{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NSIAOTDGZW5WSOBGX2RZWL66XA","short_pith_number":"pith:NSIAOTDG","canonical_record":{"source":{"id":"1903.00905","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-03T13:26:37Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"2a23f796d5677d03ee59caf0faedd139fadc530470c9bf7c3cb2583cef723883","abstract_canon_sha256":"3f1a3eaf9a07ecb2b2b513979e6f02e9b9b1b09091d1df0e448f52a42403e19e"},"schema_version":"1.0"},"canonical_sha256":"6c90074c66cdbb693826bea39b2fdeb816c294a73eddbb085792b1e65319139e","source":{"kind":"arxiv","id":"1903.00905","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.00905","created_at":"2026-05-17T23:51:18Z"},{"alias_kind":"arxiv_version","alias_value":"1903.00905v2","created_at":"2026-05-17T23:51:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00905","created_at":"2026-05-17T23:51:18Z"},{"alias_kind":"pith_short_12","alias_value":"NSIAOTDGZW5W","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NSIAOTDGZW5WSOBG","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NSIAOTDG","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NSIAOTDGZW5WSOBGX2RZWL66XA","target":"record","payload":{"canonical_record":{"source":{"id":"1903.00905","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-03T13:26:37Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"2a23f796d5677d03ee59caf0faedd139fadc530470c9bf7c3cb2583cef723883","abstract_canon_sha256":"3f1a3eaf9a07ecb2b2b513979e6f02e9b9b1b09091d1df0e448f52a42403e19e"},"schema_version":"1.0"},"canonical_sha256":"6c90074c66cdbb693826bea39b2fdeb816c294a73eddbb085792b1e65319139e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:18.995153Z","signature_b64":"1W8yUqzPgIDiIV8OsKss/o3cSztkjmsMP6ifPhu4B4Tm52yzFBUTE5VoBl+5ZHC416udO7bPDEPrOVjS8cAMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c90074c66cdbb693826bea39b2fdeb816c294a73eddbb085792b1e65319139e","last_reissued_at":"2026-05-17T23:51:18.994538Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:18.994538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.00905","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7gn3aAvDlYJt7+ENH6kLw4q9qfmfbP9nNeZq9Jj8kRnIgtw7p9mynxtXv4yh9Lv4zESN7UMQ3341VUJsZuEOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:54:39.439344Z"},"content_sha256":"14458dd1dd71272c56d5b4c890b6a795507c2c14fbacb215bbc34f782278f1bc","schema_version":"1.0","event_id":"sha256:14458dd1dd71272c56d5b4c890b6a795507c2c14fbacb215bbc34f782278f1bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NSIAOTDGZW5WSOBGX2RZWL66XA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MILDNet: A Lightweight Single Scaled Deep Ranking Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anirudha Vishvakarma","submitted_at":"2019-03-03T13:26:37Z","abstract_excerpt":"Multi-scale deep CNN architecture [1, 2, 3] successfully captures both fine and coarse level image descriptors for visual similarity task, but they come up with expensive memory overhead and latency. In this paper, we propose a competing novel CNN architecture, called MILDNet, which merits by being vastly compact (about 3 times). Inspired by the fact that successive CNN layers represent the image with increasing levels of abstraction, we compressed our deep ranking model to a single CNN by coupling activations from multiple intermediate layers along with the last layer. Trained on the famous S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00905","kind":"arxiv","version":2},"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":"2026-05-17T23:51:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c5koRnW0uOQuXRzP9R9a8Abx9qLE7vG0BNQys2M3uxf3E9eUqlXkIhFMwPNKhFdz3UcGy0efmger1xqUvT/PCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:54:39.439817Z"},"content_sha256":"33a94d1d8462f8c4592601479c3f537675fe5991aa6b5f1329399f25f83aeeca","schema_version":"1.0","event_id":"sha256:33a94d1d8462f8c4592601479c3f537675fe5991aa6b5f1329399f25f83aeeca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NSIAOTDGZW5WSOBGX2RZWL66XA/bundle.json","state_url":"https://pith.science/pith/NSIAOTDGZW5WSOBGX2RZWL66XA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NSIAOTDGZW5WSOBGX2RZWL66XA/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":"2026-08-03T15:54:39Z","links":{"resolver":"https://pith.science/pith/NSIAOTDGZW5WSOBGX2RZWL66XA","bundle":"https://pith.science/pith/NSIAOTDGZW5WSOBGX2RZWL66XA/bundle.json","state":"https://pith.science/pith/NSIAOTDGZW5WSOBGX2RZWL66XA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NSIAOTDGZW5WSOBGX2RZWL66XA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NSIAOTDGZW5WSOBGX2RZWL66XA","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":"3f1a3eaf9a07ecb2b2b513979e6f02e9b9b1b09091d1df0e448f52a42403e19e","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-03T13:26:37Z","title_canon_sha256":"2a23f796d5677d03ee59caf0faedd139fadc530470c9bf7c3cb2583cef723883"},"schema_version":"1.0","source":{"id":"1903.00905","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.00905","created_at":"2026-05-17T23:51:18Z"},{"alias_kind":"arxiv_version","alias_value":"1903.00905v2","created_at":"2026-05-17T23:51:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00905","created_at":"2026-05-17T23:51:18Z"},{"alias_kind":"pith_short_12","alias_value":"NSIAOTDGZW5W","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NSIAOTDGZW5WSOBG","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NSIAOTDG","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:33a94d1d8462f8c4592601479c3f537675fe5991aa6b5f1329399f25f83aeeca","target":"graph","created_at":"2026-05-17T23:51:18Z","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":"Multi-scale deep CNN architecture [1, 2, 3] successfully captures both fine and coarse level image descriptors for visual similarity task, but they come up with expensive memory overhead and latency. In this paper, we propose a competing novel CNN architecture, called MILDNet, which merits by being vastly compact (about 3 times). Inspired by the fact that successive CNN layers represent the image with increasing levels of abstraction, we compressed our deep ranking model to a single CNN by coupling activations from multiple intermediate layers along with the last layer. Trained on the famous S","authors_text":"Anirudha Vishvakarma","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-03T13:26:37Z","title":"MILDNet: A Lightweight Single Scaled Deep Ranking Architecture"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00905","kind":"arxiv","version":2},"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":"sha256:14458dd1dd71272c56d5b4c890b6a795507c2c14fbacb215bbc34f782278f1bc","target":"record","created_at":"2026-05-17T23:51:18Z","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":"3f1a3eaf9a07ecb2b2b513979e6f02e9b9b1b09091d1df0e448f52a42403e19e","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-03T13:26:37Z","title_canon_sha256":"2a23f796d5677d03ee59caf0faedd139fadc530470c9bf7c3cb2583cef723883"},"schema_version":"1.0","source":{"id":"1903.00905","kind":"arxiv","version":2}},"canonical_sha256":"6c90074c66cdbb693826bea39b2fdeb816c294a73eddbb085792b1e65319139e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c90074c66cdbb693826bea39b2fdeb816c294a73eddbb085792b1e65319139e","first_computed_at":"2026-05-17T23:51:18.994538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:18.994538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1W8yUqzPgIDiIV8OsKss/o3cSztkjmsMP6ifPhu4B4Tm52yzFBUTE5VoBl+5ZHC416udO7bPDEPrOVjS8cAMDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:18.995153Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.00905","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14458dd1dd71272c56d5b4c890b6a795507c2c14fbacb215bbc34f782278f1bc","sha256:33a94d1d8462f8c4592601479c3f537675fe5991aa6b5f1329399f25f83aeeca"],"state_sha256":"be9561fc316362cc54289d5fef8c56c498125166f1fa5d4e75f441fdd145751c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i8sKb5OWBcxWe6JWC7zTU6P0hmpcurpaw9WbbVMNhgE1preW1FXGEmLELvWa8cLLnjjTcZJTXA3rXYSEfHQPDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:54:39.443831Z","bundle_sha256":"fe6fd3a5b302f2e295cb133b3146306777764606ad78d8e0289e1824753ff404"}}