{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:N5HVAVYLAFC56L7NWBRK36RJWX","short_pith_number":"pith:N5HVAVYL","canonical_record":{"source":{"id":"2310.02207","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-03T17:06:52Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"28e4a950a990b8fb847e5adb498ce81fda88e751981d6f4f22ecec700262fb4f","abstract_canon_sha256":"fdf392c2afec35a9552d46cae7e1757cda685419f97be8826e72c144d8a6af1b"},"schema_version":"1.0"},"canonical_sha256":"6f4f50570b0145df2fedb062adfa29b5f542ee09bb77ec15449b6bb1ad96cf62","source":{"kind":"arxiv","id":"2310.02207","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02207","created_at":"2026-07-05T07:51:33Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02207v3","created_at":"2026-07-05T07:51:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02207","created_at":"2026-07-05T07:51:33Z"},{"alias_kind":"pith_short_12","alias_value":"N5HVAVYLAFC5","created_at":"2026-07-05T07:51:33Z"},{"alias_kind":"pith_short_16","alias_value":"N5HVAVYLAFC56L7N","created_at":"2026-07-05T07:51:33Z"},{"alias_kind":"pith_short_8","alias_value":"N5HVAVYL","created_at":"2026-07-05T07:51:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:N5HVAVYLAFC56L7NWBRK36RJWX","target":"record","payload":{"canonical_record":{"source":{"id":"2310.02207","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-03T17:06:52Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"28e4a950a990b8fb847e5adb498ce81fda88e751981d6f4f22ecec700262fb4f","abstract_canon_sha256":"fdf392c2afec35a9552d46cae7e1757cda685419f97be8826e72c144d8a6af1b"},"schema_version":"1.0"},"canonical_sha256":"6f4f50570b0145df2fedb062adfa29b5f542ee09bb77ec15449b6bb1ad96cf62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:33.115843Z","signature_b64":"DwYZQmSDxuuyh3g5JFIGedW/KrK1X6GdPQixibwd3XEopclD9AIWy/3tYEL6V+LRGOmDhjdX+WHh9Yw/IybTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f4f50570b0145df2fedb062adfa29b5f542ee09bb77ec15449b6bb1ad96cf62","last_reissued_at":"2026-07-05T07:51:33.115254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:33.115254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.02207","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:51:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ApS7It22sq2CpoeXR33SPHVQrafq115JeReLYf3Rq7tmrvz98lYHRVPWrJbzdJBs/nVz4q0VLv99bs7mY29ICQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:28:46.053672Z"},"content_sha256":"3343830c8f0ad5f768a3eb14e2ca03b287b6130dce7961d37fe04536c5271502","schema_version":"1.0","event_id":"sha256:3343830c8f0ad5f768a3eb14e2ca03b287b6130dce7961d37fe04536c5271502"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:N5HVAVYLAFC56L7NWBRK36RJWX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Models Represent Space and Time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Max Tegmark, Wes Gurnee","submitted_at":"2023-10-03T17:06:52Z","abstract_excerpt":"The capabilities of large language models (LLMs) have sparked debate over whether such systems just learn an enormous collection of superficial statistics or a set of more coherent and grounded representations that reflect the real world. We find evidence for the latter by analyzing the learned representations of three spatial datasets (world, US, NYC places) and three temporal datasets (historical figures, artworks, news headlines) in the Llama-2 family of models. We discover that LLMs learn linear representations of space and time across multiple scales. These representations are robust to p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02207","kind":"arxiv","version":3},"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/2310.02207/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":"2026-07-05T07:51:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AXOpofiXFKGc5au9ZGVZS7QzhXzJ8/SHCzZMvDoISQUwBIh04/5Qhmd8YqSjVhx1s94Ryxj2b9MNb0Mrs2JOCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:28:46.054418Z"},"content_sha256":"b9cb63735e5da903685f8cf2c41746f236cbd93287223a7552454ff60d4b5121","schema_version":"1.0","event_id":"sha256:b9cb63735e5da903685f8cf2c41746f236cbd93287223a7552454ff60d4b5121"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N5HVAVYLAFC56L7NWBRK36RJWX/bundle.json","state_url":"https://pith.science/pith/N5HVAVYLAFC56L7NWBRK36RJWX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N5HVAVYLAFC56L7NWBRK36RJWX/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":"2026-08-11T08:28:46Z","links":{"resolver":"https://pith.science/pith/N5HVAVYLAFC56L7NWBRK36RJWX","bundle":"https://pith.science/pith/N5HVAVYLAFC56L7NWBRK36RJWX/bundle.json","state":"https://pith.science/pith/N5HVAVYLAFC56L7NWBRK36RJWX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N5HVAVYLAFC56L7NWBRK36RJWX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:N5HVAVYLAFC56L7NWBRK36RJWX","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":"fdf392c2afec35a9552d46cae7e1757cda685419f97be8826e72c144d8a6af1b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-03T17:06:52Z","title_canon_sha256":"28e4a950a990b8fb847e5adb498ce81fda88e751981d6f4f22ecec700262fb4f"},"schema_version":"1.0","source":{"id":"2310.02207","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02207","created_at":"2026-07-05T07:51:33Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02207v3","created_at":"2026-07-05T07:51:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02207","created_at":"2026-07-05T07:51:33Z"},{"alias_kind":"pith_short_12","alias_value":"N5HVAVYLAFC5","created_at":"2026-07-05T07:51:33Z"},{"alias_kind":"pith_short_16","alias_value":"N5HVAVYLAFC56L7N","created_at":"2026-07-05T07:51:33Z"},{"alias_kind":"pith_short_8","alias_value":"N5HVAVYL","created_at":"2026-07-05T07:51:33Z"}],"graph_snapshots":[{"event_id":"sha256:b9cb63735e5da903685f8cf2c41746f236cbd93287223a7552454ff60d4b5121","target":"graph","created_at":"2026-07-05T07:51:33Z","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/2310.02207/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The capabilities of large language models (LLMs) have sparked debate over whether such systems just learn an enormous collection of superficial statistics or a set of more coherent and grounded representations that reflect the real world. We find evidence for the latter by analyzing the learned representations of three spatial datasets (world, US, NYC places) and three temporal datasets (historical figures, artworks, news headlines) in the Llama-2 family of models. We discover that LLMs learn linear representations of space and time across multiple scales. These representations are robust to p","authors_text":"Max Tegmark, Wes Gurnee","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-03T17:06:52Z","title":"Language Models Represent Space and Time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02207","kind":"arxiv","version":3},"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":"sha256:3343830c8f0ad5f768a3eb14e2ca03b287b6130dce7961d37fe04536c5271502","target":"record","created_at":"2026-07-05T07:51:33Z","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":"fdf392c2afec35a9552d46cae7e1757cda685419f97be8826e72c144d8a6af1b","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-03T17:06:52Z","title_canon_sha256":"28e4a950a990b8fb847e5adb498ce81fda88e751981d6f4f22ecec700262fb4f"},"schema_version":"1.0","source":{"id":"2310.02207","kind":"arxiv","version":3}},"canonical_sha256":"6f4f50570b0145df2fedb062adfa29b5f542ee09bb77ec15449b6bb1ad96cf62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f4f50570b0145df2fedb062adfa29b5f542ee09bb77ec15449b6bb1ad96cf62","first_computed_at":"2026-07-05T07:51:33.115254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:33.115254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DwYZQmSDxuuyh3g5JFIGedW/KrK1X6GdPQixibwd3XEopclD9AIWy/3tYEL6V+LRGOmDhjdX+WHh9Yw/IybTCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:33.115843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.02207","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3343830c8f0ad5f768a3eb14e2ca03b287b6130dce7961d37fe04536c5271502","sha256:b9cb63735e5da903685f8cf2c41746f236cbd93287223a7552454ff60d4b5121"],"state_sha256":"6f0848d81790b7ba5dc4a9730285a2c680f128db9eae149565d7b9feb7034b69"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+PdxT/JZVjzvgpHK0RZa+ZKG6wGUAkB804UXzVr1eiFpxpag3zkGUdwTHr7lFqpnxEQ7GDcZ1xlX5nRk+wWfCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:28:46.062458Z","bundle_sha256":"9de87f57efaa46747ac5e5866ac48cfed7b951b5a48aa939f81bc0ea5472295b"}}