{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZK5XJ5EKTUK5ZGGB4363WCYXK7","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":"8bfe216486a8bcdd2c5c94deef218f08acd24c1d766dc4dad961e94d3ddc2d2c","cross_cats_sorted":["cs.CV","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-06T09:00:38Z","title_canon_sha256":"f22a8b33b9355d0269b828b761e5f54948c3718338218832e9da3080ae6c756a"},"schema_version":"1.0","source":{"id":"2311.02960","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02960","created_at":"2026-06-24T01:14:18Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02960v5","created_at":"2026-06-24T01:14:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02960","created_at":"2026-06-24T01:14:18Z"},{"alias_kind":"pith_short_12","alias_value":"ZK5XJ5EKTUK5","created_at":"2026-06-24T01:14:18Z"},{"alias_kind":"pith_short_16","alias_value":"ZK5XJ5EKTUK5ZGGB","created_at":"2026-06-24T01:14:18Z"},{"alias_kind":"pith_short_8","alias_value":"ZK5XJ5EK","created_at":"2026-06-24T01:14:18Z"}],"graph_snapshots":[{"event_id":"sha256:d37065d653f77a2530dda4f71e7df1a8c0715b31d06608a3fb419f4b424899b7","target":"graph","created_at":"2026-06-24T01:14:18Z","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/2311.02960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data. However, it remains an open question how deep networks perform hierarchical feature learning across layers. In this work, we attempt to unveil this mystery by investigating the structures of intermediate features. Motivated by our empirical findings that linear layers mimic the roles of deep layers in nonlinear networks for feature learning, we explore how deep linear networks transform input data into output by investigating the output (i.e., features) of each layer aft","authors_text":"Can Yaras, Laura Balzano, Peng Wang, Qing Qu, Wei Hu, Xiao Li, Zhihui Zhu","cross_cats":["cs.CV","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-06T09:00:38Z","title":"Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02960","kind":"arxiv","version":5},"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:fd3416774868874f916989bbac625e7e4136b8bcb3a59dfacce842f8d8e4cef1","target":"record","created_at":"2026-06-24T01:14:18Z","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":"8bfe216486a8bcdd2c5c94deef218f08acd24c1d766dc4dad961e94d3ddc2d2c","cross_cats_sorted":["cs.CV","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-06T09:00:38Z","title_canon_sha256":"f22a8b33b9355d0269b828b761e5f54948c3718338218832e9da3080ae6c756a"},"schema_version":"1.0","source":{"id":"2311.02960","kind":"arxiv","version":5}},"canonical_sha256":"cabb74f48a9d15dc98c1e6fdbb0b1757cfaf3e2c9fd820b5f02f24897b66a5f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cabb74f48a9d15dc98c1e6fdbb0b1757cfaf3e2c9fd820b5f02f24897b66a5f6","first_computed_at":"2026-06-24T01:14:18.201571Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:18.201571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O1CD7NtR876pj4y+aD1NVBMf8QjLR6Cm1ojtxrlrSJ6vBxRqbMDhf/oDJ1QxRkEACO6IkVTlKyTK8q6t1yTlDg==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:18.202104Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.02960","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd3416774868874f916989bbac625e7e4136b8bcb3a59dfacce842f8d8e4cef1","sha256:d37065d653f77a2530dda4f71e7df1a8c0715b31d06608a3fb419f4b424899b7"],"state_sha256":"fcf25de51fa9b2652ae1d138dda8bf164de18bfcf8c9513989e53015dbd2186c"}