{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:DNC4YBFONGYRJS53HBS2L4J7YX","short_pith_number":"pith:DNC4YBFO","canonical_record":{"source":{"id":"1908.08926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-20T23:26:04Z","cross_cats_sorted":[],"title_canon_sha256":"930180de636d073e948431b665decca247c469f0ff68537884f4ad47f3a2313b","abstract_canon_sha256":"9bdf4b84e99abe620d861abbf5ccea7b90dbf469cff144a966ca686773482a30"},"schema_version":"1.0"},"canonical_sha256":"1b45cc04ae69b114cbbb3865a5f13fc5c39640816eb2c6bfa22cbab5b3bb821f","source":{"kind":"arxiv","id":"1908.08926","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08926","created_at":"2026-07-04T23:59:25Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08926v1","created_at":"2026-07-04T23:59:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08926","created_at":"2026-07-04T23:59:25Z"},{"alias_kind":"pith_short_12","alias_value":"DNC4YBFONGYR","created_at":"2026-07-04T23:59:25Z"},{"alias_kind":"pith_short_16","alias_value":"DNC4YBFONGYRJS53","created_at":"2026-07-04T23:59:25Z"},{"alias_kind":"pith_short_8","alias_value":"DNC4YBFO","created_at":"2026-07-04T23:59:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:DNC4YBFONGYRJS53HBS2L4J7YX","target":"record","payload":{"canonical_record":{"source":{"id":"1908.08926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-20T23:26:04Z","cross_cats_sorted":[],"title_canon_sha256":"930180de636d073e948431b665decca247c469f0ff68537884f4ad47f3a2313b","abstract_canon_sha256":"9bdf4b84e99abe620d861abbf5ccea7b90dbf469cff144a966ca686773482a30"},"schema_version":"1.0"},"canonical_sha256":"1b45cc04ae69b114cbbb3865a5f13fc5c39640816eb2c6bfa22cbab5b3bb821f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:25.287431Z","signature_b64":"C6DR5YohIKA55PMG1O0+IqQd1ZPQ6KDDMhXttvLQ0res7EDxN+KqScug260gUZq+XT3+zUze2Lyz2vdqoGyMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b45cc04ae69b114cbbb3865a5f13fc5c39640816eb2c6bfa22cbab5b3bb821f","last_reissued_at":"2026-07-04T23:59:25.287048Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:25.287048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.08926","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":"2026-07-04T23:59:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y9p5xfd05+QcoWODIyz+C+LrVCHC5Roe5R/UvrGC+n92zau37hZG7jOUT5IJyKHE3irxOSLEHNfFL72iz54rAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:15:53.066131Z"},"content_sha256":"4e71409c5171ef9d1240e93103c7186efb1964d4cdf9a34cd760cf6fe075238e","schema_version":"1.0","event_id":"sha256:4e71409c5171ef9d1240e93103c7186efb1964d4cdf9a34cd760cf6fe075238e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:DNC4YBFONGYRJS53HBS2L4J7YX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bichen Wu","submitted_at":"2019-08-20T23:26:04Z","abstract_excerpt":"The success of deep neural networks (DNNs) is attributable to three factors: increased compute capacity, more complex models, and more data. These factors, however, are not always present, especially for edge applications such as autonomous driving, augmented reality, and internet-of-things. Training DNNs requires a large amount of data, which is difficult to obtain. Edge devices such as mobile phones have limited compute capacity, and therefore, require specialized and efficient DNNs. However, due to the enormous design space and prohibitive training costs, designing efficient DNNs for differ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08926","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.08926/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-04T23:59:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UatM8o0ebnkY8TT8rscuyNNC8e0B66EdtbypSDTu86mBk3oDe0zuTFkEcVa9whOXgdPXEVGZ9phBgzC77DIaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:15:53.068060Z"},"content_sha256":"291dd599b978c15c504506df766b870745b8457d16cff6fb54348a3a50dd9211","schema_version":"1.0","event_id":"sha256:291dd599b978c15c504506df766b870745b8457d16cff6fb54348a3a50dd9211"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DNC4YBFONGYRJS53HBS2L4J7YX/bundle.json","state_url":"https://pith.science/pith/DNC4YBFONGYRJS53HBS2L4J7YX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DNC4YBFONGYRJS53HBS2L4J7YX/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":"2026-08-14T19:15:53Z","links":{"resolver":"https://pith.science/pith/DNC4YBFONGYRJS53HBS2L4J7YX","bundle":"https://pith.science/pith/DNC4YBFONGYRJS53HBS2L4J7YX/bundle.json","state":"https://pith.science/pith/DNC4YBFONGYRJS53HBS2L4J7YX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DNC4YBFONGYRJS53HBS2L4J7YX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DNC4YBFONGYRJS53HBS2L4J7YX","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":"9bdf4b84e99abe620d861abbf5ccea7b90dbf469cff144a966ca686773482a30","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-20T23:26:04Z","title_canon_sha256":"930180de636d073e948431b665decca247c469f0ff68537884f4ad47f3a2313b"},"schema_version":"1.0","source":{"id":"1908.08926","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08926","created_at":"2026-07-04T23:59:25Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08926v1","created_at":"2026-07-04T23:59:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08926","created_at":"2026-07-04T23:59:25Z"},{"alias_kind":"pith_short_12","alias_value":"DNC4YBFONGYR","created_at":"2026-07-04T23:59:25Z"},{"alias_kind":"pith_short_16","alias_value":"DNC4YBFONGYRJS53","created_at":"2026-07-04T23:59:25Z"},{"alias_kind":"pith_short_8","alias_value":"DNC4YBFO","created_at":"2026-07-04T23:59:25Z"}],"graph_snapshots":[{"event_id":"sha256:291dd599b978c15c504506df766b870745b8457d16cff6fb54348a3a50dd9211","target":"graph","created_at":"2026-07-04T23:59:25Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.08926/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of deep neural networks (DNNs) is attributable to three factors: increased compute capacity, more complex models, and more data. These factors, however, are not always present, especially for edge applications such as autonomous driving, augmented reality, and internet-of-things. Training DNNs requires a large amount of data, which is difficult to obtain. Edge devices such as mobile phones have limited compute capacity, and therefore, require specialized and efficient DNNs. However, due to the enormous design space and prohibitive training costs, designing efficient DNNs for differ","authors_text":"Bichen Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08926","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":"sha256:4e71409c5171ef9d1240e93103c7186efb1964d4cdf9a34cd760cf6fe075238e","target":"record","created_at":"2026-07-04T23:59:25Z","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":"9bdf4b84e99abe620d861abbf5ccea7b90dbf469cff144a966ca686773482a30","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-20T23:26:04Z","title_canon_sha256":"930180de636d073e948431b665decca247c469f0ff68537884f4ad47f3a2313b"},"schema_version":"1.0","source":{"id":"1908.08926","kind":"arxiv","version":1}},"canonical_sha256":"1b45cc04ae69b114cbbb3865a5f13fc5c39640816eb2c6bfa22cbab5b3bb821f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b45cc04ae69b114cbbb3865a5f13fc5c39640816eb2c6bfa22cbab5b3bb821f","first_computed_at":"2026-07-04T23:59:25.287048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:59:25.287048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C6DR5YohIKA55PMG1O0+IqQd1ZPQ6KDDMhXttvLQ0res7EDxN+KqScug260gUZq+XT3+zUze2Lyz2vdqoGyMDw==","signature_status":"signed_v1","signed_at":"2026-07-04T23:59:25.287431Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.08926","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e71409c5171ef9d1240e93103c7186efb1964d4cdf9a34cd760cf6fe075238e","sha256:291dd599b978c15c504506df766b870745b8457d16cff6fb54348a3a50dd9211"],"state_sha256":"445eed1452c1420428a0caecc64195dcf04b231070f243c8ee202feea0b72396"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"24Am46Qlqf3twgI9ns8wTE+ZMc49CNTuCy2DjV/k0zdIWy32ugrHQkCO8TKMLkzGC1EWLopL8p+txJgE/qHRDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:15:53.078751Z","bundle_sha256":"72b3e62f6f2a119a779890b227e4ff2fd91cf88dfa74e646d7147569ade2d149"}}