{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:E3WRIKG3T42CXQNNDDXJBYUSOD","short_pith_number":"pith:E3WRIKG3","canonical_record":{"source":{"id":"2410.06567","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T06:04:52Z","cross_cats_sorted":[],"title_canon_sha256":"6b6316fea5bfa5fdcde1d5f31cfe271b7eee3e6687d123e171a73265e96ec50c","abstract_canon_sha256":"1cc39a755432af660a4f6a287eff1f78d3c5fed1ed4ab43ef1d5d52fdee33ef0"},"schema_version":"1.0"},"canonical_sha256":"26ed1428db9f342bc1ad18ee90e29270fc7503467cb3eff49564ebd56b9ce532","source":{"kind":"arxiv","id":"2410.06567","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06567","created_at":"2026-07-05T09:18:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06567v1","created_at":"2026-07-05T09:18:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06567","created_at":"2026-07-05T09:18:04Z"},{"alias_kind":"pith_short_12","alias_value":"E3WRIKG3T42C","created_at":"2026-07-05T09:18:04Z"},{"alias_kind":"pith_short_16","alias_value":"E3WRIKG3T42CXQNN","created_at":"2026-07-05T09:18:04Z"},{"alias_kind":"pith_short_8","alias_value":"E3WRIKG3","created_at":"2026-07-05T09:18:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:E3WRIKG3T42CXQNNDDXJBYUSOD","target":"record","payload":{"canonical_record":{"source":{"id":"2410.06567","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T06:04:52Z","cross_cats_sorted":[],"title_canon_sha256":"6b6316fea5bfa5fdcde1d5f31cfe271b7eee3e6687d123e171a73265e96ec50c","abstract_canon_sha256":"1cc39a755432af660a4f6a287eff1f78d3c5fed1ed4ab43ef1d5d52fdee33ef0"},"schema_version":"1.0"},"canonical_sha256":"26ed1428db9f342bc1ad18ee90e29270fc7503467cb3eff49564ebd56b9ce532","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:04.121788Z","signature_b64":"1/PRvfWLSmVRqjmUe7Dz0yw0CIvVlo2NN77Yrp0J/SU8G1/+7xuUggHbnOBLkzZMhUb7/smg5SH3+WR0Bfi/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26ed1428db9f342bc1ad18ee90e29270fc7503467cb3eff49564ebd56b9ce532","last_reissued_at":"2026-07-05T09:18:04.121422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:04.121422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.06567","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":"2026-07-05T09:18:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P1xElvi+CrnRrl5Sf4w9v1X+Vmq1AZBRIKz6ZTy1FPi0glV6OyOcLfrTrVfT8Nv5LFPs8A6hg74/D9dQNlJbAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T14:44:26.509391Z"},"content_sha256":"d6ac124c4f3597f0af3b36009dde2a281a77ea0df44da4f73ff1a108af6bf0bd","schema_version":"1.0","event_id":"sha256:d6ac124c4f3597f0af3b36009dde2a281a77ea0df44da4f73ff1a108af6bf0bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:E3WRIKG3T42CXQNNDDXJBYUSOD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convex Distillation: Efficient Compression of Deep Networks via Convex Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mert Pilanci, Prateek Varshney","submitted_at":"2024-10-09T06:04:52Z","abstract_excerpt":"Deploying large and complex deep neural networks on resource-constrained edge devices poses significant challenges due to their computational demands and the complexities of non-convex optimization. Traditional compression methods such as distillation and pruning often retain non-convexity that complicates fine-tuning in real-time on such devices. Moreover, these methods often necessitate extensive end-to-end network fine-tuning after compression to preserve model performance, which is not only time-consuming but also requires fully annotated datasets, thus potentially negating the benefits of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06567","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/2410.06567/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":"2026-07-05T09:18:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"50KoYAqtQO8TpWGQvUNQWYYSdyO0KoW5dvoZtZkxsW+ps1P//+sdLzAMZ4mJCQMl3kHunFKMRCZ/biKGx/vPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T14:44:26.510036Z"},"content_sha256":"8196cd2320c639303c2ff0931916a351e79e3f9c2ec7328ea074d65cf82ffaa0","schema_version":"1.0","event_id":"sha256:8196cd2320c639303c2ff0931916a351e79e3f9c2ec7328ea074d65cf82ffaa0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E3WRIKG3T42CXQNNDDXJBYUSOD/bundle.json","state_url":"https://pith.science/pith/E3WRIKG3T42CXQNNDDXJBYUSOD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E3WRIKG3T42CXQNNDDXJBYUSOD/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":"2026-08-21T14:44:26Z","links":{"resolver":"https://pith.science/pith/E3WRIKG3T42CXQNNDDXJBYUSOD","bundle":"https://pith.science/pith/E3WRIKG3T42CXQNNDDXJBYUSOD/bundle.json","state":"https://pith.science/pith/E3WRIKG3T42CXQNNDDXJBYUSOD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E3WRIKG3T42CXQNNDDXJBYUSOD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E3WRIKG3T42CXQNNDDXJBYUSOD","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":"1cc39a755432af660a4f6a287eff1f78d3c5fed1ed4ab43ef1d5d52fdee33ef0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T06:04:52Z","title_canon_sha256":"6b6316fea5bfa5fdcde1d5f31cfe271b7eee3e6687d123e171a73265e96ec50c"},"schema_version":"1.0","source":{"id":"2410.06567","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06567","created_at":"2026-07-05T09:18:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06567v1","created_at":"2026-07-05T09:18:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06567","created_at":"2026-07-05T09:18:04Z"},{"alias_kind":"pith_short_12","alias_value":"E3WRIKG3T42C","created_at":"2026-07-05T09:18:04Z"},{"alias_kind":"pith_short_16","alias_value":"E3WRIKG3T42CXQNN","created_at":"2026-07-05T09:18:04Z"},{"alias_kind":"pith_short_8","alias_value":"E3WRIKG3","created_at":"2026-07-05T09:18:04Z"}],"graph_snapshots":[{"event_id":"sha256:8196cd2320c639303c2ff0931916a351e79e3f9c2ec7328ea074d65cf82ffaa0","target":"graph","created_at":"2026-07-05T09:18:04Z","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/2410.06567/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deploying large and complex deep neural networks on resource-constrained edge devices poses significant challenges due to their computational demands and the complexities of non-convex optimization. Traditional compression methods such as distillation and pruning often retain non-convexity that complicates fine-tuning in real-time on such devices. Moreover, these methods often necessitate extensive end-to-end network fine-tuning after compression to preserve model performance, which is not only time-consuming but also requires fully annotated datasets, thus potentially negating the benefits of","authors_text":"Mert Pilanci, Prateek Varshney","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T06:04:52Z","title":"Convex Distillation: Efficient Compression of Deep Networks via Convex Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06567","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:d6ac124c4f3597f0af3b36009dde2a281a77ea0df44da4f73ff1a108af6bf0bd","target":"record","created_at":"2026-07-05T09:18:04Z","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":"1cc39a755432af660a4f6a287eff1f78d3c5fed1ed4ab43ef1d5d52fdee33ef0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T06:04:52Z","title_canon_sha256":"6b6316fea5bfa5fdcde1d5f31cfe271b7eee3e6687d123e171a73265e96ec50c"},"schema_version":"1.0","source":{"id":"2410.06567","kind":"arxiv","version":1}},"canonical_sha256":"26ed1428db9f342bc1ad18ee90e29270fc7503467cb3eff49564ebd56b9ce532","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26ed1428db9f342bc1ad18ee90e29270fc7503467cb3eff49564ebd56b9ce532","first_computed_at":"2026-07-05T09:18:04.121422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:04.121422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1/PRvfWLSmVRqjmUe7Dz0yw0CIvVlo2NN77Yrp0J/SU8G1/+7xuUggHbnOBLkzZMhUb7/smg5SH3+WR0Bfi/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:04.121788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06567","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6ac124c4f3597f0af3b36009dde2a281a77ea0df44da4f73ff1a108af6bf0bd","sha256:8196cd2320c639303c2ff0931916a351e79e3f9c2ec7328ea074d65cf82ffaa0"],"state_sha256":"6de68cde4d7789b858bd785f1e8075da3e948f8bf7fe5a2babb389f9f65f9c0f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D3YNMcZn2UZEmjFGF040sooQjbw4h4tVCCs8CQGCL1KKTjG2YTAqLH7URteszJs3yyvNGVruEIKc+uHeoVIrAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T14:44:26.514485Z","bundle_sha256":"2b3d213de44d7b281f6e386849b6911704fda5ca92968959f4774fc628dc1779"}}