{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FTVLF2TRLZUYEMZONFZUJRUVOC","short_pith_number":"pith:FTVLF2TR","schema_version":"1.0","canonical_sha256":"2ceab2ea715e6982332e697344c69570852db727b3bc2e4dcb255a3c22e29f4a","source":{"kind":"arxiv","id":"1911.07346","version":2},"attestation_state":"computed","paper":{"title":"Any-Precision Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gang Hua, Haichao Yu, Haoxiang Li, Honghui Shi, Thomas S. Huang","submitted_at":"2019-11-17T21:35:32Z","abstract_excerpt":"We present any-precision deep neural networks (DNNs), which are trained with a new method that allows the learned DNNs to be flexible in numerical precision during inference. The same model in runtime can be flexibly and directly set to different bit-widths, by truncating the least significant bits, to support dynamic speed and accuracy trade-off. When all layers are set to low-bits, we show that the model achieved accuracy comparable to dedicated models trained at the same precision. This nice property facilitates flexible deployment of deep learning models in real-world applications, where i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1911.07346","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-17T21:35:32Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"92153a728454d1b311c99aff3e589f8cc75f725b295772a5a4d0d4d03fb880c0","abstract_canon_sha256":"c90af10d6edffec4b1b08339bd9bfdf41b2d513d7a7c4771c67d4f8cae8713f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:01.112102Z","signature_b64":"GhB1z5QAlZeuh9IOMR8Ewrrh3kviRvbHZD04p8hrsp6y2n2fMf6v2QKpM2evtXP8n5JfB+7c1L4Culm/7W0LDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ceab2ea715e6982332e697344c69570852db727b3bc2e4dcb255a3c22e29f4a","last_reissued_at":"2026-07-05T02:07:01.111712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:01.111712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Any-Precision Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gang Hua, Haichao Yu, Haoxiang Li, Honghui Shi, Thomas S. Huang","submitted_at":"2019-11-17T21:35:32Z","abstract_excerpt":"We present any-precision deep neural networks (DNNs), which are trained with a new method that allows the learned DNNs to be flexible in numerical precision during inference. The same model in runtime can be flexibly and directly set to different bit-widths, by truncating the least significant bits, to support dynamic speed and accuracy trade-off. When all layers are set to low-bits, we show that the model achieved accuracy comparable to dedicated models trained at the same precision. This nice property facilitates flexible deployment of deep learning models in real-world applications, where i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.07346","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/1911.07346/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1911.07346","created_at":"2026-07-05T02:07:01.111769+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.07346v2","created_at":"2026-07-05T02:07:01.111769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.07346","created_at":"2026-07-05T02:07:01.111769+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTVLF2TRLZUY","created_at":"2026-07-05T02:07:01.111769+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTVLF2TRLZUYEMZO","created_at":"2026-07-05T02:07:01.111769+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTVLF2TR","created_at":"2026-07-05T02:07:01.111769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06786","citing_title":"Matryoshka Quantization","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FTVLF2TRLZUYEMZONFZUJRUVOC","json":"https://pith.science/pith/FTVLF2TRLZUYEMZONFZUJRUVOC.json","graph_json":"https://pith.science/api/pith-number/FTVLF2TRLZUYEMZONFZUJRUVOC/graph.json","events_json":"https://pith.science/api/pith-number/FTVLF2TRLZUYEMZONFZUJRUVOC/events.json","paper":"https://pith.science/paper/FTVLF2TR"},"agent_actions":{"view_html":"https://pith.science/pith/FTVLF2TRLZUYEMZONFZUJRUVOC","download_json":"https://pith.science/pith/FTVLF2TRLZUYEMZONFZUJRUVOC.json","view_paper":"https://pith.science/paper/FTVLF2TR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.07346&json=true","fetch_graph":"https://pith.science/api/pith-number/FTVLF2TRLZUYEMZONFZUJRUVOC/graph.json","fetch_events":"https://pith.science/api/pith-number/FTVLF2TRLZUYEMZONFZUJRUVOC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTVLF2TRLZUYEMZONFZUJRUVOC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTVLF2TRLZUYEMZONFZUJRUVOC/action/storage_attestation","attest_author":"https://pith.science/pith/FTVLF2TRLZUYEMZONFZUJRUVOC/action/author_attestation","sign_citation":"https://pith.science/pith/FTVLF2TRLZUYEMZONFZUJRUVOC/action/citation_signature","submit_replication":"https://pith.science/pith/FTVLF2TRLZUYEMZONFZUJRUVOC/action/replication_record"}},"created_at":"2026-07-05T02:07:01.111769+00:00","updated_at":"2026-07-05T02:07:01.111769+00:00"}