{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3OVNVQFELAISQPTGIZH2UJRUJY","short_pith_number":"pith:3OVNVQFE","canonical_record":{"source":{"id":"2606.04476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T05:44:30Z","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"17dd9ea7e0f954dab2cc6e75c697f90bfecfea64d80383460ea4ed040d42ec76","abstract_canon_sha256":"b8a03f413fda94cb1f04e1265371445033fe4d4626d2646f9046abd751a2599c"},"schema_version":"1.0"},"canonical_sha256":"dbaadac0a45811283e66464faa26344e0b007b4dfa2f2ba0ba5f830d0e6419fc","source":{"kind":"arxiv","id":"2606.04476","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04476","created_at":"2026-06-04T01:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04476v1","created_at":"2026-06-04T01:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04476","created_at":"2026-06-04T01:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"3OVNVQFELAIS","created_at":"2026-06-04T01:09:09Z"},{"alias_kind":"pith_short_16","alias_value":"3OVNVQFELAISQPTG","created_at":"2026-06-04T01:09:09Z"},{"alias_kind":"pith_short_8","alias_value":"3OVNVQFE","created_at":"2026-06-04T01:09:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3OVNVQFELAISQPTGIZH2UJRUJY","target":"record","payload":{"canonical_record":{"source":{"id":"2606.04476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T05:44:30Z","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"17dd9ea7e0f954dab2cc6e75c697f90bfecfea64d80383460ea4ed040d42ec76","abstract_canon_sha256":"b8a03f413fda94cb1f04e1265371445033fe4d4626d2646f9046abd751a2599c"},"schema_version":"1.0"},"canonical_sha256":"dbaadac0a45811283e66464faa26344e0b007b4dfa2f2ba0ba5f830d0e6419fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:09.626171Z","signature_b64":"qKv4enBgvFMG9/nPen05j7ziH8f/IxLyeHj9fvuslfQGlHzXmnfc5RS+LyLJTYJpjtTkEp9gfso50YUorRfFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbaadac0a45811283e66464faa26344e0b007b4dfa2f2ba0ba5f830d0e6419fc","last_reissued_at":"2026-06-04T01:09:09.625726Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:09.625726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.04476","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":"2026-06-04T01:09:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wCroEgtFTnCsuz6Lu/BH9O9rrLDJAhMuxbA0SYDymKSJDVb2RexryMBwfa2LAtTQqEz8ZcVpkRZHoyJwtRS1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:15:20.256918Z"},"content_sha256":"58a60ec9914a2f48d7c152422cb1846de7ac28923e04e6f3b18d5efc20611d97","schema_version":"1.0","event_id":"sha256:58a60ec9914a2f48d7c152422cb1846de7ac28923e04e6f3b18d5efc20611d97"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3OVNVQFELAISQPTGIZH2UJRUJY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Berk Tinaz, Changzhi Xie, Mahdi Soltanolkotabi","submitted_at":"2026-06-03T05:44:30Z","abstract_excerpt":"In this paper, we study the gradient descent dynamics for jointly training both layers of a one-hidden-layer ReLU network to fit a linear target function. Concretely, we consider a realizable setting where inputs are drawn i.i.d. from a Gaussian distribution and labels follow a planted linear model. This stylized framework captures salient features of end-to-end training in inverse problems and certain auto-encoder models. Despite its apparent simplicity, the dynamics remain poorly understood, in part because the loss landscape contains multiple non-strict saddle points, making it unclear why "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04476","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/2606.04476/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":"2026-06-04T01:09:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QOcMPSnOv+Z5gcbh8gl4YD48PAeF08KCWZVX2gGG3uiG2t9Aifb0OOaSuqMwUXJFPEZZhUYysdD4CVE2EDw/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:15:20.257260Z"},"content_sha256":"79877d3d0aad13e838506c827ad892446aee8049bf3990d6e1b2d44dd87d29c8","schema_version":"1.0","event_id":"sha256:79877d3d0aad13e838506c827ad892446aee8049bf3990d6e1b2d44dd87d29c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3OVNVQFELAISQPTGIZH2UJRUJY/bundle.json","state_url":"https://pith.science/pith/3OVNVQFELAISQPTGIZH2UJRUJY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3OVNVQFELAISQPTGIZH2UJRUJY/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":"2026-08-17T14:15:20Z","links":{"resolver":"https://pith.science/pith/3OVNVQFELAISQPTGIZH2UJRUJY","bundle":"https://pith.science/pith/3OVNVQFELAISQPTGIZH2UJRUJY/bundle.json","state":"https://pith.science/pith/3OVNVQFELAISQPTGIZH2UJRUJY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3OVNVQFELAISQPTGIZH2UJRUJY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3OVNVQFELAISQPTGIZH2UJRUJY","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":"b8a03f413fda94cb1f04e1265371445033fe4d4626d2646f9046abd751a2599c","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T05:44:30Z","title_canon_sha256":"17dd9ea7e0f954dab2cc6e75c697f90bfecfea64d80383460ea4ed040d42ec76"},"schema_version":"1.0","source":{"id":"2606.04476","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04476","created_at":"2026-06-04T01:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04476v1","created_at":"2026-06-04T01:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04476","created_at":"2026-06-04T01:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"3OVNVQFELAIS","created_at":"2026-06-04T01:09:09Z"},{"alias_kind":"pith_short_16","alias_value":"3OVNVQFELAISQPTG","created_at":"2026-06-04T01:09:09Z"},{"alias_kind":"pith_short_8","alias_value":"3OVNVQFE","created_at":"2026-06-04T01:09:09Z"}],"graph_snapshots":[{"event_id":"sha256:79877d3d0aad13e838506c827ad892446aee8049bf3990d6e1b2d44dd87d29c8","target":"graph","created_at":"2026-06-04T01:09:09Z","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/2606.04476/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study the gradient descent dynamics for jointly training both layers of a one-hidden-layer ReLU network to fit a linear target function. Concretely, we consider a realizable setting where inputs are drawn i.i.d. from a Gaussian distribution and labels follow a planted linear model. This stylized framework captures salient features of end-to-end training in inverse problems and certain auto-encoder models. Despite its apparent simplicity, the dynamics remain poorly understood, in part because the loss landscape contains multiple non-strict saddle points, making it unclear why ","authors_text":"Berk Tinaz, Changzhi Xie, Mahdi Soltanolkotabi","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T05:44:30Z","title":"When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04476","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":"sha256:58a60ec9914a2f48d7c152422cb1846de7ac28923e04e6f3b18d5efc20611d97","target":"record","created_at":"2026-06-04T01:09:09Z","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":"b8a03f413fda94cb1f04e1265371445033fe4d4626d2646f9046abd751a2599c","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T05:44:30Z","title_canon_sha256":"17dd9ea7e0f954dab2cc6e75c697f90bfecfea64d80383460ea4ed040d42ec76"},"schema_version":"1.0","source":{"id":"2606.04476","kind":"arxiv","version":1}},"canonical_sha256":"dbaadac0a45811283e66464faa26344e0b007b4dfa2f2ba0ba5f830d0e6419fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbaadac0a45811283e66464faa26344e0b007b4dfa2f2ba0ba5f830d0e6419fc","first_computed_at":"2026-06-04T01:09:09.625726Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:09.625726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qKv4enBgvFMG9/nPen05j7ziH8f/IxLyeHj9fvuslfQGlHzXmnfc5RS+LyLJTYJpjtTkEp9gfso50YUorRfFBA==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:09.626171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04476","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58a60ec9914a2f48d7c152422cb1846de7ac28923e04e6f3b18d5efc20611d97","sha256:79877d3d0aad13e838506c827ad892446aee8049bf3990d6e1b2d44dd87d29c8"],"state_sha256":"8aa96b40282a8ff3e726f200ce9f0bc14283eddd3a9ad0a063dc8a63bcad010c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GPlY7lBhbi3KfkoRChm4J6VpmTKN+Feq3MePpQXlgRioNOjHsBQqwkxFtnx1aFCDLKv4DzPLPFrr4zPH1K39Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T14:15:20.259710Z","bundle_sha256":"9a1264a3343e97da1c496c6777131ff58f9262e51b30ec783699c2e30d05ba69"}}