{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:2UYUGOCRFEWC56Y75U646ZCUPU","short_pith_number":"pith:2UYUGOCR","canonical_record":{"source":{"id":"1507.06149","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-22T12:18:21Z","cross_cats_sorted":[],"title_canon_sha256":"fc6096e2e443c238b824ba595af541da4f6167b8229c1833e66b00bbf3c411d8","abstract_canon_sha256":"1627cd739a50e574c3cb4e386ad11a61857db7f992ad753627a2efa3f39feafc"},"schema_version":"1.0"},"canonical_sha256":"d531433851292c2efb1fed3dcf64547d1b630a5cf94dbc40bb4a99cb51021ace","source":{"kind":"arxiv","id":"1507.06149","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.06149","created_at":"2026-05-18T01:36:26Z"},{"alias_kind":"arxiv_version","alias_value":"1507.06149v1","created_at":"2026-05-18T01:36:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.06149","created_at":"2026-05-18T01:36:26Z"},{"alias_kind":"pith_short_12","alias_value":"2UYUGOCRFEWC","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"2UYUGOCRFEWC56Y7","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"2UYUGOCR","created_at":"2026-05-18T12:29:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:2UYUGOCRFEWC56Y75U646ZCUPU","target":"record","payload":{"canonical_record":{"source":{"id":"1507.06149","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-22T12:18:21Z","cross_cats_sorted":[],"title_canon_sha256":"fc6096e2e443c238b824ba595af541da4f6167b8229c1833e66b00bbf3c411d8","abstract_canon_sha256":"1627cd739a50e574c3cb4e386ad11a61857db7f992ad753627a2efa3f39feafc"},"schema_version":"1.0"},"canonical_sha256":"d531433851292c2efb1fed3dcf64547d1b630a5cf94dbc40bb4a99cb51021ace","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:26.570636Z","signature_b64":"TgvDSIq7rfQsTM9mHZ8KJJ9USw88aOt//NYV4C/PVcutzFQjWSJ8TqSZ/pNCjf70gtoGLqC7jF9XBgtlsYtQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d531433851292c2efb1fed3dcf64547d1b630a5cf94dbc40bb4a99cb51021ace","last_reissued_at":"2026-05-18T01:36:26.570149Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:26.570149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.06149","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":"2026-05-18T01:36:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pc733j7AQajgqN5MxwQWju3bKGswXYkJ+eGfG6MU6RH4zW8YXsfY6gA7blTUnL9Vn/W7vohT4PikDPmAzh5DCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T05:35:15.727388Z"},"content_sha256":"fb67c0c872af3783eadc6b80e08a7f97c019a76a1f30df1430c2715648edcefa","schema_version":"1.0","event_id":"sha256:fb67c0c872af3783eadc6b80e08a7f97c019a76a1f30df1430c2715648edcefa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:2UYUGOCRFEWC56Y75U646ZCUPU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data-free parameter pruning for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"R. Venkatesh Babu, Suraj Srinivas","submitted_at":"2015-07-22T12:18:21Z","abstract_excerpt":"Deep Neural nets (NNs) with millions of parameters are at the heart of many state-of-the-art computer vision systems today. However, recent works have shown that much smaller models can achieve similar levels of performance. In this work, we address the problem of pruning parameters in a trained NN model. Instead of removing individual weights one at a time as done in previous works, we remove one neuron at a time. We show how similar neurons are redundant, and propose a systematic way to remove them. Our experiments in pruning the densely connected layers show that we can remove upto 85\\% of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.06149","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":"2026-05-18T01:36:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nUcHq77Lhw6EOLpqIYl5fixEu8F6UC9BZTfmIcU4QNN0rDbc7a2sn0KtBIe13aXTJnDk3wgxcB4VKRsrn/W0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T05:35:15.728041Z"},"content_sha256":"1905526b1d5f12aa461c92d7ac9db654ba59d9a03c685cd3a58364a88f9292d6","schema_version":"1.0","event_id":"sha256:1905526b1d5f12aa461c92d7ac9db654ba59d9a03c685cd3a58364a88f9292d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2UYUGOCRFEWC56Y75U646ZCUPU/bundle.json","state_url":"https://pith.science/pith/2UYUGOCRFEWC56Y75U646ZCUPU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2UYUGOCRFEWC56Y75U646ZCUPU/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":"2026-05-19T05:35:15Z","links":{"resolver":"https://pith.science/pith/2UYUGOCRFEWC56Y75U646ZCUPU","bundle":"https://pith.science/pith/2UYUGOCRFEWC56Y75U646ZCUPU/bundle.json","state":"https://pith.science/pith/2UYUGOCRFEWC56Y75U646ZCUPU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2UYUGOCRFEWC56Y75U646ZCUPU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:2UYUGOCRFEWC56Y75U646ZCUPU","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":"1627cd739a50e574c3cb4e386ad11a61857db7f992ad753627a2efa3f39feafc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-22T12:18:21Z","title_canon_sha256":"fc6096e2e443c238b824ba595af541da4f6167b8229c1833e66b00bbf3c411d8"},"schema_version":"1.0","source":{"id":"1507.06149","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.06149","created_at":"2026-05-18T01:36:26Z"},{"alias_kind":"arxiv_version","alias_value":"1507.06149v1","created_at":"2026-05-18T01:36:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.06149","created_at":"2026-05-18T01:36:26Z"},{"alias_kind":"pith_short_12","alias_value":"2UYUGOCRFEWC","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"2UYUGOCRFEWC56Y7","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"2UYUGOCR","created_at":"2026-05-18T12:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:1905526b1d5f12aa461c92d7ac9db654ba59d9a03c685cd3a58364a88f9292d6","target":"graph","created_at":"2026-05-18T01:36:26Z","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":"Deep Neural nets (NNs) with millions of parameters are at the heart of many state-of-the-art computer vision systems today. However, recent works have shown that much smaller models can achieve similar levels of performance. In this work, we address the problem of pruning parameters in a trained NN model. Instead of removing individual weights one at a time as done in previous works, we remove one neuron at a time. We show how similar neurons are redundant, and propose a systematic way to remove them. Our experiments in pruning the densely connected layers show that we can remove upto 85\\% of ","authors_text":"R. Venkatesh Babu, Suraj Srinivas","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-22T12:18:21Z","title":"Data-free parameter pruning for Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.06149","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:fb67c0c872af3783eadc6b80e08a7f97c019a76a1f30df1430c2715648edcefa","target":"record","created_at":"2026-05-18T01:36:26Z","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":"1627cd739a50e574c3cb4e386ad11a61857db7f992ad753627a2efa3f39feafc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-22T12:18:21Z","title_canon_sha256":"fc6096e2e443c238b824ba595af541da4f6167b8229c1833e66b00bbf3c411d8"},"schema_version":"1.0","source":{"id":"1507.06149","kind":"arxiv","version":1}},"canonical_sha256":"d531433851292c2efb1fed3dcf64547d1b630a5cf94dbc40bb4a99cb51021ace","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d531433851292c2efb1fed3dcf64547d1b630a5cf94dbc40bb4a99cb51021ace","first_computed_at":"2026-05-18T01:36:26.570149Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:36:26.570149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TgvDSIq7rfQsTM9mHZ8KJJ9USw88aOt//NYV4C/PVcutzFQjWSJ8TqSZ/pNCjf70gtoGLqC7jF9XBgtlsYtQDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:36:26.570636Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.06149","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb67c0c872af3783eadc6b80e08a7f97c019a76a1f30df1430c2715648edcefa","sha256:1905526b1d5f12aa461c92d7ac9db654ba59d9a03c685cd3a58364a88f9292d6"],"state_sha256":"21caa72d80ef97cd2c3ea8f23d4de6ffa704edbf558c981d5cb74c6a961c5412"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qhLRa9wWk3MXss5S4C6GmGJSAw7GTUKi3Kth9g58Mxei+bYJRTaEDFLUCASgo1OnIdtnt1xK7OZPfDx5JfFEBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T05:35:15.730366Z","bundle_sha256":"1a98eaabb0c8e5293903169902a32c5fc0e25b305a16e0f0680ecce24e3f13de"}}