{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NFMH3A7DV6PFDE4LKRXEO7DTMA","short_pith_number":"pith:NFMH3A7D","canonical_record":{"source":{"id":"2401.16438","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-26T21:51:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6bd9df07fc51883ac9428e9a6f6fae4e7d917697418f8654c4918b8b9f3fdf11","abstract_canon_sha256":"ef06acc0467f4c684b2deaa8ff44deab6719d2f014085ff9deed9f8659ad4654"},"schema_version":"1.0"},"canonical_sha256":"69587d83e3af9e51938b546e477c73600b15bfd0de4cda284d9d02656d02c9ef","source":{"kind":"arxiv","id":"2401.16438","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.16438","created_at":"2026-07-05T07:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2401.16438v1","created_at":"2026-07-05T07:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16438","created_at":"2026-07-05T07:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"NFMH3A7DV6PF","created_at":"2026-07-05T07:38:55Z"},{"alias_kind":"pith_short_16","alias_value":"NFMH3A7DV6PFDE4L","created_at":"2026-07-05T07:38:55Z"},{"alias_kind":"pith_short_8","alias_value":"NFMH3A7D","created_at":"2026-07-05T07:38:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NFMH3A7DV6PFDE4LKRXEO7DTMA","target":"record","payload":{"canonical_record":{"source":{"id":"2401.16438","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-26T21:51:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6bd9df07fc51883ac9428e9a6f6fae4e7d917697418f8654c4918b8b9f3fdf11","abstract_canon_sha256":"ef06acc0467f4c684b2deaa8ff44deab6719d2f014085ff9deed9f8659ad4654"},"schema_version":"1.0"},"canonical_sha256":"69587d83e3af9e51938b546e477c73600b15bfd0de4cda284d9d02656d02c9ef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:55.039915Z","signature_b64":"+Cymr+sf/34skbu6hAS3scVpjipGiNpATfit9Lb4tCsHb8cnD3/ngzrh88uft0azR3gsURRkM1ugbbec72oCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69587d83e3af9e51938b546e477c73600b15bfd0de4cda284d9d02656d02c9ef","last_reissued_at":"2026-07-05T07:38:55.039519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:55.039519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.16438","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":"2026-07-05T07:38:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R43N67hss8fBol9+GJB8JxQGFBzGFh3GIxIjm2YLt/TUdYN+xI5QHIv41ZCfXeBzH5bBw+50+unui17cYaR6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:40:24.777810Z"},"content_sha256":"d00dcfc41812d0cfca6a5432fb7a68b6349cf2fa672d6536c7c370e92d67d494","schema_version":"1.0","event_id":"sha256:d00dcfc41812d0cfca6a5432fb7a68b6349cf2fa672d6536c7c370e92d67d494"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NFMH3A7DV6PFDE4LKRXEO7DTMA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do deep neural networks utilize the weight space efficiently?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Beh\\c{c}et U\\u{g}ur T\\\"oreyin, Onur Can Koyun","submitted_at":"2024-01-26T21:51:49Z","abstract_excerpt":"Deep learning models like Transformers and Convolutional Neural Networks (CNNs) have revolutionized various domains, but their parameter-intensive nature hampers deployment in resource-constrained settings. In this paper, we introduce a novel concept utilizes column space and row space of weight matrices, which allows for a substantial reduction in model parameters without compromising performance. Leveraging this paradigm, we achieve parameter-efficient deep learning models.. Our approach applies to both Bottleneck and Attention layers, effectively halving the parameters while incurring only "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16438","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/2401.16438/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":"2026-07-05T07:38:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KCfDLRJN2nZpq1eDWO3UJGo3uncVsOgquFEqsSAX3xxW41VsxAWw29SMxDp8wRYOiSJK8mx8gDZOy3ysZ3a5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:40:24.778739Z"},"content_sha256":"e9ad53a344cbe094ff071149357e9d9c776c4cc86ec7d283cd1842285f214f24","schema_version":"1.0","event_id":"sha256:e9ad53a344cbe094ff071149357e9d9c776c4cc86ec7d283cd1842285f214f24"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NFMH3A7DV6PFDE4LKRXEO7DTMA/bundle.json","state_url":"https://pith.science/pith/NFMH3A7DV6PFDE4LKRXEO7DTMA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NFMH3A7DV6PFDE4LKRXEO7DTMA/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":"2026-08-03T21:40:24Z","links":{"resolver":"https://pith.science/pith/NFMH3A7DV6PFDE4LKRXEO7DTMA","bundle":"https://pith.science/pith/NFMH3A7DV6PFDE4LKRXEO7DTMA/bundle.json","state":"https://pith.science/pith/NFMH3A7DV6PFDE4LKRXEO7DTMA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NFMH3A7DV6PFDE4LKRXEO7DTMA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NFMH3A7DV6PFDE4LKRXEO7DTMA","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":"ef06acc0467f4c684b2deaa8ff44deab6719d2f014085ff9deed9f8659ad4654","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-26T21:51:49Z","title_canon_sha256":"6bd9df07fc51883ac9428e9a6f6fae4e7d917697418f8654c4918b8b9f3fdf11"},"schema_version":"1.0","source":{"id":"2401.16438","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.16438","created_at":"2026-07-05T07:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2401.16438v1","created_at":"2026-07-05T07:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16438","created_at":"2026-07-05T07:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"NFMH3A7DV6PF","created_at":"2026-07-05T07:38:55Z"},{"alias_kind":"pith_short_16","alias_value":"NFMH3A7DV6PFDE4L","created_at":"2026-07-05T07:38:55Z"},{"alias_kind":"pith_short_8","alias_value":"NFMH3A7D","created_at":"2026-07-05T07:38:55Z"}],"graph_snapshots":[{"event_id":"sha256:e9ad53a344cbe094ff071149357e9d9c776c4cc86ec7d283cd1842285f214f24","target":"graph","created_at":"2026-07-05T07:38:55Z","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/2401.16438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning models like Transformers and Convolutional Neural Networks (CNNs) have revolutionized various domains, but their parameter-intensive nature hampers deployment in resource-constrained settings. In this paper, we introduce a novel concept utilizes column space and row space of weight matrices, which allows for a substantial reduction in model parameters without compromising performance. Leveraging this paradigm, we achieve parameter-efficient deep learning models.. Our approach applies to both Bottleneck and Attention layers, effectively halving the parameters while incurring only ","authors_text":"Beh\\c{c}et U\\u{g}ur T\\\"oreyin, Onur Can Koyun","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-26T21:51:49Z","title":"Do deep neural networks utilize the weight space efficiently?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16438","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:d00dcfc41812d0cfca6a5432fb7a68b6349cf2fa672d6536c7c370e92d67d494","target":"record","created_at":"2026-07-05T07:38:55Z","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":"ef06acc0467f4c684b2deaa8ff44deab6719d2f014085ff9deed9f8659ad4654","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-26T21:51:49Z","title_canon_sha256":"6bd9df07fc51883ac9428e9a6f6fae4e7d917697418f8654c4918b8b9f3fdf11"},"schema_version":"1.0","source":{"id":"2401.16438","kind":"arxiv","version":1}},"canonical_sha256":"69587d83e3af9e51938b546e477c73600b15bfd0de4cda284d9d02656d02c9ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69587d83e3af9e51938b546e477c73600b15bfd0de4cda284d9d02656d02c9ef","first_computed_at":"2026-07-05T07:38:55.039519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:38:55.039519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Cymr+sf/34skbu6hAS3scVpjipGiNpATfit9Lb4tCsHb8cnD3/ngzrh88uft0azR3gsURRkM1ugbbec72oCBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:38:55.039915Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.16438","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d00dcfc41812d0cfca6a5432fb7a68b6349cf2fa672d6536c7c370e92d67d494","sha256:e9ad53a344cbe094ff071149357e9d9c776c4cc86ec7d283cd1842285f214f24"],"state_sha256":"8092483748c3279b1dd94f52ec0fd284eb13750c328ba33f50901d6abdecdb85"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vP9u8PeJp3CxQcAYrSudrUeiiK5p+6JQOlZqY+WCucM3Bu/tZGuReBcaUana6mqyOyk+8A2AyOCHdKeGaFphDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:40:24.787382Z","bundle_sha256":"f9ccaa6e22e1c69c36a152328271d0d1f60ccea616d6906a276dcd345fa7621f"}}