{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DH2MY2Z4TNZQB7Q7U4KWLK6QZO","short_pith_number":"pith:DH2MY2Z4","canonical_record":{"source":{"id":"2508.02668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T17:58:22Z","cross_cats_sorted":[],"title_canon_sha256":"00e68024c48ffaa590001f5baabb71da8b3a02bb28121f1105c6e5319a2b8e55","abstract_canon_sha256":"9e74d310d39d07b3c66d04f4f8ce0e380841d055e1309701c05fd19e20142bb1"},"schema_version":"1.0"},"canonical_sha256":"19f4cc6b3c9b7300fe1fa71565abd0cb82a6f03bca1fc94c7f43367ce3128283","source":{"kind":"arxiv","id":"2508.02668","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02668","created_at":"2026-07-05T11:48:18Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02668v1","created_at":"2026-07-05T11:48:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02668","created_at":"2026-07-05T11:48:18Z"},{"alias_kind":"pith_short_12","alias_value":"DH2MY2Z4TNZQ","created_at":"2026-07-05T11:48:18Z"},{"alias_kind":"pith_short_16","alias_value":"DH2MY2Z4TNZQB7Q7","created_at":"2026-07-05T11:48:18Z"},{"alias_kind":"pith_short_8","alias_value":"DH2MY2Z4","created_at":"2026-07-05T11:48:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DH2MY2Z4TNZQB7Q7U4KWLK6QZO","target":"record","payload":{"canonical_record":{"source":{"id":"2508.02668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T17:58:22Z","cross_cats_sorted":[],"title_canon_sha256":"00e68024c48ffaa590001f5baabb71da8b3a02bb28121f1105c6e5319a2b8e55","abstract_canon_sha256":"9e74d310d39d07b3c66d04f4f8ce0e380841d055e1309701c05fd19e20142bb1"},"schema_version":"1.0"},"canonical_sha256":"19f4cc6b3c9b7300fe1fa71565abd0cb82a6f03bca1fc94c7f43367ce3128283","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:18.405631Z","signature_b64":"ElN7elxPPjlRR16YBd+U505llacpjiQN/Yjzh3y3yfNiW7eQSebMxcXcv2hZ/xN3fwcwCrLcOjAiDG73xPxsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19f4cc6b3c9b7300fe1fa71565abd0cb82a6f03bca1fc94c7f43367ce3128283","last_reissued_at":"2026-07-05T11:48:18.405089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:18.405089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.02668","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":"2026-07-05T11:48:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pBzw6NNC3ReXEOiTVEHKxE/j3o3BgApaCkqQXML6R0kmY5U0SuD9t0wIA68QM6ORRipHhxN9Lf7Goz+yV1X2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:56:20.548591Z"},"content_sha256":"864c8c6f4d08e71efd55310eea6df75c7d370667fe283422d3e3e8e05c9a6210","schema_version":"1.0","event_id":"sha256:864c8c6f4d08e71efd55310eea6df75c7d370667fe283422d3e3e8e05c9a6210"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DH2MY2Z4TNZQB7Q7U4KWLK6QZO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LOST: Low-rank and Sparse Pre-training for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaxi Li, Jinjin Xu, Li Shen, Liwu Xu, Lu Yin, Shiwei Liu, Tianjin Huang, Wenwu Wang, Xilu Wang","submitted_at":"2025-08-04T17:58:22Z","abstract_excerpt":"While large language models (LLMs) have achieved remarkable performance across a wide range of tasks, their massive scale incurs prohibitive computational and memory costs for pre-training from scratch. Recent studies have investigated the use of low-rank parameterization as a means of reducing model size and training cost. In this context, sparsity is often employed as a complementary technique to recover important information lost in low-rank compression by capturing salient features in the residual space. However, existing approaches typically combine low-rank and sparse components in a sim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02668","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/2508.02668/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":"2026-07-05T11:48:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3G6hfayWwd+3y4gNDg9Ng3cayDjmABt+GUv8RgNfplxHUDI7UhZKqbLsUqdmjPOwxgetX/WuJlbI5giSwvCdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:56:20.549542Z"},"content_sha256":"f9556aa3afb5e3ed3ba7599e09429619f5e2bc41f760bcde4460c6f16d966ce3","schema_version":"1.0","event_id":"sha256:f9556aa3afb5e3ed3ba7599e09429619f5e2bc41f760bcde4460c6f16d966ce3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DH2MY2Z4TNZQB7Q7U4KWLK6QZO/bundle.json","state_url":"https://pith.science/pith/DH2MY2Z4TNZQB7Q7U4KWLK6QZO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DH2MY2Z4TNZQB7Q7U4KWLK6QZO/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":"2026-08-18T18:56:20Z","links":{"resolver":"https://pith.science/pith/DH2MY2Z4TNZQB7Q7U4KWLK6QZO","bundle":"https://pith.science/pith/DH2MY2Z4TNZQB7Q7U4KWLK6QZO/bundle.json","state":"https://pith.science/pith/DH2MY2Z4TNZQB7Q7U4KWLK6QZO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DH2MY2Z4TNZQB7Q7U4KWLK6QZO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DH2MY2Z4TNZQB7Q7U4KWLK6QZO","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":"9e74d310d39d07b3c66d04f4f8ce0e380841d055e1309701c05fd19e20142bb1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T17:58:22Z","title_canon_sha256":"00e68024c48ffaa590001f5baabb71da8b3a02bb28121f1105c6e5319a2b8e55"},"schema_version":"1.0","source":{"id":"2508.02668","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02668","created_at":"2026-07-05T11:48:18Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02668v1","created_at":"2026-07-05T11:48:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02668","created_at":"2026-07-05T11:48:18Z"},{"alias_kind":"pith_short_12","alias_value":"DH2MY2Z4TNZQ","created_at":"2026-07-05T11:48:18Z"},{"alias_kind":"pith_short_16","alias_value":"DH2MY2Z4TNZQB7Q7","created_at":"2026-07-05T11:48:18Z"},{"alias_kind":"pith_short_8","alias_value":"DH2MY2Z4","created_at":"2026-07-05T11:48:18Z"}],"graph_snapshots":[{"event_id":"sha256:f9556aa3afb5e3ed3ba7599e09429619f5e2bc41f760bcde4460c6f16d966ce3","target":"graph","created_at":"2026-07-05T11:48:18Z","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/2508.02668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large language models (LLMs) have achieved remarkable performance across a wide range of tasks, their massive scale incurs prohibitive computational and memory costs for pre-training from scratch. Recent studies have investigated the use of low-rank parameterization as a means of reducing model size and training cost. In this context, sparsity is often employed as a complementary technique to recover important information lost in low-rank compression by capturing salient features in the residual space. However, existing approaches typically combine low-rank and sparse components in a sim","authors_text":"Jiaxi Li, Jinjin Xu, Li Shen, Liwu Xu, Lu Yin, Shiwei Liu, Tianjin Huang, Wenwu Wang, Xilu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T17:58:22Z","title":"LOST: Low-rank and Sparse Pre-training for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02668","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":"sha256:864c8c6f4d08e71efd55310eea6df75c7d370667fe283422d3e3e8e05c9a6210","target":"record","created_at":"2026-07-05T11:48:18Z","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":"9e74d310d39d07b3c66d04f4f8ce0e380841d055e1309701c05fd19e20142bb1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T17:58:22Z","title_canon_sha256":"00e68024c48ffaa590001f5baabb71da8b3a02bb28121f1105c6e5319a2b8e55"},"schema_version":"1.0","source":{"id":"2508.02668","kind":"arxiv","version":1}},"canonical_sha256":"19f4cc6b3c9b7300fe1fa71565abd0cb82a6f03bca1fc94c7f43367ce3128283","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19f4cc6b3c9b7300fe1fa71565abd0cb82a6f03bca1fc94c7f43367ce3128283","first_computed_at":"2026-07-05T11:48:18.405089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:18.405089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ElN7elxPPjlRR16YBd+U505llacpjiQN/Yjzh3y3yfNiW7eQSebMxcXcv2hZ/xN3fwcwCrLcOjAiDG73xPxsBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:18.405631Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.02668","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:864c8c6f4d08e71efd55310eea6df75c7d370667fe283422d3e3e8e05c9a6210","sha256:f9556aa3afb5e3ed3ba7599e09429619f5e2bc41f760bcde4460c6f16d966ce3"],"state_sha256":"f3107a68a45881e360fdf9ec224ff6fc6f11aae1c24d99b946a9ba69c99005ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tGmYSaA2XAyLa86p+sqbMh8ifBtfDWYHyyXsTqS1IQQejhh36KiQnSdwP04YY5UGPEY7xQrkgv1qCrCA4YA3Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:56:20.554765Z","bundle_sha256":"5681e4b0d0381a4015e3bbe175ed05d99c74bfd42808a9d9e1d8e7e5c64eeb30"}}