{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QYNKER35FOIGSC3QMEAWAHTD3L","short_pith_number":"pith:QYNKER35","canonical_record":{"source":{"id":"1802.10399","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-28T13:26:46Z","cross_cats_sorted":[],"title_canon_sha256":"54eb84b6d415733ae8bc713b177a3ce3ddf60c7d50f3bafe19625871a7ec6936","abstract_canon_sha256":"a8755448865e9a415170a67e454e5cc6fb59696f75305388bb81a7dd5bd14db1"},"schema_version":"1.0"},"canonical_sha256":"861aa2477d2b90690b706101601e63dafaafed164c130e603031aaee35d7b1e6","source":{"kind":"arxiv","id":"1802.10399","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.10399","created_at":"2026-05-18T00:18:03Z"},{"alias_kind":"arxiv_version","alias_value":"1802.10399v3","created_at":"2026-05-18T00:18:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10399","created_at":"2026-05-18T00:18:03Z"},{"alias_kind":"pith_short_12","alias_value":"QYNKER35FOIG","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"QYNKER35FOIGSC3Q","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"QYNKER35","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QYNKER35FOIGSC3QMEAWAHTD3L","target":"record","payload":{"canonical_record":{"source":{"id":"1802.10399","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-28T13:26:46Z","cross_cats_sorted":[],"title_canon_sha256":"54eb84b6d415733ae8bc713b177a3ce3ddf60c7d50f3bafe19625871a7ec6936","abstract_canon_sha256":"a8755448865e9a415170a67e454e5cc6fb59696f75305388bb81a7dd5bd14db1"},"schema_version":"1.0"},"canonical_sha256":"861aa2477d2b90690b706101601e63dafaafed164c130e603031aaee35d7b1e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:03.734990Z","signature_b64":"EzFjaehjSroET7VmvvM7/ADqphOlLIHFjql2BoKMJId0iwx0WACO5SNCEmiZf+9smIln4BlxP1A+VS3J+y1VAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"861aa2477d2b90690b706101601e63dafaafed164c130e603031aaee35d7b1e6","last_reissued_at":"2026-05-18T00:18:03.734365Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:03.734365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.10399","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:18:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cK9QEVJh5VjVM8zlivh6XD3ti0FQkEfHPAUqZrPpyX5XKDoSKNd3iu1xmUDWrhF6g9Kld0i1Hmh2j1uIRugoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:17:57.348009Z"},"content_sha256":"44d1503d58baa09d5132059114e121cd5a77eeaa412d3f9cc60e84f8a8f3a929","schema_version":"1.0","event_id":"sha256:44d1503d58baa09d5132059114e121cd5a77eeaa412d3f9cc60e84f8a8f3a929"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QYNKER35FOIGSC3QMEAWAHTD3L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compressing Neural Networks using the Variational Information Bottleneck","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Dai, Chen Zhu, David Wipf","submitted_at":"2018-02-28T13:26:46Z","abstract_excerpt":"Neural networks can be compressed to reduce memory and computational requirements, or to increase accuracy by facilitating the use of a larger base architecture. In this paper we focus on pruning individual neurons, which can simultaneously trim model size, FLOPs, and run-time memory. To improve upon the performance of existing compression algorithms we utilize the information bottleneck principle instantiated via a tractable variational bound. Minimization of this information theoretic bound reduces the redundancy between adjacent layers by aggregating useful information into a subset of neur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10399","kind":"arxiv","version":3},"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":"2026-05-18T00:18:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XbkSID+oEUrU2BwwqpxoWCdcbrOMW9/o2acSFCpJMPN7fs7N73EAvz5glND4ofu8ShpNh19dfaMtA8IxRznBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:17:57.348507Z"},"content_sha256":"7b13165738e6b474d25ba8586677439fe671661ddf697fe1356578d291be3b25","schema_version":"1.0","event_id":"sha256:7b13165738e6b474d25ba8586677439fe671661ddf697fe1356578d291be3b25"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QYNKER35FOIGSC3QMEAWAHTD3L/bundle.json","state_url":"https://pith.science/pith/QYNKER35FOIGSC3QMEAWAHTD3L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QYNKER35FOIGSC3QMEAWAHTD3L/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":"2026-05-25T15:17:57Z","links":{"resolver":"https://pith.science/pith/QYNKER35FOIGSC3QMEAWAHTD3L","bundle":"https://pith.science/pith/QYNKER35FOIGSC3QMEAWAHTD3L/bundle.json","state":"https://pith.science/pith/QYNKER35FOIGSC3QMEAWAHTD3L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QYNKER35FOIGSC3QMEAWAHTD3L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QYNKER35FOIGSC3QMEAWAHTD3L","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":"a8755448865e9a415170a67e454e5cc6fb59696f75305388bb81a7dd5bd14db1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-28T13:26:46Z","title_canon_sha256":"54eb84b6d415733ae8bc713b177a3ce3ddf60c7d50f3bafe19625871a7ec6936"},"schema_version":"1.0","source":{"id":"1802.10399","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.10399","created_at":"2026-05-18T00:18:03Z"},{"alias_kind":"arxiv_version","alias_value":"1802.10399v3","created_at":"2026-05-18T00:18:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10399","created_at":"2026-05-18T00:18:03Z"},{"alias_kind":"pith_short_12","alias_value":"QYNKER35FOIG","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"QYNKER35FOIGSC3Q","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"QYNKER35","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:7b13165738e6b474d25ba8586677439fe671661ddf697fe1356578d291be3b25","target":"graph","created_at":"2026-05-18T00:18:03Z","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":"Neural networks can be compressed to reduce memory and computational requirements, or to increase accuracy by facilitating the use of a larger base architecture. In this paper we focus on pruning individual neurons, which can simultaneously trim model size, FLOPs, and run-time memory. To improve upon the performance of existing compression algorithms we utilize the information bottleneck principle instantiated via a tractable variational bound. Minimization of this information theoretic bound reduces the redundancy between adjacent layers by aggregating useful information into a subset of neur","authors_text":"Bin Dai, Chen Zhu, David Wipf","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-28T13:26:46Z","title":"Compressing Neural Networks using the Variational Information Bottleneck"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10399","kind":"arxiv","version":3},"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":"sha256:44d1503d58baa09d5132059114e121cd5a77eeaa412d3f9cc60e84f8a8f3a929","target":"record","created_at":"2026-05-18T00:18:03Z","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":"a8755448865e9a415170a67e454e5cc6fb59696f75305388bb81a7dd5bd14db1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-28T13:26:46Z","title_canon_sha256":"54eb84b6d415733ae8bc713b177a3ce3ddf60c7d50f3bafe19625871a7ec6936"},"schema_version":"1.0","source":{"id":"1802.10399","kind":"arxiv","version":3}},"canonical_sha256":"861aa2477d2b90690b706101601e63dafaafed164c130e603031aaee35d7b1e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"861aa2477d2b90690b706101601e63dafaafed164c130e603031aaee35d7b1e6","first_computed_at":"2026-05-18T00:18:03.734365Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:03.734365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EzFjaehjSroET7VmvvM7/ADqphOlLIHFjql2BoKMJId0iwx0WACO5SNCEmiZf+9smIln4BlxP1A+VS3J+y1VAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:03.734990Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.10399","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44d1503d58baa09d5132059114e121cd5a77eeaa412d3f9cc60e84f8a8f3a929","sha256:7b13165738e6b474d25ba8586677439fe671661ddf697fe1356578d291be3b25"],"state_sha256":"60da4eedbc75ee06fa26bcdb06a8331c0cd8abb88b252f112cbc311c26cd0bb8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0eH6WEcs4Fiz2rqKL64BZHvYgXgILsaPICCbJI34xJKBjvLYkWV6xyQdc/B4iXHyHeCp7/Vpc3a12mwRFJfOAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T15:17:57.351833Z","bundle_sha256":"71294619fbeea1618140b6ab101c60817078f8f3836794e3b174ee00fb5555fa"}}