{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:WWJWBHHJZ6UZLYJ43MG32FSWFF","short_pith_number":"pith:WWJWBHHJ","canonical_record":{"source":{"id":"1707.09870","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-24T04:50:50Z","cross_cats_sorted":[],"title_canon_sha256":"6a437a44dac6a74d0f5a2ed0bd34c021ba12097fc6642d25ed18ca86e4968efe","abstract_canon_sha256":"5b217bafee40c4c163ddd5e5c58c543e1836053546cd1c41a9b270672b49ef69"},"schema_version":"1.0"},"canonical_sha256":"b593609ce9cfa995e13cdb0dbd1656295f0890d9f8c996a2b46d411111e36888","source":{"kind":"arxiv","id":"1707.09870","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.09870","created_at":"2026-05-18T00:35:16Z"},{"alias_kind":"arxiv_version","alias_value":"1707.09870v2","created_at":"2026-05-18T00:35:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09870","created_at":"2026-05-18T00:35:16Z"},{"alias_kind":"pith_short_12","alias_value":"WWJWBHHJZ6UZ","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WWJWBHHJZ6UZLYJ4","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WWJWBHHJ","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:WWJWBHHJZ6UZLYJ43MG32FSWFF","target":"record","payload":{"canonical_record":{"source":{"id":"1707.09870","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-24T04:50:50Z","cross_cats_sorted":[],"title_canon_sha256":"6a437a44dac6a74d0f5a2ed0bd34c021ba12097fc6642d25ed18ca86e4968efe","abstract_canon_sha256":"5b217bafee40c4c163ddd5e5c58c543e1836053546cd1c41a9b270672b49ef69"},"schema_version":"1.0"},"canonical_sha256":"b593609ce9cfa995e13cdb0dbd1656295f0890d9f8c996a2b46d411111e36888","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:16.033067Z","signature_b64":"cHQoaO7GZ1gXoUfGVf3JtW6q9qCCdmkLCjjhDZPmBxxZ/wo4toSRbrmE4OZGP6+L9tFcJa/rv209R6CD0xlJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b593609ce9cfa995e13cdb0dbd1656295f0890d9f8c996a2b46d411111e36888","last_reissued_at":"2026-05-18T00:35:16.032519Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:16.032519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.09870","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:35:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gx+SWMGuYQNsRctHBC4mf+YFZeH61Grh800qSPzKR8URjLKS+jLPe6Q5lpEGoc4MZd9oOKsaZ+oiIhGXuCmPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:13:17.718729Z"},"content_sha256":"c9753ddaf435c7abb4dc135305b27e9cabb67a8de9bccbcf3e1ea1d56653b382","schema_version":"1.0","event_id":"sha256:c9753ddaf435c7abb4dc135305b27e9cabb67a8de9bccbcf3e1ea1d56653b382"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:WWJWBHHJZ6UZLYJ43MG32FSWFF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Leng, Hao Li, Rong Jin, Shenghuo Zhu","submitted_at":"2017-07-24T04:50:50Z","abstract_excerpt":"Although deep learning models are highly effective for various learning tasks, their high computational costs prohibit the deployment to scenarios where either memory or computational resources are limited. In this paper, we focus on compressing and accelerating deep models with network weights represented by very small numbers of bits, referred to as extremely low bit neural network. We model this problem as a discretely constrained optimization problem. Borrowing the idea from Alternating Direction Method of Multipliers (ADMM), we decouple the continuous parameters from the discrete constrai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09870","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":""},"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":"2026-05-18T00:35:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J9tgevNvUhNOpu6pDz3rYfLPMGp8Z/hj2GR1XomLvfcW0r2VTh7su/UaIKhAKbsVAAlA3WxDYnZVjb45jfoaCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:13:17.719065Z"},"content_sha256":"011a323d1c982408e0e5130fe447d35d87415483a07f45b174c36059d2a98037","schema_version":"1.0","event_id":"sha256:011a323d1c982408e0e5130fe447d35d87415483a07f45b174c36059d2a98037"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WWJWBHHJZ6UZLYJ43MG32FSWFF/bundle.json","state_url":"https://pith.science/pith/WWJWBHHJZ6UZLYJ43MG32FSWFF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WWJWBHHJZ6UZLYJ43MG32FSWFF/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":"2026-06-02T23:13:17Z","links":{"resolver":"https://pith.science/pith/WWJWBHHJZ6UZLYJ43MG32FSWFF","bundle":"https://pith.science/pith/WWJWBHHJZ6UZLYJ43MG32FSWFF/bundle.json","state":"https://pith.science/pith/WWJWBHHJZ6UZLYJ43MG32FSWFF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WWJWBHHJZ6UZLYJ43MG32FSWFF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:WWJWBHHJZ6UZLYJ43MG32FSWFF","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":"5b217bafee40c4c163ddd5e5c58c543e1836053546cd1c41a9b270672b49ef69","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-24T04:50:50Z","title_canon_sha256":"6a437a44dac6a74d0f5a2ed0bd34c021ba12097fc6642d25ed18ca86e4968efe"},"schema_version":"1.0","source":{"id":"1707.09870","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.09870","created_at":"2026-05-18T00:35:16Z"},{"alias_kind":"arxiv_version","alias_value":"1707.09870v2","created_at":"2026-05-18T00:35:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09870","created_at":"2026-05-18T00:35:16Z"},{"alias_kind":"pith_short_12","alias_value":"WWJWBHHJZ6UZ","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WWJWBHHJZ6UZLYJ4","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WWJWBHHJ","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:011a323d1c982408e0e5130fe447d35d87415483a07f45b174c36059d2a98037","target":"graph","created_at":"2026-05-18T00:35:16Z","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"},"paper":{"abstract_excerpt":"Although deep learning models are highly effective for various learning tasks, their high computational costs prohibit the deployment to scenarios where either memory or computational resources are limited. In this paper, we focus on compressing and accelerating deep models with network weights represented by very small numbers of bits, referred to as extremely low bit neural network. We model this problem as a discretely constrained optimization problem. Borrowing the idea from Alternating Direction Method of Multipliers (ADMM), we decouple the continuous parameters from the discrete constrai","authors_text":"Cong Leng, Hao Li, Rong Jin, Shenghuo Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-24T04:50:50Z","title":"Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09870","kind":"arxiv","version":2},"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:c9753ddaf435c7abb4dc135305b27e9cabb67a8de9bccbcf3e1ea1d56653b382","target":"record","created_at":"2026-05-18T00:35:16Z","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":"5b217bafee40c4c163ddd5e5c58c543e1836053546cd1c41a9b270672b49ef69","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-24T04:50:50Z","title_canon_sha256":"6a437a44dac6a74d0f5a2ed0bd34c021ba12097fc6642d25ed18ca86e4968efe"},"schema_version":"1.0","source":{"id":"1707.09870","kind":"arxiv","version":2}},"canonical_sha256":"b593609ce9cfa995e13cdb0dbd1656295f0890d9f8c996a2b46d411111e36888","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b593609ce9cfa995e13cdb0dbd1656295f0890d9f8c996a2b46d411111e36888","first_computed_at":"2026-05-18T00:35:16.032519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:16.032519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cHQoaO7GZ1gXoUfGVf3JtW6q9qCCdmkLCjjhDZPmBxxZ/wo4toSRbrmE4OZGP6+L9tFcJa/rv209R6CD0xlJCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:16.033067Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.09870","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9753ddaf435c7abb4dc135305b27e9cabb67a8de9bccbcf3e1ea1d56653b382","sha256:011a323d1c982408e0e5130fe447d35d87415483a07f45b174c36059d2a98037"],"state_sha256":"f3aef7dc9549c817b9638c404c9d31cb954da66c5fa5023247a39fa5dbf51f7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mWUyhttviwW666rVRVbEn8FHhm6tDIIqdUsmCfAGgEtpKUqkBsyP8Juhl3tDS57nbPixioSZtya3LyEEF+MuAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T23:13:17.720943Z","bundle_sha256":"33e7d754049bed2b29c15bd1dfd92b88f634448d589a9bda00caf0890c8efc6c"}}