{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:FU4WNTUKQ2AGSK5DRZYVEOMJHR","short_pith_number":"pith:FU4WNTUK","canonical_record":{"source":{"id":"1711.07459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-11-20T18:50:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"22fe85c478f53c88be0e320379190d0320fb983790eb7c70ae6f781d29c35c32","abstract_canon_sha256":"8f48952504d5da023475a2ced4c745968c27d1efac5431123486c6068904815d"},"schema_version":"1.0"},"canonical_sha256":"2d3966ce8a8680692ba38e715239893c6ac44a025dcd1e94f33c109c21c29ecf","source":{"kind":"arxiv","id":"1711.07459","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.07459","created_at":"2026-05-18T00:30:10Z"},{"alias_kind":"arxiv_version","alias_value":"1711.07459v1","created_at":"2026-05-18T00:30:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.07459","created_at":"2026-05-18T00:30:10Z"},{"alias_kind":"pith_short_12","alias_value":"FU4WNTUKQ2AG","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FU4WNTUKQ2AGSK5D","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FU4WNTUK","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:FU4WNTUKQ2AGSK5DRZYVEOMJHR","target":"record","payload":{"canonical_record":{"source":{"id":"1711.07459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-11-20T18:50:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"22fe85c478f53c88be0e320379190d0320fb983790eb7c70ae6f781d29c35c32","abstract_canon_sha256":"8f48952504d5da023475a2ced4c745968c27d1efac5431123486c6068904815d"},"schema_version":"1.0"},"canonical_sha256":"2d3966ce8a8680692ba38e715239893c6ac44a025dcd1e94f33c109c21c29ecf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:10.115381Z","signature_b64":"cqgYQwajarnhbZgq5yJnCA3AF0V6pe4/q+VdLi1JEseJtR5cdNIpNawby9VntzwU2t3z0XgmZW2FSw7oS0YTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d3966ce8a8680692ba38e715239893c6ac44a025dcd1e94f33c109c21c29ecf","last_reissued_at":"2026-05-18T00:30:10.114627Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:10.114627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.07459","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":"2026-05-18T00:30:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i9A3tAsAYpBVubhTe7qCaQ3/k7/UBhubpbu0DhoH55RFvjdGQAm9ZRaecLoc7KS1IoYOfGOjJkSz+CwSQT3PAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T08:39:06.647857Z"},"content_sha256":"c669f9bece84a555db076eece531c5cafc0b44a7c22ebd600eb66c2f3202b9ca","schema_version":"1.0","event_id":"sha256:c669f9bece84a555db076eece531c5cafc0b44a7c22ebd600eb66c2f3202b9ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:FU4WNTUKQ2AGSK5DRZYVEOMJHR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SquishedNets: Squishing SqueezeNet further for edge device scenarios via deep evolutionary synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Alexander Wong, Brendan Chwyl, Francis Li, Mohammad Javad Shafiee","submitted_at":"2017-11-20T18:50:05Z","abstract_excerpt":"While deep neural networks have been shown in recent years to outperform other machine learning methods in a wide range of applications, one of the biggest challenges with enabling deep neural networks for widespread deployment on edge devices such as mobile and other consumer devices is high computational and memory requirements. Recently, there has been greater exploration into small deep neural network architectures that are more suitable for edge devices, with one of the most popular architectures being SqueezeNet, with an incredibly small model size of 4.8MB. Taking further advantage of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.07459","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":"2026-05-18T00:30:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JDwCu3m0XQdGfmF0PBJ1xq+w3/5Q0IrtMtrA+wjFqBoeTVmYLP0u6FWJP55mUqRyVezi9SOzPDrlOmYVE+MrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T08:39:06.648206Z"},"content_sha256":"1b8bd1935e28f6acfb1ff5b4a5ecfeb6b7109e7170e8fec03bd8db74b7e035d5","schema_version":"1.0","event_id":"sha256:1b8bd1935e28f6acfb1ff5b4a5ecfeb6b7109e7170e8fec03bd8db74b7e035d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FU4WNTUKQ2AGSK5DRZYVEOMJHR/bundle.json","state_url":"https://pith.science/pith/FU4WNTUKQ2AGSK5DRZYVEOMJHR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FU4WNTUKQ2AGSK5DRZYVEOMJHR/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":"2026-06-02T08:39:06Z","links":{"resolver":"https://pith.science/pith/FU4WNTUKQ2AGSK5DRZYVEOMJHR","bundle":"https://pith.science/pith/FU4WNTUKQ2AGSK5DRZYVEOMJHR/bundle.json","state":"https://pith.science/pith/FU4WNTUKQ2AGSK5DRZYVEOMJHR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FU4WNTUKQ2AGSK5DRZYVEOMJHR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:FU4WNTUKQ2AGSK5DRZYVEOMJHR","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":"8f48952504d5da023475a2ced4c745968c27d1efac5431123486c6068904815d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-11-20T18:50:05Z","title_canon_sha256":"22fe85c478f53c88be0e320379190d0320fb983790eb7c70ae6f781d29c35c32"},"schema_version":"1.0","source":{"id":"1711.07459","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.07459","created_at":"2026-05-18T00:30:10Z"},{"alias_kind":"arxiv_version","alias_value":"1711.07459v1","created_at":"2026-05-18T00:30:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.07459","created_at":"2026-05-18T00:30:10Z"},{"alias_kind":"pith_short_12","alias_value":"FU4WNTUKQ2AG","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FU4WNTUKQ2AGSK5D","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FU4WNTUK","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:1b8bd1935e28f6acfb1ff5b4a5ecfeb6b7109e7170e8fec03bd8db74b7e035d5","target":"graph","created_at":"2026-05-18T00:30:10Z","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":"While deep neural networks have been shown in recent years to outperform other machine learning methods in a wide range of applications, one of the biggest challenges with enabling deep neural networks for widespread deployment on edge devices such as mobile and other consumer devices is high computational and memory requirements. Recently, there has been greater exploration into small deep neural network architectures that are more suitable for edge devices, with one of the most popular architectures being SqueezeNet, with an incredibly small model size of 4.8MB. Taking further advantage of t","authors_text":"Alexander Wong, Brendan Chwyl, Francis Li, Mohammad Javad Shafiee","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-11-20T18:50:05Z","title":"SquishedNets: Squishing SqueezeNet further for edge device scenarios via deep evolutionary synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.07459","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:c669f9bece84a555db076eece531c5cafc0b44a7c22ebd600eb66c2f3202b9ca","target":"record","created_at":"2026-05-18T00:30:10Z","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":"8f48952504d5da023475a2ced4c745968c27d1efac5431123486c6068904815d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-11-20T18:50:05Z","title_canon_sha256":"22fe85c478f53c88be0e320379190d0320fb983790eb7c70ae6f781d29c35c32"},"schema_version":"1.0","source":{"id":"1711.07459","kind":"arxiv","version":1}},"canonical_sha256":"2d3966ce8a8680692ba38e715239893c6ac44a025dcd1e94f33c109c21c29ecf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d3966ce8a8680692ba38e715239893c6ac44a025dcd1e94f33c109c21c29ecf","first_computed_at":"2026-05-18T00:30:10.114627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:10.114627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cqgYQwajarnhbZgq5yJnCA3AF0V6pe4/q+VdLi1JEseJtR5cdNIpNawby9VntzwU2t3z0XgmZW2FSw7oS0YTBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:10.115381Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.07459","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c669f9bece84a555db076eece531c5cafc0b44a7c22ebd600eb66c2f3202b9ca","sha256:1b8bd1935e28f6acfb1ff5b4a5ecfeb6b7109e7170e8fec03bd8db74b7e035d5"],"state_sha256":"a8b237f8a30956b68d91948aec24ef858c24a8b60126d9b9e2f065d632839b52"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4YZOHxAk66gqWce0ON8k93Dv+GZBFX669i9mWSYSXt1heIXOWyH5ZuR3UtQoutQTFNmH4AC20+R3GcFkvgWzAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T08:39:06.650287Z","bundle_sha256":"7fbbf4fb98d356264c0bafe358ad66d37448894b50cb908c37c74abd9df9e5b8"}}