{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C76NBRQ67BC4QPIRXPA67MEQSG","short_pith_number":"pith:C76NBRQ6","schema_version":"1.0","canonical_sha256":"17fcd0c61ef845c83d11bbc1efb090918caf9a857384509b89d1e3107d383a43","source":{"kind":"arxiv","id":"2608.03294","version":1},"attestation_state":"computed","paper":{"title":"Provably Learning Multi-Head Attention with Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Insung Kim, Jian Guo, Sunyeop Kim","submitted_at":"2026-08-04T08:06:15Z","abstract_excerpt":"We study the problem of learning multi-head softmax attention from black-box input-output access. The learner may query arbitrary real-valued token sequences and observe only the scalar output at the final token. Recent work gives an algorithm using $O(d^2)$ value queries to recover the single-head parameters $(W,v)$. For multiple heads, the same work establishes identifiability under the assumption that the heads occupy pairwise orthogonal subspaces. Applying the single-head recovery algorithm separately to the heads additionally requires bases for these subspaces to be known. We recover a ca"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.03294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T08:06:15Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"6b088f98f41c10a7e3c3346bccd9d6600796f503ac99c805975a4c00dc17b899","abstract_canon_sha256":"6a1e1e4fce7c1b99367cdbda976f5e89ec791fea09f34da7bf5780346821d992"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:46:40.984984Z","signature_b64":"e5DsSbjCF5bNPsekW6H/FWkdT0Td+FuYnQU+QNWverbFUIYMzTSd66BLciyCmvBldCew8ZVFLopKIJOeKO6LCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17fcd0c61ef845c83d11bbc1efb090918caf9a857384509b89d1e3107d383a43","last_reissued_at":"2026-08-05T00:46:40.982681Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:46:40.982681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably Learning Multi-Head Attention with Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Insung Kim, Jian Guo, Sunyeop Kim","submitted_at":"2026-08-04T08:06:15Z","abstract_excerpt":"We study the problem of learning multi-head softmax attention from black-box input-output access. The learner may query arbitrary real-valued token sequences and observe only the scalar output at the final token. Recent work gives an algorithm using $O(d^2)$ value queries to recover the single-head parameters $(W,v)$. For multiple heads, the same work establishes identifiability under the assumption that the heads occupy pairwise orthogonal subspaces. Applying the single-head recovery algorithm separately to the heads additionally requires bases for these subspaces to be known. We recover a ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03294","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/2608.03294/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.03294","created_at":"2026-08-05T00:46:40.983511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03294v1","created_at":"2026-08-05T00:46:40.983511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03294","created_at":"2026-08-05T00:46:40.983511+00:00"},{"alias_kind":"pith_short_12","alias_value":"C76NBRQ67BC4","created_at":"2026-08-05T00:46:40.983511+00:00"},{"alias_kind":"pith_short_16","alias_value":"C76NBRQ67BC4QPIR","created_at":"2026-08-05T00:46:40.983511+00:00"},{"alias_kind":"pith_short_8","alias_value":"C76NBRQ6","created_at":"2026-08-05T00:46:40.983511+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C76NBRQ67BC4QPIRXPA67MEQSG","json":"https://pith.science/pith/C76NBRQ67BC4QPIRXPA67MEQSG.json","graph_json":"https://pith.science/api/pith-number/C76NBRQ67BC4QPIRXPA67MEQSG/graph.json","events_json":"https://pith.science/api/pith-number/C76NBRQ67BC4QPIRXPA67MEQSG/events.json","paper":"https://pith.science/paper/C76NBRQ6"},"agent_actions":{"view_html":"https://pith.science/pith/C76NBRQ67BC4QPIRXPA67MEQSG","download_json":"https://pith.science/pith/C76NBRQ67BC4QPIRXPA67MEQSG.json","view_paper":"https://pith.science/paper/C76NBRQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03294&json=true","fetch_graph":"https://pith.science/api/pith-number/C76NBRQ67BC4QPIRXPA67MEQSG/graph.json","fetch_events":"https://pith.science/api/pith-number/C76NBRQ67BC4QPIRXPA67MEQSG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C76NBRQ67BC4QPIRXPA67MEQSG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C76NBRQ67BC4QPIRXPA67MEQSG/action/storage_attestation","attest_author":"https://pith.science/pith/C76NBRQ67BC4QPIRXPA67MEQSG/action/author_attestation","sign_citation":"https://pith.science/pith/C76NBRQ67BC4QPIRXPA67MEQSG/action/citation_signature","submit_replication":"https://pith.science/pith/C76NBRQ67BC4QPIRXPA67MEQSG/action/replication_record"}},"created_at":"2026-08-05T00:46:40.983511+00:00","updated_at":"2026-08-05T00:46:40.983511+00:00"}