{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JXRIN2LT74BASU2K6MB6DS4NTA","short_pith_number":"pith:JXRIN2LT","canonical_record":{"source":{"id":"2405.15471","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T11:49:07Z","cross_cats_sorted":[],"title_canon_sha256":"a2539b6004602d2f985a84423f763427bb11d4940c35a1285de98945d3ed8ac7","abstract_canon_sha256":"1920a28b8551f9be73209fc1653a6fe948e4f58521ba1d791234e021e9e88ea9"},"schema_version":"1.0"},"canonical_sha256":"4de286e973ff0209534af303e1cb8d980773d5838ea3cec5fb3ea387b2d02ef4","source":{"kind":"arxiv","id":"2405.15471","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15471","created_at":"2026-07-05T10:56:06Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15471v4","created_at":"2026-07-05T10:56:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15471","created_at":"2026-07-05T10:56:06Z"},{"alias_kind":"pith_short_12","alias_value":"JXRIN2LT74BA","created_at":"2026-07-05T10:56:06Z"},{"alias_kind":"pith_short_16","alias_value":"JXRIN2LT74BASU2K","created_at":"2026-07-05T10:56:06Z"},{"alias_kind":"pith_short_8","alias_value":"JXRIN2LT","created_at":"2026-07-05T10:56:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JXRIN2LT74BASU2K6MB6DS4NTA","target":"record","payload":{"canonical_record":{"source":{"id":"2405.15471","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T11:49:07Z","cross_cats_sorted":[],"title_canon_sha256":"a2539b6004602d2f985a84423f763427bb11d4940c35a1285de98945d3ed8ac7","abstract_canon_sha256":"1920a28b8551f9be73209fc1653a6fe948e4f58521ba1d791234e021e9e88ea9"},"schema_version":"1.0"},"canonical_sha256":"4de286e973ff0209534af303e1cb8d980773d5838ea3cec5fb3ea387b2d02ef4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:06.396726Z","signature_b64":"F/aLUnXwSodASwfprR/MKLMCTaOc+6jITx/v/QD5+DeREGFjut7ji+sXZiQpCedHwDgi8q2wpZ1KabJxudP0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4de286e973ff0209534af303e1cb8d980773d5838ea3cec5fb3ea387b2d02ef4","last_reissued_at":"2026-07-05T10:56:06.396093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:06.396093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.15471","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:56:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0toKB4PE/Y0Qz4TXdrAdLfqyycujTNzaYKxeNSQ2UJqbaAQar4nankynP3r5CK3oAAwZ6MSFMn5jGLWJ0xZ5Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T22:35:50.130262Z"},"content_sha256":"f2153681f7c0858fb21352da4cafe34b823500312e78dc18250b54b744751e1c","schema_version":"1.0","event_id":"sha256:f2153681f7c0858fb21352da4cafe34b823500312e78dc18250b54b744751e1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JXRIN2LT74BASU2K6MB6DS4NTA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Emergence of a High-Dimensional Abstraction Phase in Language Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alessandro Laio, Corentin Kervadec, Diego Doimo, Emily Cheng, Iuri Macocco, Jade Yu, Marco Baroni","submitted_at":"2024-05-24T11:49:07Z","abstract_excerpt":"A language model (LM) is a mapping from a linguistic context to an output token. However, much remains to be known about this mapping, including how its geometric properties relate to its function. We take a high-level geometric approach to its analysis, observing, across five pre-trained transformer-based LMs and three input datasets, a distinct phase characterized by high intrinsic dimensionality. During this phase, representations (1) correspond to the first full linguistic abstraction of the input; (2) are the first to viably transfer to downstream tasks; (3) predict each other across diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15471","kind":"arxiv","version":4},"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/2405.15471/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":"2026-07-05T10:56:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ssdh85+/uh1n1EgmWybFGL16iyY42mCatSpulkg3LgiKZ4AZbaCDIx9dVQTVKr61qRS5ttxvWxM7X3AoSoV4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T22:35:50.130664Z"},"content_sha256":"3df2faccb3a96cc455c86b078f9433acb91ec3a8b52f5c3fd51398eccb10992b","schema_version":"1.0","event_id":"sha256:3df2faccb3a96cc455c86b078f9433acb91ec3a8b52f5c3fd51398eccb10992b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JXRIN2LT74BASU2K6MB6DS4NTA/bundle.json","state_url":"https://pith.science/pith/JXRIN2LT74BASU2K6MB6DS4NTA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JXRIN2LT74BASU2K6MB6DS4NTA/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":"2026-07-11T22:35:50Z","links":{"resolver":"https://pith.science/pith/JXRIN2LT74BASU2K6MB6DS4NTA","bundle":"https://pith.science/pith/JXRIN2LT74BASU2K6MB6DS4NTA/bundle.json","state":"https://pith.science/pith/JXRIN2LT74BASU2K6MB6DS4NTA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JXRIN2LT74BASU2K6MB6DS4NTA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JXRIN2LT74BASU2K6MB6DS4NTA","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":"1920a28b8551f9be73209fc1653a6fe948e4f58521ba1d791234e021e9e88ea9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T11:49:07Z","title_canon_sha256":"a2539b6004602d2f985a84423f763427bb11d4940c35a1285de98945d3ed8ac7"},"schema_version":"1.0","source":{"id":"2405.15471","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15471","created_at":"2026-07-05T10:56:06Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15471v4","created_at":"2026-07-05T10:56:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15471","created_at":"2026-07-05T10:56:06Z"},{"alias_kind":"pith_short_12","alias_value":"JXRIN2LT74BA","created_at":"2026-07-05T10:56:06Z"},{"alias_kind":"pith_short_16","alias_value":"JXRIN2LT74BASU2K","created_at":"2026-07-05T10:56:06Z"},{"alias_kind":"pith_short_8","alias_value":"JXRIN2LT","created_at":"2026-07-05T10:56:06Z"}],"graph_snapshots":[{"event_id":"sha256:3df2faccb3a96cc455c86b078f9433acb91ec3a8b52f5c3fd51398eccb10992b","target":"graph","created_at":"2026-07-05T10:56:06Z","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/2405.15471/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A language model (LM) is a mapping from a linguistic context to an output token. However, much remains to be known about this mapping, including how its geometric properties relate to its function. We take a high-level geometric approach to its analysis, observing, across five pre-trained transformer-based LMs and three input datasets, a distinct phase characterized by high intrinsic dimensionality. During this phase, representations (1) correspond to the first full linguistic abstraction of the input; (2) are the first to viably transfer to downstream tasks; (3) predict each other across diff","authors_text":"Alessandro Laio, Corentin Kervadec, Diego Doimo, Emily Cheng, Iuri Macocco, Jade Yu, Marco Baroni","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T11:49:07Z","title":"Emergence of a High-Dimensional Abstraction Phase in Language Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15471","kind":"arxiv","version":4},"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:f2153681f7c0858fb21352da4cafe34b823500312e78dc18250b54b744751e1c","target":"record","created_at":"2026-07-05T10:56:06Z","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":"1920a28b8551f9be73209fc1653a6fe948e4f58521ba1d791234e021e9e88ea9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T11:49:07Z","title_canon_sha256":"a2539b6004602d2f985a84423f763427bb11d4940c35a1285de98945d3ed8ac7"},"schema_version":"1.0","source":{"id":"2405.15471","kind":"arxiv","version":4}},"canonical_sha256":"4de286e973ff0209534af303e1cb8d980773d5838ea3cec5fb3ea387b2d02ef4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4de286e973ff0209534af303e1cb8d980773d5838ea3cec5fb3ea387b2d02ef4","first_computed_at":"2026-07-05T10:56:06.396093Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:56:06.396093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F/aLUnXwSodASwfprR/MKLMCTaOc+6jITx/v/QD5+DeREGFjut7ji+sXZiQpCedHwDgi8q2wpZ1KabJxudP0BA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:56:06.396726Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15471","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2153681f7c0858fb21352da4cafe34b823500312e78dc18250b54b744751e1c","sha256:3df2faccb3a96cc455c86b078f9433acb91ec3a8b52f5c3fd51398eccb10992b"],"state_sha256":"5b3217f8b145f4aba960d7cc78c0c0581216aa55ded9ba91d0b05a4fdae89f6a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C7HnARnf+AKEqZGQLmqtRC5W0tZXYrg9BZqCyfg01fZEXLkeoxpYO6YJ9FqdzFlZWVahI06Woo3Zt2kX8GnLDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T22:35:50.136637Z","bundle_sha256":"0e87bf5298d99fdbf0f6e9c0e699220494230479aa54851b0607faefab72e0f0"}}