{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2IGN3G53W2ORAKEI2K5WPUIITJ","short_pith_number":"pith:2IGN3G53","canonical_record":{"source":{"id":"2310.12688","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T12:35:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"66257aea5f8a53afd29fe08dbba67d64925bda51776fc9c97e7302e9e1934312","abstract_canon_sha256":"2ff5751f6cda24b9e5efeb0a419b4178aac99de8f179d21d002ec8418cfc0493"},"schema_version":"1.0"},"canonical_sha256":"d20cdd9bbbb69d102888d2bb67d1089a6645eef49199c035069e7bb3dc855906","source":{"kind":"arxiv","id":"2310.12688","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12688","created_at":"2026-07-05T07:02:41Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12688v1","created_at":"2026-07-05T07:02:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12688","created_at":"2026-07-05T07:02:41Z"},{"alias_kind":"pith_short_12","alias_value":"2IGN3G53W2OR","created_at":"2026-07-05T07:02:41Z"},{"alias_kind":"pith_short_16","alias_value":"2IGN3G53W2ORAKEI","created_at":"2026-07-05T07:02:41Z"},{"alias_kind":"pith_short_8","alias_value":"2IGN3G53","created_at":"2026-07-05T07:02:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2IGN3G53W2ORAKEI2K5WPUIITJ","target":"record","payload":{"canonical_record":{"source":{"id":"2310.12688","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T12:35:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"66257aea5f8a53afd29fe08dbba67d64925bda51776fc9c97e7302e9e1934312","abstract_canon_sha256":"2ff5751f6cda24b9e5efeb0a419b4178aac99de8f179d21d002ec8418cfc0493"},"schema_version":"1.0"},"canonical_sha256":"d20cdd9bbbb69d102888d2bb67d1089a6645eef49199c035069e7bb3dc855906","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:41.450756Z","signature_b64":"EU3pLQRgz3OYUCnUJ7axZY0yzvATxoTzGHlxX1ac5BNpdzzjJ1KE7La7UvQ3RiUgwmSoj4AYAEh/QiSO/Io+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d20cdd9bbbb69d102888d2bb67d1089a6645eef49199c035069e7bb3dc855906","last_reissued_at":"2026-07-05T07:02:41.450281Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:41.450281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.12688","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":"2026-07-05T07:02:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MRId1mchLeg6kVRonAKl105hQCn0cz6gVApRP0/0lx9IobYfE5Jl03Yf2SC9xqbNi8fWI8vFUkyN9RP4n2eTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:19:03.542800Z"},"content_sha256":"e98ec1fa06ea622205862167e2e2c4e8a57dc65eb4bab8a9bd8b3b236a937578","schema_version":"1.0","event_id":"sha256:e98ec1fa06ea622205862167e2e2c4e8a57dc65eb4bab8a9bd8b3b236a937578"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2IGN3G53W2ORAKEI2K5WPUIITJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compression of Recurrent Neural Networks using Matrix Factorization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"H\\'elion du Mas des Bourboux, Lucas Maison, Thomas Courtat","submitted_at":"2023-10-19T12:35:30Z","abstract_excerpt":"Compressing neural networks is a key step when deploying models for real-time or embedded applications. Factorizing the model's matrices using low-rank approximations is a promising method for achieving compression. While it is possible to set the rank before training, this approach is neither flexible nor optimal. In this work, we propose a post-training rank-selection method called Rank-Tuning that selects a different rank for each matrix. Used in combination with training adaptations, our method achieves high compression rates with no or little performance degradation. Our numerical experim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12688","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/2310.12688/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":"2026-07-05T07:02:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BjbuB2GrQgWl0eZvKIpqSrNfz4i/4oyv4AOSueZ2NlXuXIk0rjQqHuulqMaNoHQHMkQRbDnmdL2Pq/+oEdURCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:19:03.543294Z"},"content_sha256":"af5867478017372e111bd467c5745783498feebfd405907f47d8937a5b0a51ba","schema_version":"1.0","event_id":"sha256:af5867478017372e111bd467c5745783498feebfd405907f47d8937a5b0a51ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2IGN3G53W2ORAKEI2K5WPUIITJ/bundle.json","state_url":"https://pith.science/pith/2IGN3G53W2ORAKEI2K5WPUIITJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2IGN3G53W2ORAKEI2K5WPUIITJ/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":"2026-08-08T18:19:03Z","links":{"resolver":"https://pith.science/pith/2IGN3G53W2ORAKEI2K5WPUIITJ","bundle":"https://pith.science/pith/2IGN3G53W2ORAKEI2K5WPUIITJ/bundle.json","state":"https://pith.science/pith/2IGN3G53W2ORAKEI2K5WPUIITJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2IGN3G53W2ORAKEI2K5WPUIITJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2IGN3G53W2ORAKEI2K5WPUIITJ","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":"2ff5751f6cda24b9e5efeb0a419b4178aac99de8f179d21d002ec8418cfc0493","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T12:35:30Z","title_canon_sha256":"66257aea5f8a53afd29fe08dbba67d64925bda51776fc9c97e7302e9e1934312"},"schema_version":"1.0","source":{"id":"2310.12688","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12688","created_at":"2026-07-05T07:02:41Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12688v1","created_at":"2026-07-05T07:02:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12688","created_at":"2026-07-05T07:02:41Z"},{"alias_kind":"pith_short_12","alias_value":"2IGN3G53W2OR","created_at":"2026-07-05T07:02:41Z"},{"alias_kind":"pith_short_16","alias_value":"2IGN3G53W2ORAKEI","created_at":"2026-07-05T07:02:41Z"},{"alias_kind":"pith_short_8","alias_value":"2IGN3G53","created_at":"2026-07-05T07:02:41Z"}],"graph_snapshots":[{"event_id":"sha256:af5867478017372e111bd467c5745783498feebfd405907f47d8937a5b0a51ba","target":"graph","created_at":"2026-07-05T07:02:41Z","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/2310.12688/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Compressing neural networks is a key step when deploying models for real-time or embedded applications. Factorizing the model's matrices using low-rank approximations is a promising method for achieving compression. While it is possible to set the rank before training, this approach is neither flexible nor optimal. In this work, we propose a post-training rank-selection method called Rank-Tuning that selects a different rank for each matrix. Used in combination with training adaptations, our method achieves high compression rates with no or little performance degradation. Our numerical experim","authors_text":"H\\'elion du Mas des Bourboux, Lucas Maison, Thomas Courtat","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T12:35:30Z","title":"Compression of Recurrent Neural Networks using Matrix Factorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12688","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:e98ec1fa06ea622205862167e2e2c4e8a57dc65eb4bab8a9bd8b3b236a937578","target":"record","created_at":"2026-07-05T07:02:41Z","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":"2ff5751f6cda24b9e5efeb0a419b4178aac99de8f179d21d002ec8418cfc0493","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T12:35:30Z","title_canon_sha256":"66257aea5f8a53afd29fe08dbba67d64925bda51776fc9c97e7302e9e1934312"},"schema_version":"1.0","source":{"id":"2310.12688","kind":"arxiv","version":1}},"canonical_sha256":"d20cdd9bbbb69d102888d2bb67d1089a6645eef49199c035069e7bb3dc855906","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d20cdd9bbbb69d102888d2bb67d1089a6645eef49199c035069e7bb3dc855906","first_computed_at":"2026-07-05T07:02:41.450281Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:41.450281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EU3pLQRgz3OYUCnUJ7axZY0yzvATxoTzGHlxX1ac5BNpdzzjJ1KE7La7UvQ3RiUgwmSoj4AYAEh/QiSO/Io+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:41.450756Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.12688","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e98ec1fa06ea622205862167e2e2c4e8a57dc65eb4bab8a9bd8b3b236a937578","sha256:af5867478017372e111bd467c5745783498feebfd405907f47d8937a5b0a51ba"],"state_sha256":"9f5a89c7b09b9f26ca87ade613c4f85d98b0e87abea7fc1aa5349db67a355c17"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EQ5Fr43Uujm8tQPdZUhWfR9sYiIIODUemMbggabOEWTLW8K0xS+aMX9ykoflYLG8GYdzUeYPgAy8fIJ0P8fhAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:19:03.547053Z","bundle_sha256":"d078718846de8bce3d441da89ad14e74105600417f4a8089313d1690982aea22"}}