{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2R326XCGD57XWBYBFTAKVUSSBL","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":"1730a138a0e44eaf6984cacb50266856b2962d5e676eab05c328e2bc76776fee","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T08:33:34Z","title_canon_sha256":"4d9a238edcaf3093781ff37aef48398d9d3c0ca77d4ca90b680c283fe8f560fd"},"schema_version":"1.0","source":{"id":"2606.26749","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26749","created_at":"2026-06-26T01:15:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26749v1","created_at":"2026-06-26T01:15:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26749","created_at":"2026-06-26T01:15:58Z"},{"alias_kind":"pith_short_12","alias_value":"2R326XCGD57X","created_at":"2026-06-26T01:15:58Z"},{"alias_kind":"pith_short_16","alias_value":"2R326XCGD57XWBYB","created_at":"2026-06-26T01:15:58Z"},{"alias_kind":"pith_short_8","alias_value":"2R326XCG","created_at":"2026-06-26T01:15:58Z"}],"graph_snapshots":[{"event_id":"sha256:2c57eccd2e0a63151c7b7dce5892f69bf697628d4d7e504b47f15bdf1423bd49","target":"graph","created_at":"2026-06-26T01:15:58Z","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/2606.26749/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural Collapse predicts that balanced one-hot classification pushes model representations to be equally far from each other; a symmetric configuration that depends only on the output label and ignores any semantic similarity in the inputs. This creates a puzzle: next-token prediction language models are trained predominantly (as context length increases) with one-hot labels: the same context is very unlikely to appear twice in training with different labels. However, they clearly learn latent structural features. That is, despite the one-hot training regime, a language model's contextual embe","authors_text":"Christos Thrampoulidis, Isabel Papadimitriou, Yize Zhao","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T08:33:34Z","title":"Structure Before Collapse: Transient semantic geometry in next-token prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26749","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:b80a8e59dcc42327c1fa1d74a3a683741b9db3df7bbad6bffdb012a4491bbcf0","target":"record","created_at":"2026-06-26T01:15:58Z","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":"1730a138a0e44eaf6984cacb50266856b2962d5e676eab05c328e2bc76776fee","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T08:33:34Z","title_canon_sha256":"4d9a238edcaf3093781ff37aef48398d9d3c0ca77d4ca90b680c283fe8f560fd"},"schema_version":"1.0","source":{"id":"2606.26749","kind":"arxiv","version":1}},"canonical_sha256":"d477af5c461f7f7b07012cc0aad2520acee46d2fcbeb780ab61b0d1140916dfe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d477af5c461f7f7b07012cc0aad2520acee46d2fcbeb780ab61b0d1140916dfe","first_computed_at":"2026-06-26T01:15:58.695385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:15:58.695385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a93mF3rueZh0ORUPFO5EARwoE+MOsCANpUt5rqiURc9EXjLtrnb79av2zL+qn4uD6tJhRGwVW7w9Ma7kV62vCg==","signature_status":"signed_v1","signed_at":"2026-06-26T01:15:58.695795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26749","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b80a8e59dcc42327c1fa1d74a3a683741b9db3df7bbad6bffdb012a4491bbcf0","sha256:2c57eccd2e0a63151c7b7dce5892f69bf697628d4d7e504b47f15bdf1423bd49"],"state_sha256":"589599efa9860ad430eb19d2c7e7508e705b413094e75a277359442247178f75"}