{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AQWYLLMSBJZSWZ4D2YWTTPBRDI","short_pith_number":"pith:AQWYLLMS","canonical_record":{"source":{"id":"2410.08993","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DG","submitted_at":"2024-10-11T17:07:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c8a71b36553665a1554cc9f7e31a640b95113fd49211e94649c1ed4ebca0c89d","abstract_canon_sha256":"68e1b1ecd1e5788016ae5f86728d9a849967f54c44dcc28300288a490a216ee0"},"schema_version":"1.0"},"canonical_sha256":"042d85ad920a732b6783d62d39bc311a25f2d089c162de888da22c1b02ba2356","source":{"kind":"arxiv","id":"2410.08993","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08993","created_at":"2026-07-05T09:19:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08993v1","created_at":"2026-07-05T09:19:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08993","created_at":"2026-07-05T09:19:20Z"},{"alias_kind":"pith_short_12","alias_value":"AQWYLLMSBJZS","created_at":"2026-07-05T09:19:20Z"},{"alias_kind":"pith_short_16","alias_value":"AQWYLLMSBJZSWZ4D","created_at":"2026-07-05T09:19:20Z"},{"alias_kind":"pith_short_8","alias_value":"AQWYLLMS","created_at":"2026-07-05T09:19:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AQWYLLMSBJZSWZ4D2YWTTPBRDI","target":"record","payload":{"canonical_record":{"source":{"id":"2410.08993","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DG","submitted_at":"2024-10-11T17:07:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c8a71b36553665a1554cc9f7e31a640b95113fd49211e94649c1ed4ebca0c89d","abstract_canon_sha256":"68e1b1ecd1e5788016ae5f86728d9a849967f54c44dcc28300288a490a216ee0"},"schema_version":"1.0"},"canonical_sha256":"042d85ad920a732b6783d62d39bc311a25f2d089c162de888da22c1b02ba2356","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:20.432972Z","signature_b64":"BMPj9daoJTKFYKwY7GZ8742n3TgfmFmvooJ2/v5cyTmVBRUQKen15WfT0AMTl8ThDJN5d9IEoco7u7NIU2cwAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"042d85ad920a732b6783d62d39bc311a25f2d089c162de888da22c1b02ba2356","last_reissued_at":"2026-07-05T09:19:20.432514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:20.432514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.08993","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":"2026-07-05T09:19:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JAK5x5J6KXRltnvMOEA9DKSkuWYH0JbZWDWFsG3gRcNWiHo8z5Gg2hSI7jkY4QzQJjo/YLtLazWRWjeQskxgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:14:43.570001Z"},"content_sha256":"27156343ebcfac3e6c4c177738e223ca209df7d3e4b714ee0fd34dd6fe6b9daf","schema_version":"1.0","event_id":"sha256:27156343ebcfac3e6c4c177738e223ca209df7d3e4b714ee0fd34dd6fe6b9daf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AQWYLLMSBJZSWZ4D2YWTTPBRDI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The structure of the token space for large language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"math.DG","authors_text":"Michael Robinson, Shauna Sweet, Sourya Dey","submitted_at":"2024-10-11T17:07:15Z","abstract_excerpt":"Large language models encode the correlational structure present in natural language by fitting segments of utterances (tokens) into a high dimensional ambient latent space upon which the models then operate. We assert that in order to develop a foundational, first-principles understanding of the behavior and limitations of large language models, it is crucial to understand the topological and geometric structure of this token subspace. In this article, we present estimators for the dimension and Ricci scalar curvature of the token subspace, and apply it to three open source large language mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08993","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/2410.08993/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":"2026-07-05T09:19:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XhZebQUVjvz7v9rqzJtTW9BaAkt8j7+NndTR5XGRAqXqQczQOUzVFfSU2K46W4ymF2EyA/vS6+v8KI8S4h6hAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:14:43.570489Z"},"content_sha256":"4d48b314827068234cf26b287bbdf1280f97e262fbcde3cd7c1967ccdc5ae52a","schema_version":"1.0","event_id":"sha256:4d48b314827068234cf26b287bbdf1280f97e262fbcde3cd7c1967ccdc5ae52a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AQWYLLMSBJZSWZ4D2YWTTPBRDI/bundle.json","state_url":"https://pith.science/pith/AQWYLLMSBJZSWZ4D2YWTTPBRDI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AQWYLLMSBJZSWZ4D2YWTTPBRDI/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":"2026-08-08T00:14:43Z","links":{"resolver":"https://pith.science/pith/AQWYLLMSBJZSWZ4D2YWTTPBRDI","bundle":"https://pith.science/pith/AQWYLLMSBJZSWZ4D2YWTTPBRDI/bundle.json","state":"https://pith.science/pith/AQWYLLMSBJZSWZ4D2YWTTPBRDI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AQWYLLMSBJZSWZ4D2YWTTPBRDI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AQWYLLMSBJZSWZ4D2YWTTPBRDI","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":"68e1b1ecd1e5788016ae5f86728d9a849967f54c44dcc28300288a490a216ee0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DG","submitted_at":"2024-10-11T17:07:15Z","title_canon_sha256":"c8a71b36553665a1554cc9f7e31a640b95113fd49211e94649c1ed4ebca0c89d"},"schema_version":"1.0","source":{"id":"2410.08993","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08993","created_at":"2026-07-05T09:19:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08993v1","created_at":"2026-07-05T09:19:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08993","created_at":"2026-07-05T09:19:20Z"},{"alias_kind":"pith_short_12","alias_value":"AQWYLLMSBJZS","created_at":"2026-07-05T09:19:20Z"},{"alias_kind":"pith_short_16","alias_value":"AQWYLLMSBJZSWZ4D","created_at":"2026-07-05T09:19:20Z"},{"alias_kind":"pith_short_8","alias_value":"AQWYLLMS","created_at":"2026-07-05T09:19:20Z"}],"graph_snapshots":[{"event_id":"sha256:4d48b314827068234cf26b287bbdf1280f97e262fbcde3cd7c1967ccdc5ae52a","target":"graph","created_at":"2026-07-05T09:19:20Z","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/2410.08993/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models encode the correlational structure present in natural language by fitting segments of utterances (tokens) into a high dimensional ambient latent space upon which the models then operate. We assert that in order to develop a foundational, first-principles understanding of the behavior and limitations of large language models, it is crucial to understand the topological and geometric structure of this token subspace. In this article, we present estimators for the dimension and Ricci scalar curvature of the token subspace, and apply it to three open source large language mod","authors_text":"Michael Robinson, Shauna Sweet, Sourya Dey","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DG","submitted_at":"2024-10-11T17:07:15Z","title":"The structure of the token space for large language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08993","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":"sha256:27156343ebcfac3e6c4c177738e223ca209df7d3e4b714ee0fd34dd6fe6b9daf","target":"record","created_at":"2026-07-05T09:19:20Z","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":"68e1b1ecd1e5788016ae5f86728d9a849967f54c44dcc28300288a490a216ee0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DG","submitted_at":"2024-10-11T17:07:15Z","title_canon_sha256":"c8a71b36553665a1554cc9f7e31a640b95113fd49211e94649c1ed4ebca0c89d"},"schema_version":"1.0","source":{"id":"2410.08993","kind":"arxiv","version":1}},"canonical_sha256":"042d85ad920a732b6783d62d39bc311a25f2d089c162de888da22c1b02ba2356","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"042d85ad920a732b6783d62d39bc311a25f2d089c162de888da22c1b02ba2356","first_computed_at":"2026-07-05T09:19:20.432514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:20.432514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BMPj9daoJTKFYKwY7GZ8742n3TgfmFmvooJ2/v5cyTmVBRUQKen15WfT0AMTl8ThDJN5d9IEoco7u7NIU2cwAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:20.432972Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08993","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27156343ebcfac3e6c4c177738e223ca209df7d3e4b714ee0fd34dd6fe6b9daf","sha256:4d48b314827068234cf26b287bbdf1280f97e262fbcde3cd7c1967ccdc5ae52a"],"state_sha256":"f9e5ef4d180448a3a0bc20fb317d8d8876a94ac580fdf014d0544ddd96066787"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"apRzqft7QL4X81pkfO52eap/i7uThCLpTMkV9A2d8HK+5pyhfZM9/xlxUQst7Im5yEkv1krk+Tf2sxLXmka7Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T00:14:43.573985Z","bundle_sha256":"e3219ee2232f5e40760af3a47a0f7abd710f0b0df94d45942d8fd1e5ffa98253"}}