{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GN7LCM6CZOBYJ7GTNJAUPQNJL7","short_pith_number":"pith:GN7LCM6C","canonical_record":{"source":{"id":"2410.01537","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-02T13:28:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2f46bffa62fae48a7a9d23c9ba9db7ccc588eff60a40a605f0c630988af1ca12","abstract_canon_sha256":"b05316fcc0a0a1adf311f498563f546da915c347598e98d0a5dff7aebda1169f"},"schema_version":"1.0"},"canonical_sha256":"337eb133c2cb8384fcd36a4147c1a95fc43191c1fa0594c14179cfe1f85a3c61","source":{"kind":"arxiv","id":"2410.01537","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01537","created_at":"2026-07-05T10:19:55Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01537v2","created_at":"2026-07-05T10:19:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01537","created_at":"2026-07-05T10:19:55Z"},{"alias_kind":"pith_short_12","alias_value":"GN7LCM6CZOBY","created_at":"2026-07-05T10:19:55Z"},{"alias_kind":"pith_short_16","alias_value":"GN7LCM6CZOBYJ7GT","created_at":"2026-07-05T10:19:55Z"},{"alias_kind":"pith_short_8","alias_value":"GN7LCM6C","created_at":"2026-07-05T10:19:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GN7LCM6CZOBYJ7GTNJAUPQNJL7","target":"record","payload":{"canonical_record":{"source":{"id":"2410.01537","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-02T13:28:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2f46bffa62fae48a7a9d23c9ba9db7ccc588eff60a40a605f0c630988af1ca12","abstract_canon_sha256":"b05316fcc0a0a1adf311f498563f546da915c347598e98d0a5dff7aebda1169f"},"schema_version":"1.0"},"canonical_sha256":"337eb133c2cb8384fcd36a4147c1a95fc43191c1fa0594c14179cfe1f85a3c61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:55.971001Z","signature_b64":"3gzX3YYh9RvPeB7z7hAyA/Oqbju1PkOV3GLw08npJCyRVhsL+c7JzevSdik1QjQItA/0Dgw8SrbEYZuuapwIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"337eb133c2cb8384fcd36a4147c1a95fc43191c1fa0594c14179cfe1f85a3c61","last_reissued_at":"2026-07-05T10:19:55.970385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:55.970385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.01537","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:19:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TXs0h2ZbHYdqwUlg77U4EHEvTd1FMzVrtiAKiDg9tutFuAoupdujqOmqkK1t0odigdNci8Y7Jw23Ghek0qhNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:52:41.637595Z"},"content_sha256":"8edb307780cea4e0d6256fa7a50e622261f3e6cc2425d7ca3389f4775adc586e","schema_version":"1.0","event_id":"sha256:8edb307780cea4e0d6256fa7a50e622261f3e6cc2425d7ca3389f4775adc586e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GN7LCM6CZOBYJ7GTNJAUPQNJL7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attention layers provably solve single-location regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Claire Boyer, G\\'erard Biau, Pierre Marion, Rapha\\\"el Berthier","submitted_at":"2024-10-02T13:28:02Z","abstract_excerpt":"Attention-based models, such as Transformer, excel across various tasks but lack a comprehensive theoretical understanding, especially regarding token-wise sparsity and internal linear representations. To address this gap, we introduce the single-location regression task, where only one token in a sequence determines the output, and its position is a latent random variable, retrievable via a linear projection of the input. To solve this task, we propose a dedicated predictor, which turns out to be a simplified version of a non-linear self-attention layer. We study its theoretical properties, b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01537","kind":"arxiv","version":2},"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/2410.01537/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":"2026-07-05T10:19:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CXAMRUlEZnWDF1SwE2pEOVtOhw5HNCxFfhtTpzWZpGJmYP/xqqBn5ecMkSVDavFKqSxoaeflA7ug/FDfRbM1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:52:41.638132Z"},"content_sha256":"af232a8384e425be9ef528089858d8e75c81f4d5764720de87d51b637622b5f4","schema_version":"1.0","event_id":"sha256:af232a8384e425be9ef528089858d8e75c81f4d5764720de87d51b637622b5f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GN7LCM6CZOBYJ7GTNJAUPQNJL7/bundle.json","state_url":"https://pith.science/pith/GN7LCM6CZOBYJ7GTNJAUPQNJL7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GN7LCM6CZOBYJ7GTNJAUPQNJL7/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":"2026-08-09T18:52:41Z","links":{"resolver":"https://pith.science/pith/GN7LCM6CZOBYJ7GTNJAUPQNJL7","bundle":"https://pith.science/pith/GN7LCM6CZOBYJ7GTNJAUPQNJL7/bundle.json","state":"https://pith.science/pith/GN7LCM6CZOBYJ7GTNJAUPQNJL7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GN7LCM6CZOBYJ7GTNJAUPQNJL7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GN7LCM6CZOBYJ7GTNJAUPQNJL7","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":"b05316fcc0a0a1adf311f498563f546da915c347598e98d0a5dff7aebda1169f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-02T13:28:02Z","title_canon_sha256":"2f46bffa62fae48a7a9d23c9ba9db7ccc588eff60a40a605f0c630988af1ca12"},"schema_version":"1.0","source":{"id":"2410.01537","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01537","created_at":"2026-07-05T10:19:55Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01537v2","created_at":"2026-07-05T10:19:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01537","created_at":"2026-07-05T10:19:55Z"},{"alias_kind":"pith_short_12","alias_value":"GN7LCM6CZOBY","created_at":"2026-07-05T10:19:55Z"},{"alias_kind":"pith_short_16","alias_value":"GN7LCM6CZOBYJ7GT","created_at":"2026-07-05T10:19:55Z"},{"alias_kind":"pith_short_8","alias_value":"GN7LCM6C","created_at":"2026-07-05T10:19:55Z"}],"graph_snapshots":[{"event_id":"sha256:af232a8384e425be9ef528089858d8e75c81f4d5764720de87d51b637622b5f4","target":"graph","created_at":"2026-07-05T10:19:55Z","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/2410.01537/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Attention-based models, such as Transformer, excel across various tasks but lack a comprehensive theoretical understanding, especially regarding token-wise sparsity and internal linear representations. To address this gap, we introduce the single-location regression task, where only one token in a sequence determines the output, and its position is a latent random variable, retrievable via a linear projection of the input. To solve this task, we propose a dedicated predictor, which turns out to be a simplified version of a non-linear self-attention layer. We study its theoretical properties, b","authors_text":"Claire Boyer, G\\'erard Biau, Pierre Marion, Rapha\\\"el Berthier","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-02T13:28:02Z","title":"Attention layers provably solve single-location regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01537","kind":"arxiv","version":2},"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":"sha256:8edb307780cea4e0d6256fa7a50e622261f3e6cc2425d7ca3389f4775adc586e","target":"record","created_at":"2026-07-05T10:19:55Z","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":"b05316fcc0a0a1adf311f498563f546da915c347598e98d0a5dff7aebda1169f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-02T13:28:02Z","title_canon_sha256":"2f46bffa62fae48a7a9d23c9ba9db7ccc588eff60a40a605f0c630988af1ca12"},"schema_version":"1.0","source":{"id":"2410.01537","kind":"arxiv","version":2}},"canonical_sha256":"337eb133c2cb8384fcd36a4147c1a95fc43191c1fa0594c14179cfe1f85a3c61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"337eb133c2cb8384fcd36a4147c1a95fc43191c1fa0594c14179cfe1f85a3c61","first_computed_at":"2026-07-05T10:19:55.970385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:55.970385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3gzX3YYh9RvPeB7z7hAyA/Oqbju1PkOV3GLw08npJCyRVhsL+c7JzevSdik1QjQItA/0Dgw8SrbEYZuuapwIBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:55.971001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01537","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8edb307780cea4e0d6256fa7a50e622261f3e6cc2425d7ca3389f4775adc586e","sha256:af232a8384e425be9ef528089858d8e75c81f4d5764720de87d51b637622b5f4"],"state_sha256":"764e3acbad844eab2c28048c1cf5a585070aec43e68e4726ca299b5e474de304"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VPscLLSBGzeOPejAcKq69bCoASlrlKA50w7b7MJvzdmulKho0APrgQQ49bdfQLfqZwNqrUqmCW1P9gHO2wQgAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:52:41.644019Z","bundle_sha256":"5ef1a79785ddced883569634850be2830650cc1117557f83f90b5e24085c17c4"}}