{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PZTTNKXP2BLJNW4XR6RKUZL2EJ","short_pith_number":"pith:PZTTNKXP","canonical_record":{"source":{"id":"2402.05738","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T15:15:09Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"fbdc80cbe6c1e59359bc1d013a6e59ea2f26f88f14b4afd068972aa15610522b","abstract_canon_sha256":"894e14976d082e1ce51a267d049fe6b0c72073ba0bf22ec8c7ce7a56c4cf9d86"},"schema_version":"1.0"},"canonical_sha256":"7e6736aaefd05696db978fa2aa657a225a8a472179a73ab6a6454e92ea567830","source":{"kind":"arxiv","id":"2402.05738","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05738","created_at":"2026-07-05T10:41:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05738v2","created_at":"2026-07-05T10:41:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05738","created_at":"2026-07-05T10:41:45Z"},{"alias_kind":"pith_short_12","alias_value":"PZTTNKXP2BLJ","created_at":"2026-07-05T10:41:45Z"},{"alias_kind":"pith_short_16","alias_value":"PZTTNKXP2BLJNW4X","created_at":"2026-07-05T10:41:45Z"},{"alias_kind":"pith_short_8","alias_value":"PZTTNKXP","created_at":"2026-07-05T10:41:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PZTTNKXP2BLJNW4XR6RKUZL2EJ","target":"record","payload":{"canonical_record":{"source":{"id":"2402.05738","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T15:15:09Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"fbdc80cbe6c1e59359bc1d013a6e59ea2f26f88f14b4afd068972aa15610522b","abstract_canon_sha256":"894e14976d082e1ce51a267d049fe6b0c72073ba0bf22ec8c7ce7a56c4cf9d86"},"schema_version":"1.0"},"canonical_sha256":"7e6736aaefd05696db978fa2aa657a225a8a472179a73ab6a6454e92ea567830","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:45.469493Z","signature_b64":"HN7csUNc7KAG80xJGgtJ4CLJoCn8O2gtu1syQjQGjEF4MlRUgpJh5niHqqU6Tpotvbs2vpsrEShhnE897Ou8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e6736aaefd05696db978fa2aa657a225a8a472179a73ab6a6454e92ea567830","last_reissued_at":"2026-07-05T10:41:45.468962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:45.468962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.05738","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":"2026-07-05T10:41:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hi6WL5Y2WnwUTSoD2uWL+TXuo+Ki6sBXjhrGwwuiO1oJiapJgQNT+HAZes1j+LE9ZE8n57raF5dSk0NJezQ+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:26:03.494041Z"},"content_sha256":"dedf2fa90d627cf4cc6eecfc537910440d239c094d5bae53a082778119c3c278","schema_version":"1.0","event_id":"sha256:dedf2fa90d627cf4cc6eecfc537910440d239c094d5bae53a082778119c3c278"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PZTTNKXP2BLJNW4XR6RKUZL2EJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Implicit Bias and Fast Convergence Rates for Self-attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bhavya Vasudeva, Christos Thrampoulidis, Puneesh Deora","submitted_at":"2024-02-08T15:15:09Z","abstract_excerpt":"We study the fundamental optimization principles of self-attention, the defining mechanism of transformers, by analyzing the implicit bias of gradient-based optimizers in training a self-attention layer with a linear decoder in binary classification. Building on prior studies in linear logistic regression, recent findings demonstrate that the key-query matrix $W_t$ from gradient-descent (GD) converges in direction towards $W_{mm}$, which maximizes the margin between optimal and non-optimal tokens across sequences. However, this convergence is local, dependent on initial conditions, only holds "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05738","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/2402.05738/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":"2026-07-05T10:41:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4TDcUunxj+oF97cyLC/yHGDuybufJcJefe5xk0zI4BvBE2ljLc2Uz0I+2EX29LaEcmAvm1wg+4Er10udBYE/CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:26:03.494591Z"},"content_sha256":"83f4749183bcb62a896dee2f771820dcc6c23f544cb3fcabbe01ef8dd30babb2","schema_version":"1.0","event_id":"sha256:83f4749183bcb62a896dee2f771820dcc6c23f544cb3fcabbe01ef8dd30babb2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PZTTNKXP2BLJNW4XR6RKUZL2EJ/bundle.json","state_url":"https://pith.science/pith/PZTTNKXP2BLJNW4XR6RKUZL2EJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PZTTNKXP2BLJNW4XR6RKUZL2EJ/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":"2026-08-10T03:26:03Z","links":{"resolver":"https://pith.science/pith/PZTTNKXP2BLJNW4XR6RKUZL2EJ","bundle":"https://pith.science/pith/PZTTNKXP2BLJNW4XR6RKUZL2EJ/bundle.json","state":"https://pith.science/pith/PZTTNKXP2BLJNW4XR6RKUZL2EJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PZTTNKXP2BLJNW4XR6RKUZL2EJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PZTTNKXP2BLJNW4XR6RKUZL2EJ","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":"894e14976d082e1ce51a267d049fe6b0c72073ba0bf22ec8c7ce7a56c4cf9d86","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T15:15:09Z","title_canon_sha256":"fbdc80cbe6c1e59359bc1d013a6e59ea2f26f88f14b4afd068972aa15610522b"},"schema_version":"1.0","source":{"id":"2402.05738","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05738","created_at":"2026-07-05T10:41:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05738v2","created_at":"2026-07-05T10:41:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05738","created_at":"2026-07-05T10:41:45Z"},{"alias_kind":"pith_short_12","alias_value":"PZTTNKXP2BLJ","created_at":"2026-07-05T10:41:45Z"},{"alias_kind":"pith_short_16","alias_value":"PZTTNKXP2BLJNW4X","created_at":"2026-07-05T10:41:45Z"},{"alias_kind":"pith_short_8","alias_value":"PZTTNKXP","created_at":"2026-07-05T10:41:45Z"}],"graph_snapshots":[{"event_id":"sha256:83f4749183bcb62a896dee2f771820dcc6c23f544cb3fcabbe01ef8dd30babb2","target":"graph","created_at":"2026-07-05T10:41:45Z","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/2402.05738/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the fundamental optimization principles of self-attention, the defining mechanism of transformers, by analyzing the implicit bias of gradient-based optimizers in training a self-attention layer with a linear decoder in binary classification. Building on prior studies in linear logistic regression, recent findings demonstrate that the key-query matrix $W_t$ from gradient-descent (GD) converges in direction towards $W_{mm}$, which maximizes the margin between optimal and non-optimal tokens across sequences. However, this convergence is local, dependent on initial conditions, only holds ","authors_text":"Bhavya Vasudeva, Christos Thrampoulidis, Puneesh Deora","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T15:15:09Z","title":"Implicit Bias and Fast Convergence Rates for Self-attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05738","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:dedf2fa90d627cf4cc6eecfc537910440d239c094d5bae53a082778119c3c278","target":"record","created_at":"2026-07-05T10:41:45Z","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":"894e14976d082e1ce51a267d049fe6b0c72073ba0bf22ec8c7ce7a56c4cf9d86","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T15:15:09Z","title_canon_sha256":"fbdc80cbe6c1e59359bc1d013a6e59ea2f26f88f14b4afd068972aa15610522b"},"schema_version":"1.0","source":{"id":"2402.05738","kind":"arxiv","version":2}},"canonical_sha256":"7e6736aaefd05696db978fa2aa657a225a8a472179a73ab6a6454e92ea567830","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e6736aaefd05696db978fa2aa657a225a8a472179a73ab6a6454e92ea567830","first_computed_at":"2026-07-05T10:41:45.468962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:45.468962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HN7csUNc7KAG80xJGgtJ4CLJoCn8O2gtu1syQjQGjEF4MlRUgpJh5niHqqU6Tpotvbs2vpsrEShhnE897Ou8AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:45.469493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05738","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dedf2fa90d627cf4cc6eecfc537910440d239c094d5bae53a082778119c3c278","sha256:83f4749183bcb62a896dee2f771820dcc6c23f544cb3fcabbe01ef8dd30babb2"],"state_sha256":"8e6e15207635e66134ddafbd0c22b5a58b034baa2be195a8ab67e1879ff40359"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m8ikCo4aBqaU/gvWOYS8AMG4cb55DMMAEZ2nbPJl4wyZXKAAN2i6mNViwlTUmg/hH0e0YM5lHQp/CAPNbcMLDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T03:26:03.500222Z","bundle_sha256":"2c02b65aa7da4810acb9215cf47f3374d4bcc343a1153575adeb2de03adb3a28"}}