{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AOC7HIPP4I2EGSB5WUONVPRRX3","short_pith_number":"pith:AOC7HIPP","canonical_record":{"source":{"id":"2303.11453","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T21:05:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fd1907eaf9a85f0e80ce0093a9d5000eb8a3b73358406d8843a7586878c644ad","abstract_canon_sha256":"31270c6e67005c408a60f0c0560563aaaa9d2e407d3445f1778a1f7852fd3789"},"schema_version":"1.0"},"canonical_sha256":"0385f3a1efe23443483db51cdabe31bedf739a9f3c5b10869f2ebf4e44ce5abb","source":{"kind":"arxiv","id":"2303.11453","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.11453","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"arxiv_version","alias_value":"2303.11453v2","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11453","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"pith_short_12","alias_value":"AOC7HIPP4I2E","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"pith_short_16","alias_value":"AOC7HIPP4I2EGSB5","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"pith_short_8","alias_value":"AOC7HIPP","created_at":"2026-07-05T06:17:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AOC7HIPP4I2EGSB5WUONVPRRX3","target":"record","payload":{"canonical_record":{"source":{"id":"2303.11453","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T21:05:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fd1907eaf9a85f0e80ce0093a9d5000eb8a3b73358406d8843a7586878c644ad","abstract_canon_sha256":"31270c6e67005c408a60f0c0560563aaaa9d2e407d3445f1778a1f7852fd3789"},"schema_version":"1.0"},"canonical_sha256":"0385f3a1efe23443483db51cdabe31bedf739a9f3c5b10869f2ebf4e44ce5abb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:05.589533Z","signature_b64":"5C1fUVLhuU0mx3kE1wI/MxSZ0ugD12Itv1ZyqWRsiCUqQJqiPd0mxKwyxeL7RrEdN12Oi9QQ73GLFw3ef81EDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0385f3a1efe23443483db51cdabe31bedf739a9f3c5b10869f2ebf4e44ce5abb","last_reissued_at":"2026-07-05T06:17:05.589053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:05.589053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.11453","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":"2026-07-05T06:17:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5kT57wav+cdUZZOFFbm0jkZi02nrRvMciLarSGHyblGx0Wb9M+O/8+Lp9OHZY3GaQm01POykoIuvlhci9SjxAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:29:31.674354Z"},"content_sha256":"8f07bb2cc6b6a0d53f7d13322b94856e60a9c2dc5831599c75c65eefa8bcf49a","schema_version":"1.0","event_id":"sha256:8f07bb2cc6b6a0d53f7d13322b94856e60a9c2dc5831599c75c65eefa8bcf49a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AOC7HIPP4I2EGSB5WUONVPRRX3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aryan Mokhtari, Devvrit, Kannan Ramchandran, Nived Rajaraman","submitted_at":"2023-03-20T21:05:44Z","abstract_excerpt":"Pruning schemes have been widely used in practice to reduce the complexity of trained models with a massive number of parameters. In fact, several practical studies have shown that if a pruned model is fine-tuned with some gradient-based updates it generalizes well to new samples. Although the above pipeline, which we refer to as pruning + fine-tuning, has been extremely successful in lowering the complexity of trained models, there is very little known about the theory behind this success. In this paper, we address this issue by investigating the pruning + fine-tuning framework on the overpar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11453","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/2303.11453/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":"2026-07-05T06:17:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YYomOKAJXSfN1uXrVy/9SKhoHivRMSfOiovhkN+iaEoY/8esLXx2HdB73FnTRml875DLCzVdSyjjTqh/CEckAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:29:31.674998Z"},"content_sha256":"545f90da859a55c65579985118339cfb298525b48c1d26f56540f65d01a6341d","schema_version":"1.0","event_id":"sha256:545f90da859a55c65579985118339cfb298525b48c1d26f56540f65d01a6341d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AOC7HIPP4I2EGSB5WUONVPRRX3/bundle.json","state_url":"https://pith.science/pith/AOC7HIPP4I2EGSB5WUONVPRRX3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AOC7HIPP4I2EGSB5WUONVPRRX3/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":"2026-07-07T05:29:31Z","links":{"resolver":"https://pith.science/pith/AOC7HIPP4I2EGSB5WUONVPRRX3","bundle":"https://pith.science/pith/AOC7HIPP4I2EGSB5WUONVPRRX3/bundle.json","state":"https://pith.science/pith/AOC7HIPP4I2EGSB5WUONVPRRX3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AOC7HIPP4I2EGSB5WUONVPRRX3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AOC7HIPP4I2EGSB5WUONVPRRX3","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":"31270c6e67005c408a60f0c0560563aaaa9d2e407d3445f1778a1f7852fd3789","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T21:05:44Z","title_canon_sha256":"fd1907eaf9a85f0e80ce0093a9d5000eb8a3b73358406d8843a7586878c644ad"},"schema_version":"1.0","source":{"id":"2303.11453","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.11453","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"arxiv_version","alias_value":"2303.11453v2","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11453","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"pith_short_12","alias_value":"AOC7HIPP4I2E","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"pith_short_16","alias_value":"AOC7HIPP4I2EGSB5","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"pith_short_8","alias_value":"AOC7HIPP","created_at":"2026-07-05T06:17:05Z"}],"graph_snapshots":[{"event_id":"sha256:545f90da859a55c65579985118339cfb298525b48c1d26f56540f65d01a6341d","target":"graph","created_at":"2026-07-05T06:17:05Z","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/2303.11453/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pruning schemes have been widely used in practice to reduce the complexity of trained models with a massive number of parameters. In fact, several practical studies have shown that if a pruned model is fine-tuned with some gradient-based updates it generalizes well to new samples. Although the above pipeline, which we refer to as pruning + fine-tuning, has been extremely successful in lowering the complexity of trained models, there is very little known about the theory behind this success. In this paper, we address this issue by investigating the pruning + fine-tuning framework on the overpar","authors_text":"Aryan Mokhtari, Devvrit, Kannan Ramchandran, Nived Rajaraman","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T21:05:44Z","title":"Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11453","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":"sha256:8f07bb2cc6b6a0d53f7d13322b94856e60a9c2dc5831599c75c65eefa8bcf49a","target":"record","created_at":"2026-07-05T06:17:05Z","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":"31270c6e67005c408a60f0c0560563aaaa9d2e407d3445f1778a1f7852fd3789","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T21:05:44Z","title_canon_sha256":"fd1907eaf9a85f0e80ce0093a9d5000eb8a3b73358406d8843a7586878c644ad"},"schema_version":"1.0","source":{"id":"2303.11453","kind":"arxiv","version":2}},"canonical_sha256":"0385f3a1efe23443483db51cdabe31bedf739a9f3c5b10869f2ebf4e44ce5abb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0385f3a1efe23443483db51cdabe31bedf739a9f3c5b10869f2ebf4e44ce5abb","first_computed_at":"2026-07-05T06:17:05.589053Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:05.589053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5C1fUVLhuU0mx3kE1wI/MxSZ0ugD12Itv1ZyqWRsiCUqQJqiPd0mxKwyxeL7RrEdN12Oi9QQ73GLFw3ef81EDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:05.589533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.11453","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f07bb2cc6b6a0d53f7d13322b94856e60a9c2dc5831599c75c65eefa8bcf49a","sha256:545f90da859a55c65579985118339cfb298525b48c1d26f56540f65d01a6341d"],"state_sha256":"7c6745a312417d9307eb3e245574ae34f64a9550541f6f95fc21eecda2823097"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2TH9iq/tkGE900sU+WoAF7urAnwMMIJVw00YVEuaLX27CrMBVu/BKs+eqv1+wvD4LC+zx+bGHwI7s52NpaLNAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:29:31.678163Z","bundle_sha256":"c25506e0b1d3794b28752a3af15f5b0461d5c57a7b3aeea26377fd79062b64e3"}}