{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:4ELSUFWNAZOAYSYDGY3XZOM567","short_pith_number":"pith:4ELSUFWN","canonical_record":{"source":{"id":"1506.04449","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-14T23:16:40Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"d59567c62b0d9f15fcf6d5b00e830fc17521256f4a56c4877c2c563dfc0d6bb3","abstract_canon_sha256":"aed3727309f3f844d6e7423bb017f239e8f5bad68ff4dbb5ad36d3ccbb92fd8a"},"schema_version":"1.0"},"canonical_sha256":"e1172a16cd065c0c4b0336377cb99df7c84d55b4c351341e92249c46a5e82b0d","source":{"kind":"arxiv","id":"1506.04449","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.04449","created_at":"2026-05-18T01:49:54Z"},{"alias_kind":"arxiv_version","alias_value":"1506.04449v1","created_at":"2026-05-18T01:49:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.04449","created_at":"2026-05-18T01:49:54Z"},{"alias_kind":"pith_short_12","alias_value":"4ELSUFWNAZOA","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"4ELSUFWNAZOAYSYD","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"4ELSUFWN","created_at":"2026-05-18T12:29:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:4ELSUFWNAZOAYSYDGY3XZOM567","target":"record","payload":{"canonical_record":{"source":{"id":"1506.04449","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-14T23:16:40Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"d59567c62b0d9f15fcf6d5b00e830fc17521256f4a56c4877c2c563dfc0d6bb3","abstract_canon_sha256":"aed3727309f3f844d6e7423bb017f239e8f5bad68ff4dbb5ad36d3ccbb92fd8a"},"schema_version":"1.0"},"canonical_sha256":"e1172a16cd065c0c4b0336377cb99df7c84d55b4c351341e92249c46a5e82b0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:49:54.535027Z","signature_b64":"N0Mudn2k3GhXnMlkMx1jtcnmXPFBaeohrgiTKftEgil+/WO1tCbboVTF5+aHpUU3snU+TSXMennwDGv+Oo1dAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1172a16cd065c0c4b0336377cb99df7c84d55b4c351341e92249c46a5e82b0d","last_reissued_at":"2026-05-18T01:49:54.534594Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:49:54.534594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.04449","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":"2026-05-18T01:49:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yip91rJ94mMsvem9QHK4Cs5//xOeUKRecf1S1wOLg3wT7pOLeReb5dGENfLU0m0ETW8M9nUB0E/+H2IpyvA6Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:06:01.882145Z"},"content_sha256":"8907c0b8cd08155d31c33ecc29619bd46d26448a2d41ba6e4b18a64becd32c31","schema_version":"1.0","event_id":"sha256:8907c0b8cd08155d31c33ecc29619bd46d26448a2d41ba6e4b18a64becd32c31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:4ELSUFWNAZOAYSYDGY3XZOM567","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compressing Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"James T. Wilson, Kilian Q. Weinberger, Stephen Tyree, Wenlin Chen, Yixin Chen","submitted_at":"2015-06-14T23:16:40Z","abstract_excerpt":"Convolutional neural networks (CNN) are increasingly used in many areas of computer vision. They are particularly attractive because of their ability to \"absorb\" great quantities of labeled data through millions of parameters. However, as model sizes increase, so do the storage and memory requirements of the classifiers. We present a novel network architecture, Frequency-Sensitive Hashed Nets (FreshNets), which exploits inherent redundancy in both convolutional layers and fully-connected layers of a deep learning model, leading to dramatic savings in memory and storage consumption. Based on th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.04449","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":"2026-05-18T01:49:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D8ddw3WnbsWXlqkW0a0JRT+9pIOdaRO61ZKCvvBLms9clpl0MsjiJofV8S1UwMi9/ixlNibWZYSYXEvPaYW6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:06:01.882812Z"},"content_sha256":"794a758ad7fd42319751b182adcfa0743dc41716aa68d7f6e76ce68e10513afb","schema_version":"1.0","event_id":"sha256:794a758ad7fd42319751b182adcfa0743dc41716aa68d7f6e76ce68e10513afb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4ELSUFWNAZOAYSYDGY3XZOM567/bundle.json","state_url":"https://pith.science/pith/4ELSUFWNAZOAYSYDGY3XZOM567/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4ELSUFWNAZOAYSYDGY3XZOM567/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":"2026-05-29T18:06:01Z","links":{"resolver":"https://pith.science/pith/4ELSUFWNAZOAYSYDGY3XZOM567","bundle":"https://pith.science/pith/4ELSUFWNAZOAYSYDGY3XZOM567/bundle.json","state":"https://pith.science/pith/4ELSUFWNAZOAYSYDGY3XZOM567/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4ELSUFWNAZOAYSYDGY3XZOM567/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:4ELSUFWNAZOAYSYDGY3XZOM567","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":"aed3727309f3f844d6e7423bb017f239e8f5bad68ff4dbb5ad36d3ccbb92fd8a","cross_cats_sorted":["cs.CV","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-14T23:16:40Z","title_canon_sha256":"d59567c62b0d9f15fcf6d5b00e830fc17521256f4a56c4877c2c563dfc0d6bb3"},"schema_version":"1.0","source":{"id":"1506.04449","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.04449","created_at":"2026-05-18T01:49:54Z"},{"alias_kind":"arxiv_version","alias_value":"1506.04449v1","created_at":"2026-05-18T01:49:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.04449","created_at":"2026-05-18T01:49:54Z"},{"alias_kind":"pith_short_12","alias_value":"4ELSUFWNAZOA","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"4ELSUFWNAZOAYSYD","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"4ELSUFWN","created_at":"2026-05-18T12:29:05Z"}],"graph_snapshots":[{"event_id":"sha256:794a758ad7fd42319751b182adcfa0743dc41716aa68d7f6e76ce68e10513afb","target":"graph","created_at":"2026-05-18T01:49:54Z","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":"Convolutional neural networks (CNN) are increasingly used in many areas of computer vision. They are particularly attractive because of their ability to \"absorb\" great quantities of labeled data through millions of parameters. However, as model sizes increase, so do the storage and memory requirements of the classifiers. We present a novel network architecture, Frequency-Sensitive Hashed Nets (FreshNets), which exploits inherent redundancy in both convolutional layers and fully-connected layers of a deep learning model, leading to dramatic savings in memory and storage consumption. Based on th","authors_text":"James T. Wilson, Kilian Q. Weinberger, Stephen Tyree, Wenlin Chen, Yixin Chen","cross_cats":["cs.CV","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-14T23:16:40Z","title":"Compressing Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.04449","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":"sha256:8907c0b8cd08155d31c33ecc29619bd46d26448a2d41ba6e4b18a64becd32c31","target":"record","created_at":"2026-05-18T01:49:54Z","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":"aed3727309f3f844d6e7423bb017f239e8f5bad68ff4dbb5ad36d3ccbb92fd8a","cross_cats_sorted":["cs.CV","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-14T23:16:40Z","title_canon_sha256":"d59567c62b0d9f15fcf6d5b00e830fc17521256f4a56c4877c2c563dfc0d6bb3"},"schema_version":"1.0","source":{"id":"1506.04449","kind":"arxiv","version":1}},"canonical_sha256":"e1172a16cd065c0c4b0336377cb99df7c84d55b4c351341e92249c46a5e82b0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1172a16cd065c0c4b0336377cb99df7c84d55b4c351341e92249c46a5e82b0d","first_computed_at":"2026-05-18T01:49:54.534594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:49:54.534594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N0Mudn2k3GhXnMlkMx1jtcnmXPFBaeohrgiTKftEgil+/WO1tCbboVTF5+aHpUU3snU+TSXMennwDGv+Oo1dAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:49:54.535027Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.04449","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8907c0b8cd08155d31c33ecc29619bd46d26448a2d41ba6e4b18a64becd32c31","sha256:794a758ad7fd42319751b182adcfa0743dc41716aa68d7f6e76ce68e10513afb"],"state_sha256":"428c5a6333bf9a03e86303a41f4645bdaf413bdc3155faefd11bceec8cb5dac9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+X93vRfNuwM0IXkQmmu7NtLnCtUU9I/5QQiZNVXYCmEb2S2MmITaufjSD2KrlCSJ2vga2xhgic0Xp7EGr4fmAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T18:06:01.886200Z","bundle_sha256":"d3120e10904b3c031032ac75842f64d9dd14d9e938aa7941c1017dfd67add2b5"}}