{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:G22N2X3KENBGQCSEF3B3IMJHE3","short_pith_number":"pith:G22N2X3K","canonical_record":{"source":{"id":"2408.15138","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T15:23:09Z","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.CL"],"title_canon_sha256":"f486b29307b15b8ccf35e84d055a39cc504f57cc5b392918fae86cae2e8b49cf","abstract_canon_sha256":"c4a068a3dfba61dd50d39107df58db5591880c37fa8cd2b9e2494e83e4d4ecc2"},"schema_version":"1.0"},"canonical_sha256":"36b4dd5f6a2342680a442ec3b4312726d964f5a03e8b725e5a1b04d75157dbdf","source":{"kind":"arxiv","id":"2408.15138","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15138","created_at":"2026-07-05T11:19:00Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15138v3","created_at":"2026-07-05T11:19:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15138","created_at":"2026-07-05T11:19:00Z"},{"alias_kind":"pith_short_12","alias_value":"G22N2X3KENBG","created_at":"2026-07-05T11:19:00Z"},{"alias_kind":"pith_short_16","alias_value":"G22N2X3KENBGQCSE","created_at":"2026-07-05T11:19:00Z"},{"alias_kind":"pith_short_8","alias_value":"G22N2X3K","created_at":"2026-07-05T11:19:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:G22N2X3KENBGQCSEF3B3IMJHE3","target":"record","payload":{"canonical_record":{"source":{"id":"2408.15138","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T15:23:09Z","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.CL"],"title_canon_sha256":"f486b29307b15b8ccf35e84d055a39cc504f57cc5b392918fae86cae2e8b49cf","abstract_canon_sha256":"c4a068a3dfba61dd50d39107df58db5591880c37fa8cd2b9e2494e83e4d4ecc2"},"schema_version":"1.0"},"canonical_sha256":"36b4dd5f6a2342680a442ec3b4312726d964f5a03e8b725e5a1b04d75157dbdf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:00.267170Z","signature_b64":"3DkmRCvgb48sNZJCTO+xFU1APkoWjhAdIdPYZPhQIxbotBgWtN3YOc19oeh+oJtsv5pQxC68uK2T8+lWIgEXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36b4dd5f6a2342680a442ec3b4312726d964f5a03e8b725e5a1b04d75157dbdf","last_reissued_at":"2026-07-05T11:19:00.266675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:00.266675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.15138","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":"2026-07-05T11:19:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LM+nZRKPngE6535LQ+zK/0r4XbsgnF5RrYL9Z0Q7d2fN4v2V1+KLs/nTfmXBTMalc4j0yjg0anSVgsACSFBBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:25:27.911186Z"},"content_sha256":"ee47763328d0682c1b42fbe5e2dcf92a16946734496733cf839cfd86fda66073","schema_version":"1.0","event_id":"sha256:ee47763328d0682c1b42fbe5e2dcf92a16946734496733cf839cfd86fda66073"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:G22N2X3KENBGQCSEF3B3IMJHE3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How transformers learn structured data: insights from hierarchical filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cond-mat.stat-mech","cs.CL"],"primary_cat":"cs.LG","authors_text":"Emanuele Moscato, Jerome Garnier-Brun, Luca Saglietti, Marc M\\'ezard","submitted_at":"2024-08-27T15:23:09Z","abstract_excerpt":"Understanding the learning process and the embedded computation in transformers is becoming a central goal for the development of interpretable AI. In the present study, we introduce a hierarchical filtering procedure for data models of sequences on trees, allowing us to hand-tune the range of positional correlations in the data. Leveraging this controlled setting, we provide evidence that vanilla encoder-only transformers can approximate the exact inference algorithm when trained on root classification and masked language modeling tasks, and study how this computation is discovered and implem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15138","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/2408.15138/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":"2026-07-05T11:19:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wlpQwrPFiX1IScAnCEjw1ArMKWuZiWFghRgQbj5HehTEhScJzGAbkntvxomU90ETILUyFMT8+FSVzMUByB47Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:25:27.912166Z"},"content_sha256":"7bfcc84e686e3e167d1a50edebf92201422fcdd6e9799d17329ca9542c9de59c","schema_version":"1.0","event_id":"sha256:7bfcc84e686e3e167d1a50edebf92201422fcdd6e9799d17329ca9542c9de59c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G22N2X3KENBGQCSEF3B3IMJHE3/bundle.json","state_url":"https://pith.science/pith/G22N2X3KENBGQCSEF3B3IMJHE3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G22N2X3KENBGQCSEF3B3IMJHE3/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":"2026-08-07T09:25:27Z","links":{"resolver":"https://pith.science/pith/G22N2X3KENBGQCSEF3B3IMJHE3","bundle":"https://pith.science/pith/G22N2X3KENBGQCSEF3B3IMJHE3/bundle.json","state":"https://pith.science/pith/G22N2X3KENBGQCSEF3B3IMJHE3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G22N2X3KENBGQCSEF3B3IMJHE3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G22N2X3KENBGQCSEF3B3IMJHE3","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":"c4a068a3dfba61dd50d39107df58db5591880c37fa8cd2b9e2494e83e4d4ecc2","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T15:23:09Z","title_canon_sha256":"f486b29307b15b8ccf35e84d055a39cc504f57cc5b392918fae86cae2e8b49cf"},"schema_version":"1.0","source":{"id":"2408.15138","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15138","created_at":"2026-07-05T11:19:00Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15138v3","created_at":"2026-07-05T11:19:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15138","created_at":"2026-07-05T11:19:00Z"},{"alias_kind":"pith_short_12","alias_value":"G22N2X3KENBG","created_at":"2026-07-05T11:19:00Z"},{"alias_kind":"pith_short_16","alias_value":"G22N2X3KENBGQCSE","created_at":"2026-07-05T11:19:00Z"},{"alias_kind":"pith_short_8","alias_value":"G22N2X3K","created_at":"2026-07-05T11:19:00Z"}],"graph_snapshots":[{"event_id":"sha256:7bfcc84e686e3e167d1a50edebf92201422fcdd6e9799d17329ca9542c9de59c","target":"graph","created_at":"2026-07-05T11:19:00Z","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/2408.15138/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the learning process and the embedded computation in transformers is becoming a central goal for the development of interpretable AI. In the present study, we introduce a hierarchical filtering procedure for data models of sequences on trees, allowing us to hand-tune the range of positional correlations in the data. Leveraging this controlled setting, we provide evidence that vanilla encoder-only transformers can approximate the exact inference algorithm when trained on root classification and masked language modeling tasks, and study how this computation is discovered and implem","authors_text":"Emanuele Moscato, Jerome Garnier-Brun, Luca Saglietti, Marc M\\'ezard","cross_cats":["cond-mat.dis-nn","cond-mat.stat-mech","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T15:23:09Z","title":"How transformers learn structured data: insights from hierarchical filtering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15138","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:ee47763328d0682c1b42fbe5e2dcf92a16946734496733cf839cfd86fda66073","target":"record","created_at":"2026-07-05T11:19:00Z","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":"c4a068a3dfba61dd50d39107df58db5591880c37fa8cd2b9e2494e83e4d4ecc2","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T15:23:09Z","title_canon_sha256":"f486b29307b15b8ccf35e84d055a39cc504f57cc5b392918fae86cae2e8b49cf"},"schema_version":"1.0","source":{"id":"2408.15138","kind":"arxiv","version":3}},"canonical_sha256":"36b4dd5f6a2342680a442ec3b4312726d964f5a03e8b725e5a1b04d75157dbdf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36b4dd5f6a2342680a442ec3b4312726d964f5a03e8b725e5a1b04d75157dbdf","first_computed_at":"2026-07-05T11:19:00.266675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:00.266675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3DkmRCvgb48sNZJCTO+xFU1APkoWjhAdIdPYZPhQIxbotBgWtN3YOc19oeh+oJtsv5pQxC68uK2T8+lWIgEXCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:00.267170Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.15138","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee47763328d0682c1b42fbe5e2dcf92a16946734496733cf839cfd86fda66073","sha256:7bfcc84e686e3e167d1a50edebf92201422fcdd6e9799d17329ca9542c9de59c"],"state_sha256":"bd2f3d0b7659f14e754ed5e5c62b8de84e784e10b55daa58dd3fd509445cdfc1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wfJPIfwi+zTNS2M5W52YQbwx2zIC1ENn3vYTrNixZSU2SE6V78OiGBja778W1uJqngHkay6uOFPEALhxv8uUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T09:25:27.919352Z","bundle_sha256":"44b9b2ca22cb7a757838b07a29e053fff36b5093444d4dd1f2509fa56a199762"}}