":"oUE0YBqK7LYbCVt8DoJmUZL1N6gpJLPJ3fCuVwP9DPUJM2oZ0CUpFLd1bNu15VftpU7bUZVbLmuJIiAcX2tNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"529e24b21de3d6bb2776608a9369f5d01fa61ffe0473714e9daf7d8c678bfd27","last_reissued_at":"2026-07-05T09:35:17.615787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:17.615787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.08968","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":"2026-07-05T09:35:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KK74az+S6uqvp3bi6Lcs8DvWRj91TMyidGnNsUgLTqnm9FAicpRvxBv2ioQ77ilKe7Dt9EFKE++KebwxdQHgCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:06:07.029469Z"},"content_sha256":"2a4b2a0688907b79ba1e575c405f1965adf698882d50a0082a82c95bbebbb917","schema_version":"1.0","event_id":"sha256:2a4b2a0688907b79ba1e575c405f1965adf698882d50a0082a82c95bbebbb917"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KKPCJMQ54PLLWJ3WMCFJG2PV2A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparse Upcycling: Inference Inefficient Finetuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Nikhil Sardana, Sasha Doubov, Vitaliy Chiley","submitted_at":"2024-11-13T19:02:36Z","abstract_excerpt":"Small, highly trained, open-source large language models are widely used due to their inference efficiency, but further improving their quality remains a challenge. Sparse upcycling is a promising approach that transforms a pretrained dense model into a Mixture-of-Experts (MoE) architecture, increasing the model's parameter count and quality. In this work, we compare the effectiveness of sparse upcycling against continued pretraining (CPT) across different model sizes, compute budgets, and pretraining durations. Our experiments show that sparse upcycling can achieve better quality, with improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08968","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/2411.08968/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":"2026-07-05T09:35:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bhMUn4C6fhH1hXSDge6Lw4JszZ2CKTrtVYBLJaOebCUKuzW0KTehFj1M8U/YV3eOU7HbVwUI6qouducguHXXAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:06:07.029842Z"},"content_sha256":"8484f036d932af787afdfccdf2fd2199954d610a8c75d6dd9f431edd0db8256f","schema_version":"1.0","event_id":"sha256:8484f036d932af787afdfccdf2fd2199954d610a8c75d6dd9f431edd0db8256f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KKPCJMQ54PLLWJ3WMCFJG2PV2A/bundle.json","state_url":"https://pith.science/pith/KKPCJMQ54PLLWJ3WMCFJG2PV2A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KKPCJMQ54PLLWJ3WMCFJG2PV2A/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":"2026-07-06T19:06:07Z","links":{"resolver":"https://pith.science/pith/KKPCJMQ54PLLWJ3WMCFJG2PV2A","bundle":"https://pith.science/pith/KKPCJMQ54PLLWJ3WMCFJG2PV2A/bundle.json","state":"https://pith.science/pith/KKPCJMQ54PLLWJ3WMCFJG2PV2A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KKPCJMQ54PLLWJ3WMCFJG2PV2A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KKPCJMQ54PLLWJ3WMCFJG2PV2A","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":"e4e96fe4231f02d5a265a101a6af77a954164fed75fd061d5fb4cd4eaa50d3bd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-13T19:02:36Z","title_canon_sha256":"9a1338de3d83269da4b904f404db4358c5b99866eee54e75e14d9e0262e67a9a"},"schema_version":"1.0","source":{"id":"2411.08968","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08968","created_at":"2026-07-05T09:35:17Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08968v1","created_at":"2026-07-05T09:35:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08968","created_at":"2026-07-05T09:35:17Z"},{"alias_kind":"pith_short_12","alias_value":"KKPCJMQ54PLL","created_at":"2026-07-05T09:35:17Z"},{"alias_kind":"pith_short_16","alias_value":"KKPCJMQ54PLLWJ3W","created_at":"2026-07-05T09:35:17Z"},{"alias_kind":"pith_short_8","alias_value":"KKPCJMQ5","created_at":"2026-07-05T09:35:17Z"}],"graph_snapshots":[{"event_id":"sha256:8484f036d932af787afdfccdf2fd2199954d610a8c75d6dd9f431edd0db8256f","target":"graph","created_at":"2026-07-05T09:35:17Z","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/2411.08968/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Small, highly trained, open-source large language models are widely used due to their inference efficiency, but further improving their quality remains a challenge. Sparse upcycling is a promising approach that transforms a pretrained dense model into a Mixture-of-Experts (MoE) architecture, increasing the model's parameter count and quality. In this work, we compare the effectiveness of sparse upcycling against continued pretraining (CPT) across different model sizes, compute budgets, and pretraining durations. Our experiments show that sparse upcycling can achieve better quality, with improv","authors_text":"Nikhil Sardana, Sasha Doubov, Vitaliy Chiley","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-13T19:02:36Z","title":"Sparse Upcycling: Inference Inefficient Finetuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08968","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":"sha256:2a4b2a0688907b79ba1e575c405f1965adf698882d50a0082a82c95bbebbb917","target":"record","created_at":"2026-07-05T09:35:17Z","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":"e4e96fe4231f02d5a265a101a6af77a954164fed75fd061d5fb4cd4eaa50d3bd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-13T19:02:36Z","title_canon_sha256":"9a1338de3d83269da4b904f404db4358c5b99866eee54e75e14d9e0262e67a9a"},"schema_version":"1.0","source":{"id":"2411.08968","kind":"arxiv","version":1}},"canonical_sha256":"529e24b21de3d6bb2776608a9369f5d01fa61ffe0473714e9daf7d8c678bfd27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"529e24b21de3d6bb2776608a9369f5d01fa61ffe0473714e9daf7d8c678bfd27","first_computed_at":"2026-07-05T09:35:17.615787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:17.615787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oUE0YBqK7LYbCVt8DoJmUZL1N6gpJLPJ3fCuVwP9DPUJM2oZ0CUpFLd1bNu15VftpU7bUZVbLmuJIiAcX2tNCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:17.616289Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.08968","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a4b2a0688907b79ba1e575c405f1965adf698882d50a0082a82c95bbebbb917","sha256:8484f036d932af787afdfccdf2fd2199954d610a8c75d6dd9f431edd0db8256f"],"state_sha256":"c2eeadb825d4fd15f563c4eda8d30aef301777c11510f095f4ec60fd445aec19"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UkS2QGnE4mxlZFVoWN2Qt/Lwy8lslawIbY7ogZ8+h1zgwu2RZBpTZu9yIRG/3yUqg8c9syrEL7/oIFO9S2EiCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:06:07.031831Z","bundle_sha256":"035204bbd7119b5973a9c61c3db9a209b86aca4ae8fba24417a68afcb0dfc43b"}}