{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:EAIILGGS4KT44COSGDCAPFUJB3","short_pith_number":"pith:EAIILGGS","canonical_record":{"source":{"id":"1910.04576","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-09T07:27:33Z","cross_cats_sorted":[],"title_canon_sha256":"d8a6eb18d9a7cfe7567702cec40222f6ddf01392028de7e4c709585968bf0350","abstract_canon_sha256":"302ab2f27e3ba8b519380762860918d14a7567ce5bfd4101e2681d6a5468f9f8"},"schema_version":"1.0"},"canonical_sha256":"20108598d2e2a7ce09d230c40796890ee7ab40ea418957a09fb30b6c23e6f506","source":{"kind":"arxiv","id":"1910.04576","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.04576","created_at":"2026-07-05T00:35:33Z"},{"alias_kind":"arxiv_version","alias_value":"1910.04576v4","created_at":"2026-07-05T00:35:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.04576","created_at":"2026-07-05T00:35:33Z"},{"alias_kind":"pith_short_12","alias_value":"EAIILGGS4KT4","created_at":"2026-07-05T00:35:33Z"},{"alias_kind":"pith_short_16","alias_value":"EAIILGGS4KT44COS","created_at":"2026-07-05T00:35:33Z"},{"alias_kind":"pith_short_8","alias_value":"EAIILGGS","created_at":"2026-07-05T00:35:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:EAIILGGS4KT44COSGDCAPFUJB3","target":"record","payload":{"canonical_record":{"source":{"id":"1910.04576","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-09T07:27:33Z","cross_cats_sorted":[],"title_canon_sha256":"d8a6eb18d9a7cfe7567702cec40222f6ddf01392028de7e4c709585968bf0350","abstract_canon_sha256":"302ab2f27e3ba8b519380762860918d14a7567ce5bfd4101e2681d6a5468f9f8"},"schema_version":"1.0"},"canonical_sha256":"20108598d2e2a7ce09d230c40796890ee7ab40ea418957a09fb30b6c23e6f506","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:33.770235Z","signature_b64":"OmBz+EIVfEpA8iCfJZulLX2xFmgg14u7T6OZEj0M/sD20MRaMi4+uu7YnmuOGLjGL3JI6ot9iO5wfSRyJmsRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20108598d2e2a7ce09d230c40796890ee7ab40ea418957a09fb30b6c23e6f506","last_reissued_at":"2026-07-05T00:35:33.769849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:33.769849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.04576","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:35:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e7dj7/T7Mx+MFnTBPhYKlOPJk7HgISDPnNSv/GfTJg/0av8oLB6PFTCrSh6Voqc5taF1FqlQIHe3j9RCdYbxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T22:30:08.204544Z"},"content_sha256":"31673cd305b6afaca720de55819353035b3da0453854fd7bcd511a861d5dd8f2","schema_version":"1.0","event_id":"sha256:31673cd305b6afaca720de55819353035b3da0453854fd7bcd511a861d5dd8f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:EAIILGGS4KT44COSGDCAPFUJB3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Trained Rank Pruning for Efficient Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Botao Wang, Hongkai Xiong, Shuai Zhang, Wei Wen, Weiyao Lin, Wenrui Dai, Yingyong Qi, Yiran Chen, Yuhui Xu, Yuxi Li","submitted_at":"2019-10-09T07:27:33Z","abstract_excerpt":"To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a pre-trained model by low-rank decomposition; however, small approximation errors in parameters can ripple over a large prediction loss. Apparently, it is not optimal to separate low-rank approximation from training. Unlike previous works, this paper integrates low rank approximation and regularization into the training process. We propose Trained Rank Pruning (TRP), which alternates betw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.04576","kind":"arxiv","version":4},"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/1910.04576/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":"2026-07-05T00:35:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4WOvTYbV47/jpcCS4k8X4FJV4+h0TO6seXyj6krs6dFS0Xb8TONCOXlGVLDZnV74/+CJ4Jyv2MScp3nO0H5OBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T22:30:08.204911Z"},"content_sha256":"d45abfba96f72bd9e300500951ea2e8b72ae168fec0a4d8878f89c2dce75825f","schema_version":"1.0","event_id":"sha256:d45abfba96f72bd9e300500951ea2e8b72ae168fec0a4d8878f89c2dce75825f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EAIILGGS4KT44COSGDCAPFUJB3/bundle.json","state_url":"https://pith.science/pith/EAIILGGS4KT44COSGDCAPFUJB3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EAIILGGS4KT44COSGDCAPFUJB3/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":"2026-07-08T22:30:08Z","links":{"resolver":"https://pith.science/pith/EAIILGGS4KT44COSGDCAPFUJB3","bundle":"https://pith.science/pith/EAIILGGS4KT44COSGDCAPFUJB3/bundle.json","state":"https://pith.science/pith/EAIILGGS4KT44COSGDCAPFUJB3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EAIILGGS4KT44COSGDCAPFUJB3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:EAIILGGS4KT44COSGDCAPFUJB3","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":"302ab2f27e3ba8b519380762860918d14a7567ce5bfd4101e2681d6a5468f9f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-09T07:27:33Z","title_canon_sha256":"d8a6eb18d9a7cfe7567702cec40222f6ddf01392028de7e4c709585968bf0350"},"schema_version":"1.0","source":{"id":"1910.04576","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.04576","created_at":"2026-07-05T00:35:33Z"},{"alias_kind":"arxiv_version","alias_value":"1910.04576v4","created_at":"2026-07-05T00:35:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.04576","created_at":"2026-07-05T00:35:33Z"},{"alias_kind":"pith_short_12","alias_value":"EAIILGGS4KT4","created_at":"2026-07-05T00:35:33Z"},{"alias_kind":"pith_short_16","alias_value":"EAIILGGS4KT44COS","created_at":"2026-07-05T00:35:33Z"},{"alias_kind":"pith_short_8","alias_value":"EAIILGGS","created_at":"2026-07-05T00:35:33Z"}],"graph_snapshots":[{"event_id":"sha256:d45abfba96f72bd9e300500951ea2e8b72ae168fec0a4d8878f89c2dce75825f","target":"graph","created_at":"2026-07-05T00:35:33Z","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/1910.04576/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a pre-trained model by low-rank decomposition; however, small approximation errors in parameters can ripple over a large prediction loss. Apparently, it is not optimal to separate low-rank approximation from training. Unlike previous works, this paper integrates low rank approximation and regularization into the training process. We propose Trained Rank Pruning (TRP), which alternates betw","authors_text":"Botao Wang, Hongkai Xiong, Shuai Zhang, Wei Wen, Weiyao Lin, Wenrui Dai, Yingyong Qi, Yiran Chen, Yuhui Xu, Yuxi Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-09T07:27:33Z","title":"Trained Rank Pruning for Efficient Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.04576","kind":"arxiv","version":4},"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":"sha256:31673cd305b6afaca720de55819353035b3da0453854fd7bcd511a861d5dd8f2","target":"record","created_at":"2026-07-05T00:35:33Z","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":"302ab2f27e3ba8b519380762860918d14a7567ce5bfd4101e2681d6a5468f9f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-09T07:27:33Z","title_canon_sha256":"d8a6eb18d9a7cfe7567702cec40222f6ddf01392028de7e4c709585968bf0350"},"schema_version":"1.0","source":{"id":"1910.04576","kind":"arxiv","version":4}},"canonical_sha256":"20108598d2e2a7ce09d230c40796890ee7ab40ea418957a09fb30b6c23e6f506","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20108598d2e2a7ce09d230c40796890ee7ab40ea418957a09fb30b6c23e6f506","first_computed_at":"2026-07-05T00:35:33.769849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:35:33.769849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OmBz+EIVfEpA8iCfJZulLX2xFmgg14u7T6OZEj0M/sD20MRaMi4+uu7YnmuOGLjGL3JI6ot9iO5wfSRyJmsRDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:35:33.770235Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.04576","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31673cd305b6afaca720de55819353035b3da0453854fd7bcd511a861d5dd8f2","sha256:d45abfba96f72bd9e300500951ea2e8b72ae168fec0a4d8878f89c2dce75825f"],"state_sha256":"7467a41da3422f2cdc904fdab869f8915589c6f21e56ecd0a47cd39e806b4b19"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tlfHDyPu1v3C3BjzNNpGAhtkRAK1h6uwE0wIoU+7EdUOf3Snlb9jOuhESnE/+RHCI+SZQ9WUtoaJx1oYhOM2DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T22:30:08.207000Z","bundle_sha256":"6197bcc4c19f34452393c479f3714bf37e88fd4467905b0ad69cdf4705237860"}}