{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4VSAJOTJLTFCVY4ALZE2XEDGAH","short_pith_number":"pith:4VSAJOTJ","schema_version":"1.0","canonical_sha256":"e56404ba695cca2ae3805e49ab906601e32910633e577c82f8e0bf3ff1e94f74","source":{"kind":"arxiv","id":"2605.26489","version":1},"attestation_state":"computed","paper":{"title":"The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenxi Jia, Hongtao Zhang, Wei Chen, Wenjie Zhou, Xueqi Cheng","submitted_at":"2026-05-26T03:03:24Z","abstract_excerpt":"Large language model pre-training typically exhibits a two-phase trajectory: a fast initial loss drop followed by a prolonged slow improvement. We identify an underlying spectral phenomenon, Stability of Singular Distribution (SoSD), where the trace-normalized singular value spectrum stabilizes early, even as parameter matrices continue to evolve. We demonstrate that synchronization between SoSD and the slow-descent regime is widely observed across diverse architectures (GPT-2, LLaMA) and settings, including various schedules (Step-wise, WSD, Cosine Decay), weight decays, and optimizers (AdamW"},"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":"2605.26489","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T03:03:24Z","cross_cats_sorted":[],"title_canon_sha256":"c25a235daca071f3102b881489218d5597b24c8618979621c102a411b98b295f","abstract_canon_sha256":"049b0c8211e61b175ad68eccf3d00ab3e69c298449a4a8ea98019e5249dcb6de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:20.934054Z","signature_b64":"PE8mxhNVPissz+U/+x9PmaE88vpWVid7fGXuQlPpeNRbFpFIXKpn5jsLy47+sRYNDGGAs8af40pCV6uufrk0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e56404ba695cca2ae3805e49ab906601e32910633e577c82f8e0bf3ff1e94f74","last_reissued_at":"2026-05-27T01:05:20.933230Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:20.933230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenxi Jia, Hongtao Zhang, Wei Chen, Wenjie Zhou, Xueqi Cheng","submitted_at":"2026-05-26T03:03:24Z","abstract_excerpt":"Large language model pre-training typically exhibits a two-phase trajectory: a fast initial loss drop followed by a prolonged slow improvement. We identify an underlying spectral phenomenon, Stability of Singular Distribution (SoSD), where the trace-normalized singular value spectrum stabilizes early, even as parameter matrices continue to evolve. We demonstrate that synchronization between SoSD and the slow-descent regime is widely observed across diverse architectures (GPT-2, LLaMA) and settings, including various schedules (Step-wise, WSD, Cosine Decay), weight decays, and optimizers (AdamW"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26489","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/2605.26489/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":"2605.26489","created_at":"2026-05-27T01:05:20.933371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26489v1","created_at":"2026-05-27T01:05:20.933371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26489","created_at":"2026-05-27T01:05:20.933371+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VSAJOTJLTFC","created_at":"2026-05-27T01:05:20.933371+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VSAJOTJLTFCVY4A","created_at":"2026-05-27T01:05:20.933371+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VSAJOTJ","created_at":"2026-05-27T01:05:20.933371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VSAJOTJLTFCVY4ALZE2XEDGAH","json":"https://pith.science/pith/4VSAJOTJLTFCVY4ALZE2XEDGAH.json","graph_json":"https://pith.science/api/pith-number/4VSAJOTJLTFCVY4ALZE2XEDGAH/graph.json","events_json":"https://pith.science/api/pith-number/4VSAJOTJLTFCVY4ALZE2XEDGAH/events.json","paper":"https://pith.science/paper/4VSAJOTJ"},"agent_actions":{"view_html":"https://pith.science/pith/4VSAJOTJLTFCVY4ALZE2XEDGAH","download_json":"https://pith.science/pith/4VSAJOTJLTFCVY4ALZE2XEDGAH.json","view_paper":"https://pith.science/paper/4VSAJOTJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26489&json=true","fetch_graph":"https://pith.science/api/pith-number/4VSAJOTJLTFCVY4ALZE2XEDGAH/graph.json","fetch_events":"https://pith.science/api/pith-number/4VSAJOTJLTFCVY4ALZE2XEDGAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VSAJOTJLTFCVY4ALZE2XEDGAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VSAJOTJLTFCVY4ALZE2XEDGAH/action/storage_attestation","attest_author":"https://pith.science/pith/4VSAJOTJLTFCVY4ALZE2XEDGAH/action/author_attestation","sign_citation":"https://pith.science/pith/4VSAJOTJLTFCVY4ALZE2XEDGAH/action/citation_signature","submit_replication":"https://pith.science/pith/4VSAJOTJLTFCVY4ALZE2XEDGAH/action/replication_record"}},"created_at":"2026-05-27T01:05:20.933371+00:00","updated_at":"2026-05-27T01:05:20.933371+00:00"}