{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MVCXK2U7IKY7CZHLRJS2DZZNIB","short_pith_number":"pith:MVCXK2U7","canonical_record":{"source":{"id":"2211.11052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-20T18:17:47Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"d7da4a0166441af015e2792b374c8d9e9eba59ba12f7dba08144bde77029bcf8","abstract_canon_sha256":"675bc2f8c6aec9e5dc4b2fff6fb33115fa04694d5dc09f7c0552c14f3e3ce644"},"schema_version":"1.0"},"canonical_sha256":"6545756a9f42b1f164eb8a65a1e72d4076df962a06cc38116c93af6f447e1b51","source":{"kind":"arxiv","id":"2211.11052","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.11052","created_at":"2026-07-05T05:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2211.11052v1","created_at":"2026-07-05T05:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11052","created_at":"2026-07-05T05:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"MVCXK2U7IKY7","created_at":"2026-07-05T05:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"MVCXK2U7IKY7CZHL","created_at":"2026-07-05T05:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"MVCXK2U7","created_at":"2026-07-05T05:18:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MVCXK2U7IKY7CZHLRJS2DZZNIB","target":"record","payload":{"canonical_record":{"source":{"id":"2211.11052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-20T18:17:47Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"d7da4a0166441af015e2792b374c8d9e9eba59ba12f7dba08144bde77029bcf8","abstract_canon_sha256":"675bc2f8c6aec9e5dc4b2fff6fb33115fa04694d5dc09f7c0552c14f3e3ce644"},"schema_version":"1.0"},"canonical_sha256":"6545756a9f42b1f164eb8a65a1e72d4076df962a06cc38116c93af6f447e1b51","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:08.720488Z","signature_b64":"hFV2JYTiCgOWQ+BmnkNijXpSCCHuhv+5+OpcoSjrVjk1sB7PKu+se7Pixwi0urFdqDlPChW4HH01LipDSnDrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6545756a9f42b1f164eb8a65a1e72d4076df962a06cc38116c93af6f447e1b51","last_reissued_at":"2026-07-05T05:18:08.720088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:08.720088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.11052","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":"2026-07-05T05:18:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YbQXQUUa411PG8OdBturylG8JdcrvJcY21GXxBsH2MWzfkX4ukK091IKOYXMWc7Y4fwjHN8uvfHq8WP5C9EPDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T06:42:14.054091Z"},"content_sha256":"be288c1980583bd9f8bf7add115419155a356001ed4bc019cc3b3b50bf4bc80c","schema_version":"1.0","event_id":"sha256:be288c1980583bd9f8bf7add115419155a356001ed4bc019cc3b3b50bf4bc80c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MVCXK2U7IKY7CZHLRJS2DZZNIB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convexifying Transformers: Improving optimization and understanding of transformer networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Behnam Neyshabur, Harsh Mehta, Tolga Ergen","submitted_at":"2022-11-20T18:17:47Z","abstract_excerpt":"Understanding the fundamental mechanism behind the success of transformer networks is still an open problem in the deep learning literature. Although their remarkable performance has been mostly attributed to the self-attention mechanism, the literature still lacks a solid analysis of these networks and interpretation of the functions learned by them. To this end, we study the training problem of attention/transformer networks and introduce a novel convex analytic approach to improve the understanding and optimization of these networks. Particularly, we first introduce a convex alternative to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11052","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/2211.11052/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":"2026-07-05T05:18:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eqe6enP7ZvYjvr4X7mVgYOIciCreL49jicjVB2m2UZ28n6PQDfm0Q+pk7Pc9spiFGig2ONLHJeASJB7KfLkiCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T06:42:14.054508Z"},"content_sha256":"0274fc2047d0750796463bd2ea3e0102f65abd14ff1d30d1045fac16b0cca9c5","schema_version":"1.0","event_id":"sha256:0274fc2047d0750796463bd2ea3e0102f65abd14ff1d30d1045fac16b0cca9c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MVCXK2U7IKY7CZHLRJS2DZZNIB/bundle.json","state_url":"https://pith.science/pith/MVCXK2U7IKY7CZHLRJS2DZZNIB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MVCXK2U7IKY7CZHLRJS2DZZNIB/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":"2026-07-11T06:42:14Z","links":{"resolver":"https://pith.science/pith/MVCXK2U7IKY7CZHLRJS2DZZNIB","bundle":"https://pith.science/pith/MVCXK2U7IKY7CZHLRJS2DZZNIB/bundle.json","state":"https://pith.science/pith/MVCXK2U7IKY7CZHLRJS2DZZNIB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MVCXK2U7IKY7CZHLRJS2DZZNIB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MVCXK2U7IKY7CZHLRJS2DZZNIB","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":"675bc2f8c6aec9e5dc4b2fff6fb33115fa04694d5dc09f7c0552c14f3e3ce644","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-20T18:17:47Z","title_canon_sha256":"d7da4a0166441af015e2792b374c8d9e9eba59ba12f7dba08144bde77029bcf8"},"schema_version":"1.0","source":{"id":"2211.11052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.11052","created_at":"2026-07-05T05:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2211.11052v1","created_at":"2026-07-05T05:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11052","created_at":"2026-07-05T05:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"MVCXK2U7IKY7","created_at":"2026-07-05T05:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"MVCXK2U7IKY7CZHL","created_at":"2026-07-05T05:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"MVCXK2U7","created_at":"2026-07-05T05:18:08Z"}],"graph_snapshots":[{"event_id":"sha256:0274fc2047d0750796463bd2ea3e0102f65abd14ff1d30d1045fac16b0cca9c5","target":"graph","created_at":"2026-07-05T05:18:08Z","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/2211.11052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the fundamental mechanism behind the success of transformer networks is still an open problem in the deep learning literature. Although their remarkable performance has been mostly attributed to the self-attention mechanism, the literature still lacks a solid analysis of these networks and interpretation of the functions learned by them. To this end, we study the training problem of attention/transformer networks and introduce a novel convex analytic approach to improve the understanding and optimization of these networks. Particularly, we first introduce a convex alternative to ","authors_text":"Behnam Neyshabur, Harsh Mehta, Tolga Ergen","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-20T18:17:47Z","title":"Convexifying Transformers: Improving optimization and understanding of transformer networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11052","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:be288c1980583bd9f8bf7add115419155a356001ed4bc019cc3b3b50bf4bc80c","target":"record","created_at":"2026-07-05T05:18:08Z","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":"675bc2f8c6aec9e5dc4b2fff6fb33115fa04694d5dc09f7c0552c14f3e3ce644","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-20T18:17:47Z","title_canon_sha256":"d7da4a0166441af015e2792b374c8d9e9eba59ba12f7dba08144bde77029bcf8"},"schema_version":"1.0","source":{"id":"2211.11052","kind":"arxiv","version":1}},"canonical_sha256":"6545756a9f42b1f164eb8a65a1e72d4076df962a06cc38116c93af6f447e1b51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6545756a9f42b1f164eb8a65a1e72d4076df962a06cc38116c93af6f447e1b51","first_computed_at":"2026-07-05T05:18:08.720088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:18:08.720088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hFV2JYTiCgOWQ+BmnkNijXpSCCHuhv+5+OpcoSjrVjk1sB7PKu+se7Pixwi0urFdqDlPChW4HH01LipDSnDrDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:18:08.720488Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.11052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be288c1980583bd9f8bf7add115419155a356001ed4bc019cc3b3b50bf4bc80c","sha256:0274fc2047d0750796463bd2ea3e0102f65abd14ff1d30d1045fac16b0cca9c5"],"state_sha256":"95fc0a9395199ec62ceb4e602df0c0df3118c2f59d13ee83d728640bbaf48929"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uGS98Rs1RGdX3HoBaiP0aUx4Is8Mt+KzlU6F3mkabAozFdTsQoj8rC4DHP2p3wtMv3pR6njGHfyPl5O7hLx9AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T06:42:14.058392Z","bundle_sha256":"eedd3d7fa21a6502fa26827ba4ecfd912293e37bf4fb7a29bc82a1f8023083b2"}}