{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:GER3HI436KRWKWRB2JVT3TLKFE","short_pith_number":"pith:GER3HI43","canonical_record":{"source":{"id":"1711.04686","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-13T16:28:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"173d2b4f47bb52cd7bc226580e4a92f0ac6182b1797b2c4ad23d75149e1a138a","abstract_canon_sha256":"b323e00cd2ae0daff95f56ecfd74df5060a1bd989b90b412cb3fc5f744f3315b"},"schema_version":"1.0"},"canonical_sha256":"3123b3a39bf2a3655a21d26b3dcd6a29161dc66b797741ae9b8f775d7667899d","source":{"kind":"arxiv","id":"1711.04686","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.04686","created_at":"2026-05-18T00:30:35Z"},{"alias_kind":"arxiv_version","alias_value":"1711.04686v1","created_at":"2026-05-18T00:30:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04686","created_at":"2026-05-18T00:30:35Z"},{"alias_kind":"pith_short_12","alias_value":"GER3HI436KRW","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"GER3HI436KRWKWRB","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"GER3HI43","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:GER3HI436KRWKWRB2JVT3TLKFE","target":"record","payload":{"canonical_record":{"source":{"id":"1711.04686","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-13T16:28:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"173d2b4f47bb52cd7bc226580e4a92f0ac6182b1797b2c4ad23d75149e1a138a","abstract_canon_sha256":"b323e00cd2ae0daff95f56ecfd74df5060a1bd989b90b412cb3fc5f744f3315b"},"schema_version":"1.0"},"canonical_sha256":"3123b3a39bf2a3655a21d26b3dcd6a29161dc66b797741ae9b8f775d7667899d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:35.913348Z","signature_b64":"9dgywBiWOs+StlYyU5ROyrLh+s5YMIpbGdXjrP9gJ2d2AXluLZTPxcOzvelyOctW8AFwxIanskhF3uNkjLxxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3123b3a39bf2a3655a21d26b3dcd6a29161dc66b797741ae9b8f775d7667899d","last_reissued_at":"2026-05-18T00:30:35.912633Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:35.912633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.04686","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":"2026-05-18T00:30:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kQXsxbDI4Bv707WBKTy6tX4uf375SsJFSUOz6L0+KgFTkxQIUy4x66Tf68lZ7H9eY/JwetyFVb6J1tUwDNNFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:52:19.708963Z"},"content_sha256":"9297a869d1c0c63b92f30557f196515c555371d3fb82ed9ad544db5ea46a8042","schema_version":"1.0","event_id":"sha256:9297a869d1c0c63b92f30557f196515c555371d3fb82ed9ad544db5ea46a8042"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:GER3HI436KRWKWRB2JVT3TLKFE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weightless: Lossy Weight Encoding For Deep Neural Network Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander M. Rush, Brandon Reagen, David Brooks, Gu-Yeon Wei, Michael M. Mitzenmacher, Robert Adolf, Udit Gupta","submitted_at":"2017-11-13T16:28:37Z","abstract_excerpt":"The large memory requirements of deep neural networks limit their deployment and adoption on many devices. Model compression methods effectively reduce the memory requirements of these models, usually through applying transformations such as weight pruning or quantization. In this paper, we present a novel scheme for lossy weight encoding which complements conventional compression techniques. The encoding is based on the Bloomier filter, a probabilistic data structure that can save space at the cost of introducing random errors. Leveraging the ability of neural networks to tolerate these imper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04686","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":""},"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":"2026-05-18T00:30:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5KxAo0Zt2SMzqBydGOy6wDHVKoFnY+Af7fV2ZG40A6dE2KVzhI3iES3P78nwnD9V3jnMOjjaf6euq477gilkAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:52:19.709329Z"},"content_sha256":"93a28e7a38af8db8be647184123a291ba33aeb692bc0ae2206a32b0f4294c0e7","schema_version":"1.0","event_id":"sha256:93a28e7a38af8db8be647184123a291ba33aeb692bc0ae2206a32b0f4294c0e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GER3HI436KRWKWRB2JVT3TLKFE/bundle.json","state_url":"https://pith.science/pith/GER3HI436KRWKWRB2JVT3TLKFE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GER3HI436KRWKWRB2JVT3TLKFE/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":"2026-05-29T16:52:19Z","links":{"resolver":"https://pith.science/pith/GER3HI436KRWKWRB2JVT3TLKFE","bundle":"https://pith.science/pith/GER3HI436KRWKWRB2JVT3TLKFE/bundle.json","state":"https://pith.science/pith/GER3HI436KRWKWRB2JVT3TLKFE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GER3HI436KRWKWRB2JVT3TLKFE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:GER3HI436KRWKWRB2JVT3TLKFE","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":"b323e00cd2ae0daff95f56ecfd74df5060a1bd989b90b412cb3fc5f744f3315b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-13T16:28:37Z","title_canon_sha256":"173d2b4f47bb52cd7bc226580e4a92f0ac6182b1797b2c4ad23d75149e1a138a"},"schema_version":"1.0","source":{"id":"1711.04686","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.04686","created_at":"2026-05-18T00:30:35Z"},{"alias_kind":"arxiv_version","alias_value":"1711.04686v1","created_at":"2026-05-18T00:30:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04686","created_at":"2026-05-18T00:30:35Z"},{"alias_kind":"pith_short_12","alias_value":"GER3HI436KRW","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"GER3HI436KRWKWRB","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"GER3HI43","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:93a28e7a38af8db8be647184123a291ba33aeb692bc0ae2206a32b0f4294c0e7","target":"graph","created_at":"2026-05-18T00:30:35Z","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":"The large memory requirements of deep neural networks limit their deployment and adoption on many devices. Model compression methods effectively reduce the memory requirements of these models, usually through applying transformations such as weight pruning or quantization. In this paper, we present a novel scheme for lossy weight encoding which complements conventional compression techniques. The encoding is based on the Bloomier filter, a probabilistic data structure that can save space at the cost of introducing random errors. Leveraging the ability of neural networks to tolerate these imper","authors_text":"Alexander M. Rush, Brandon Reagen, David Brooks, Gu-Yeon Wei, Michael M. Mitzenmacher, Robert Adolf, Udit Gupta","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-13T16:28:37Z","title":"Weightless: Lossy Weight Encoding For Deep Neural Network Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04686","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":"sha256:9297a869d1c0c63b92f30557f196515c555371d3fb82ed9ad544db5ea46a8042","target":"record","created_at":"2026-05-18T00:30:35Z","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":"b323e00cd2ae0daff95f56ecfd74df5060a1bd989b90b412cb3fc5f744f3315b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-13T16:28:37Z","title_canon_sha256":"173d2b4f47bb52cd7bc226580e4a92f0ac6182b1797b2c4ad23d75149e1a138a"},"schema_version":"1.0","source":{"id":"1711.04686","kind":"arxiv","version":1}},"canonical_sha256":"3123b3a39bf2a3655a21d26b3dcd6a29161dc66b797741ae9b8f775d7667899d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3123b3a39bf2a3655a21d26b3dcd6a29161dc66b797741ae9b8f775d7667899d","first_computed_at":"2026-05-18T00:30:35.912633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:35.912633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9dgywBiWOs+StlYyU5ROyrLh+s5YMIpbGdXjrP9gJ2d2AXluLZTPxcOzvelyOctW8AFwxIanskhF3uNkjLxxCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:35.913348Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.04686","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9297a869d1c0c63b92f30557f196515c555371d3fb82ed9ad544db5ea46a8042","sha256:93a28e7a38af8db8be647184123a291ba33aeb692bc0ae2206a32b0f4294c0e7"],"state_sha256":"b992fe05e344dbabf33c446dcd17986a0e621ad7ee8aa4180ec4b164e90c8429"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u+LS65SBCOiQU78ESgIimSeA7tWJeQ548nIPoWKCkQgX7uMuh9J7OQJ6FozMhsVwyrk3LiXCeicTSV5P3V7TCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T16:52:19.711308Z","bundle_sha256":"86a67a5132a0809c56264b95075a72077c17f3bf88c5cfa686dd5b83df4f73be"}}