{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UWLEIS7MXFJ6CG7SOXDTMRSZTA","short_pith_number":"pith:UWLEIS7M","canonical_record":{"source":{"id":"2607.01006","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T14:45:18Z","cross_cats_sorted":[],"title_canon_sha256":"79dfbcf5d706721996a9c337b2a2e9599e38fd30d27c1594aa766bf156096356","abstract_canon_sha256":"d6f351b6d45bc6ed156f00eaf9ce2cb10dd345fb437ecd856268e788e6c2d34f"},"schema_version":"1.0"},"canonical_sha256":"a596444becb953e11bf275c73646599825a72a1bb5466f3b6cb6d94cfb1d3005","source":{"kind":"arxiv","id":"2607.01006","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01006","created_at":"2026-07-02T01:18:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01006v1","created_at":"2026-07-02T01:18:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01006","created_at":"2026-07-02T01:18:25Z"},{"alias_kind":"pith_short_12","alias_value":"UWLEIS7MXFJ6","created_at":"2026-07-02T01:18:25Z"},{"alias_kind":"pith_short_16","alias_value":"UWLEIS7MXFJ6CG7S","created_at":"2026-07-02T01:18:25Z"},{"alias_kind":"pith_short_8","alias_value":"UWLEIS7M","created_at":"2026-07-02T01:18:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UWLEIS7MXFJ6CG7SOXDTMRSZTA","target":"record","payload":{"canonical_record":{"source":{"id":"2607.01006","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T14:45:18Z","cross_cats_sorted":[],"title_canon_sha256":"79dfbcf5d706721996a9c337b2a2e9599e38fd30d27c1594aa766bf156096356","abstract_canon_sha256":"d6f351b6d45bc6ed156f00eaf9ce2cb10dd345fb437ecd856268e788e6c2d34f"},"schema_version":"1.0"},"canonical_sha256":"a596444becb953e11bf275c73646599825a72a1bb5466f3b6cb6d94cfb1d3005","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:25.838332Z","signature_b64":"uFjJHrHeaZcNi6ur2YQbyx/fwoH8WIyjZvdOTmiqN+VpnsX6uTwXHSAVfmbezUzrcR+2eLfPTmNBNtn9zQVUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a596444becb953e11bf275c73646599825a72a1bb5466f3b6cb6d94cfb1d3005","last_reissued_at":"2026-07-02T01:18:25.837872Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:25.837872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.01006","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":"2026-07-02T01:18:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0CY44JJ7VYMPkwYh+5CP6P3pyCDIUROfagERyB4W2kEeVSchsLQIoyvjG4xbCoMWBWKbKLg5t3b5zcxoA/P7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:57:34.072925Z"},"content_sha256":"80cd934b5c072a00d84960c3ac696f003ca3d649bb1fe3b700caf774bf7ee0f2","schema_version":"1.0","event_id":"sha256:80cd934b5c072a00d84960c3ac696f003ca3d649bb1fe3b700caf774bf7ee0f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UWLEIS7MXFJ6CG7SOXDTMRSZTA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Thomas Eisenmann, Yannik Keller","submitted_at":"2026-07-01T14:45:18Z","abstract_excerpt":"Large Language Models (LLMs) represent one of the most significant advances in AI and natural language processing in recent years. Still, many pressing questions about their mechanisms, capabilities, and relationship to human cognition remain highly debated. This chapter aims to outline our current understanding of LLMs by discussing recent evidence on emerging capabilities and their mechanistic implementation within processing layers. We begin with a concise overview of the Transformer architecture, emphasizing how the attention mechanism enables training on massive datasets, allowing LLMs to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01006","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/2607.01006/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":"2026-07-02T01:18:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Qvt6Xy2mxabDWxyDSPMVoF2nzgNmJ5SA2qBLbUabkoTs4/4+U37kUobuIyiJxvkhvHKQ0N3L6fTrS9chXoACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:57:34.073746Z"},"content_sha256":"008aa8390b52254885519d05fc1b0bf40356106f98700674bdbccb75f6a5d4a9","schema_version":"1.0","event_id":"sha256:008aa8390b52254885519d05fc1b0bf40356106f98700674bdbccb75f6a5d4a9"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:UWLEIS7MXFJ6CG7SOXDTMRSZTA","target":"integrity","payload":{"note":"DOI '10.18653/v1/w18-' as printed in the bibliography is syntactically invalid and cannot resolve.","snippet":"Cur- ran Associates, Inc. Available online:https://proceedings.neurips.cc/ paper/2019/hash/4496bf24afe7fab6f046bf4923da8de6-Abstract.html. Wang, Alex, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman (2018). “GLUE: ","arxiv_id":"2607.01006","detector":"doi_compliance","evidence":{"ref_index":17,"raw_excerpt":"Cur- ran Associates, Inc. Available online:https://proceedings.neurips.cc/ paper/2019/hash/4496bf24afe7fab6f046bf4923da8de6-Abstract.html. Wang, Alex, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman (2018). “GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding”. In:Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpret","verdict_class":"incontrovertible","doi_as_printed":"10.18653/v1/w18-"},"severity":"critical","ref_index":17,"audited_at":"2026-07-09T09:26:19.949974Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/w18-","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"broken_identifier","evidence_hash":"983f2e2fec8da1c95031d80501e6adfca0c6952236fbea360f18945c0e4008ca","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":8195,"payload_sha256":"b68529e9f4d8537ab7ddc7a91a2c062baf71aba3cfd89a91f9f77260b495ee84","signature_b64":"+kOD6Ml0pKIFBjEcfwn0HwaJXaf++YGW08aenjBBKffnMtXBY1WvJIODQoyLw/cQBLl3W37b4tMhX6+lGK7ZCg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-09T09:27:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kREQj75H+vWm3iY1znCdtb9tNSbujv8ncIOZR0URBSYpSqC0oZ0+4+dRisN4iTh8Os34xk4I09jrOnIduYDcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:57:34.079465Z"},"content_sha256":"933155bca2241d35ce5e4c44d1871676c778e8ca8cf0d786e1ecd5c003e4686f","schema_version":"1.0","event_id":"sha256:933155bca2241d35ce5e4c44d1871676c778e8ca8cf0d786e1ecd5c003e4686f"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:UWLEIS7MXFJ6CG7SOXDTMRSZTA","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2025.findings-acl.1242.Available) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Ed. by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar. Vi- enna, Austria: Association for Computational Linguistics, pp. 24208–24213. doi:10.18653/v1/2025.findings- acl.1242. Available online:https: //aclantholo","arxiv_id":"2607.01006","detector":"doi_compliance","evidence":{"ref_index":11,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Ed. by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar. Vi- enna, Austria: Association for Computational Linguistics, pp. 24208–24213. doi:10.18653/v1/2025.findings- acl.1242. Available online:https: //aclantholo","reconstructed_doi":"10.18653/v1/2025.findings-acl.1242.Available"},"severity":"advisory","ref_index":11,"audited_at":"2026-07-09T09:26:19.949974Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2025.findings-acl.1242.Available","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"df938a586fc76ecf529ba9f45b7007dd8bdcb30a0451e765818dec0c31966324","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":8194,"payload_sha256":"de93c5dedc8020b4719d4a5b9e5d5988b002a4c2b4aa98ed641883b26f01053b","signature_b64":"QYN8cPskV54vHvhHUaXY2fwgTB23JckhbVbmRSxt04mKqAEJq3fJaPWaWI1QWCKLaPt4LQK9Ffptz6Kp1OQiCA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-09T09:27:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8jNFUfxM4l5h8F66ygGkGjSzJPjTdprkylK+lXa5aXXw7j7zvOMWFr7Q/RCHxjt4a77vvAgPs7emI1FLM2vyDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:57:34.081172Z"},"content_sha256":"adc1fe18aa794261dec7d8a22fcb2ca24d52ebf9a77598cbb04685ef6c44f3be","schema_version":"1.0","event_id":"sha256:adc1fe18aa794261dec7d8a22fcb2ca24d52ebf9a77598cbb04685ef6c44f3be"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:UWLEIS7MXFJ6CG7SOXDTMRSZTA","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2308.01906.Available) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Available online: https : / / www . hepi . ac . uk / 2025 / 02 / 26 / student - generative - ai - survey-2025/. Gaur, Vedant and Nikunj Saunshi (2023).Reasoning in Large Language Mod- els Through Symbolic Math Word Problems.doi:10.48550/arX","arxiv_id":"2607.01006","detector":"doi_compliance","evidence":{"ref_index":9,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Available online: https : / / www . hepi . ac . uk / 2025 / 02 / 26 / student - generative - ai - survey-2025/. Gaur, Vedant and Nikunj Saunshi (2023).Reasoning in Large Language Mod- els Through Symbolic Math Word Problems.doi:10.48550/arX","reconstructed_doi":"10.48550/arXiv.2308.01906.Available"},"severity":"advisory","ref_index":9,"audited_at":"2026-07-09T09:26:19.949974Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/arXiv.2308.01906.Available","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"a80ab1e7f3bca1ba658d36696343fdcba8971ca1484085347445117d79f2fa0e","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":8193,"payload_sha256":"467167d435f3b5dd837c1ad6b3046ad6bb8f2272db6973a721bd0d68b8494bb6","signature_b64":"rB8VWkiPYAFgljl/ra57IbhqPw25ZxcYgoHorVpHy+6GPessar50rZ7K+ZjhwSYjtbF74QFMKV54iLkVrIApCg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-09T09:27:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"45ipnavuw2Q3nzdXd+KvNd/NYzsa/jtS6x6jBfATgVrq+6qIvfcN5wDyQf0uehVy8Ft/whQPbmvsqkyr+VWFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:57:34.085270Z"},"content_sha256":"4a1918195f6842d4fd4aac38f335b0da89ab3a8f6f86f84d447e56967ba2c1d5","schema_version":"1.0","event_id":"sha256:4a1918195f6842d4fd4aac38f335b0da89ab3a8f6f86f84d447e56967ba2c1d5"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:UWLEIS7MXFJ6CG7SOXDTMRSZTA","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2023.emnlp) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Available online:https://aclanthology.org/N19-1423/. Dijk, Bram van, Tom Kouwenhoven, Marco Spruit, and Max Johannes van Duijn (2023). “Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understandi","arxiv_id":"2607.01006","detector":"doi_compliance","evidence":{"ref_index":6,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Available online:https://aclanthology.org/N19-1423/. Dijk, Bram van, Tom Kouwenhoven, Marco Spruit, and Max Johannes van Duijn (2023). “Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understandi","reconstructed_doi":"10.18653/v1/2023.emnlp"},"severity":"advisory","ref_index":6,"audited_at":"2026-07-09T09:26:19.949974Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2023.emnlp","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"33ba3c954a6389cd7de94b49c221b4018901cacf7a73cd0a711ed176cd21d4a6","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":8192,"payload_sha256":"72506d941f3ed773cdf98650296f83cd14ba7fc537a6ceb06953733478a3c543","signature_b64":"4y7b39L4rcE+TxguBZU39/0wShWt1B29YyBRNEdOpR5vxR3uX5seki5K7bLy78dqUb2muCey/3GBgfB7Ntn/BQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-09T09:27:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WmDi9ANCrCijl0jTMbEugK7hk6yn5GOl8Z379XyrcWyPz+REksbwBFLANoVdAuFJnhzGzNPfJUBJXs81zI/RCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:57:34.086171Z"},"content_sha256":"a6beba66dc85a5e17a3b91d973d5c6a37411a336a7979dabfa8a0a6ddc89b948","schema_version":"1.0","event_id":"sha256:a6beba66dc85a5e17a3b91d973d5c6a37411a336a7979dabfa8a0a6ddc89b948"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UWLEIS7MXFJ6CG7SOXDTMRSZTA/bundle.json","state_url":"https://pith.science/pith/UWLEIS7MXFJ6CG7SOXDTMRSZTA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UWLEIS7MXFJ6CG7SOXDTMRSZTA/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":"2026-08-04T06:57:34Z","links":{"resolver":"https://pith.science/pith/UWLEIS7MXFJ6CG7SOXDTMRSZTA","bundle":"https://pith.science/pith/UWLEIS7MXFJ6CG7SOXDTMRSZTA/bundle.json","state":"https://pith.science/pith/UWLEIS7MXFJ6CG7SOXDTMRSZTA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UWLEIS7MXFJ6CG7SOXDTMRSZTA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UWLEIS7MXFJ6CG7SOXDTMRSZTA","merge_version":"pith-open-graph-merge-v1","event_count":6,"valid_event_count":6,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d6f351b6d45bc6ed156f00eaf9ce2cb10dd345fb437ecd856268e788e6c2d34f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T14:45:18Z","title_canon_sha256":"79dfbcf5d706721996a9c337b2a2e9599e38fd30d27c1594aa766bf156096356"},"schema_version":"1.0","source":{"id":"2607.01006","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01006","created_at":"2026-07-02T01:18:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01006v1","created_at":"2026-07-02T01:18:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01006","created_at":"2026-07-02T01:18:25Z"},{"alias_kind":"pith_short_12","alias_value":"UWLEIS7MXFJ6","created_at":"2026-07-02T01:18:25Z"},{"alias_kind":"pith_short_16","alias_value":"UWLEIS7MXFJ6CG7S","created_at":"2026-07-02T01:18:25Z"},{"alias_kind":"pith_short_8","alias_value":"UWLEIS7M","created_at":"2026-07-02T01:18:25Z"}],"graph_snapshots":[{"event_id":"sha256:008aa8390b52254885519d05fc1b0bf40356106f98700674bdbccb75f6a5d4a9","target":"graph","created_at":"2026-07-02T01:18:25Z","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/2607.01006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) represent one of the most significant advances in AI and natural language processing in recent years. Still, many pressing questions about their mechanisms, capabilities, and relationship to human cognition remain highly debated. This chapter aims to outline our current understanding of LLMs by discussing recent evidence on emerging capabilities and their mechanistic implementation within processing layers. We begin with a concise overview of the Transformer architecture, emphasizing how the attention mechanism enables training on massive datasets, allowing LLMs to","authors_text":"Thomas Eisenmann, Yannik Keller","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T14:45:18Z","title":"Understanding Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01006","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":"sha256:80cd934b5c072a00d84960c3ac696f003ca3d649bb1fe3b700caf774bf7ee0f2","target":"record","created_at":"2026-07-02T01:18:25Z","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":"d6f351b6d45bc6ed156f00eaf9ce2cb10dd345fb437ecd856268e788e6c2d34f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T14:45:18Z","title_canon_sha256":"79dfbcf5d706721996a9c337b2a2e9599e38fd30d27c1594aa766bf156096356"},"schema_version":"1.0","source":{"id":"2607.01006","kind":"arxiv","version":1}},"canonical_sha256":"a596444becb953e11bf275c73646599825a72a1bb5466f3b6cb6d94cfb1d3005","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a596444becb953e11bf275c73646599825a72a1bb5466f3b6cb6d94cfb1d3005","first_computed_at":"2026-07-02T01:18:25.837872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:18:25.837872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uFjJHrHeaZcNi6ur2YQbyx/fwoH8WIyjZvdOTmiqN+VpnsX6uTwXHSAVfmbezUzrcR+2eLfPTmNBNtn9zQVUCw==","signature_status":"signed_v1","signed_at":"2026-07-02T01:18:25.838332Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01006","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:4a1918195f6842d4fd4aac38f335b0da89ab3a8f6f86f84d447e56967ba2c1d5","sha256:933155bca2241d35ce5e4c44d1871676c778e8ca8cf0d786e1ecd5c003e4686f","sha256:a6beba66dc85a5e17a3b91d973d5c6a37411a336a7979dabfa8a0a6ddc89b948","sha256:adc1fe18aa794261dec7d8a22fcb2ca24d52ebf9a77598cbb04685ef6c44f3be"]}],"invalid_events":[],"applied_event_ids":["sha256:80cd934b5c072a00d84960c3ac696f003ca3d649bb1fe3b700caf774bf7ee0f2","sha256:008aa8390b52254885519d05fc1b0bf40356106f98700674bdbccb75f6a5d4a9"],"state_sha256":"667bcaf335238008fae0c6c7a3c460c00aab8b980508872d5a743bcf46a1a00f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sezJu6KOkkG8HU3ogQOX2+MePvxg7HuWvCo8ufzD3kE0UcJmo2OnZwkDEWa3j8aEj0AsUa3GT+Hs7FHDO+8kAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:57:34.143018Z","bundle_sha256":"c567908089a1b239408837b5329455e5987fece1069474d4b92369c3c85317b3"}}