{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ACCEBVP6GHOOISPNJVB662R2UW","short_pith_number":"pith:ACCEBVP6","canonical_record":{"source":{"id":"1709.01353","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-05T12:39:30Z","cross_cats_sorted":[],"title_canon_sha256":"b8817780717f595055b8e0b5fbdfaa5a65d28d1f5860d3b5c1b92c8740ac2fa1","abstract_canon_sha256":"67dc471fe529547b7e1e10a64f8730e30abe7b6788ff0407d4c59f6871ea7094"},"schema_version":"1.0"},"canonical_sha256":"008440d5fe31dce449ed4d43ef6a3aa5abbbd899a325c706264443b1bf9f6ba3","source":{"kind":"arxiv","id":"1709.01353","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.01353","created_at":"2026-05-17T23:48:57Z"},{"alias_kind":"arxiv_version","alias_value":"1709.01353v2","created_at":"2026-05-17T23:48:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.01353","created_at":"2026-05-17T23:48:57Z"},{"alias_kind":"pith_short_12","alias_value":"ACCEBVP6GHOO","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"ACCEBVP6GHOOISPN","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"ACCEBVP6","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ACCEBVP6GHOOISPNJVB662R2UW","target":"record","payload":{"canonical_record":{"source":{"id":"1709.01353","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-05T12:39:30Z","cross_cats_sorted":[],"title_canon_sha256":"b8817780717f595055b8e0b5fbdfaa5a65d28d1f5860d3b5c1b92c8740ac2fa1","abstract_canon_sha256":"67dc471fe529547b7e1e10a64f8730e30abe7b6788ff0407d4c59f6871ea7094"},"schema_version":"1.0"},"canonical_sha256":"008440d5fe31dce449ed4d43ef6a3aa5abbbd899a325c706264443b1bf9f6ba3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:57.441038Z","signature_b64":"t1PILuRXRhqas0M53zcD5Z1QOnW1i9q6emHZszvmi2G0aPuh+Sfdbj8xqiyeBk6o8NzgklyVSSEeKdOiqTtfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"008440d5fe31dce449ed4d43ef6a3aa5abbbd899a325c706264443b1bf9f6ba3","last_reissued_at":"2026-05-17T23:48:57.440499Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:57.440499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.01353","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":"2026-05-17T23:48:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xb8UruErGMyiaQm1FvDBaiVMD3+WALPjHtmR5jewUhacViEH9sNvRRQuADQGCtJHgh+agrB1EM5MVFguRRUBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T20:32:31.509454Z"},"content_sha256":"eb01242e3c42b2061be456a6135e2fb5f9747353336cb85fd3302cfbe76983c8","schema_version":"1.0","event_id":"sha256:eb01242e3c42b2061be456a6135e2fb5f9747353336cb85fd3302cfbe76983c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ACCEBVP6GHOOISPNJVB662R2UW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Non-Metric Visual Similarity for Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"George Vogiatzis, Noa Garcia","submitted_at":"2017-09-05T12:39:30Z","abstract_excerpt":"Measuring visual similarity between two or more instances within a data distribution is a fundamental task in image retrieval. Theoretically, non-metric distances are able to generate a more complex and accurate similarity model than metric distances, provided that the non-linear data distribution is precisely captured by the system. In this work, we explore neural networks models for learning a non-metric similarity function for instance search. We argue that non-metric similarity functions based on neural networks can build a better model of human visual perception than standard metric dista"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.01353","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":"2026-05-17T23:48:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YBE++fvqlso0Ire3L710csmgnlLXf55RIYlj7nW5wPARuyy4tTLKW5l4tv3X3R9X/vv308yyWm/YIWHpogjGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T20:32:31.509807Z"},"content_sha256":"832aea0308782913e4fde7c92aaeeec421d592aed032e5562c7d75866f55e194","schema_version":"1.0","event_id":"sha256:832aea0308782913e4fde7c92aaeeec421d592aed032e5562c7d75866f55e194"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACCEBVP6GHOOISPNJVB662R2UW/bundle.json","state_url":"https://pith.science/pith/ACCEBVP6GHOOISPNJVB662R2UW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACCEBVP6GHOOISPNJVB662R2UW/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":"2026-06-24T20:32:31Z","links":{"resolver":"https://pith.science/pith/ACCEBVP6GHOOISPNJVB662R2UW","bundle":"https://pith.science/pith/ACCEBVP6GHOOISPNJVB662R2UW/bundle.json","state":"https://pith.science/pith/ACCEBVP6GHOOISPNJVB662R2UW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACCEBVP6GHOOISPNJVB662R2UW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ACCEBVP6GHOOISPNJVB662R2UW","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":"67dc471fe529547b7e1e10a64f8730e30abe7b6788ff0407d4c59f6871ea7094","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-05T12:39:30Z","title_canon_sha256":"b8817780717f595055b8e0b5fbdfaa5a65d28d1f5860d3b5c1b92c8740ac2fa1"},"schema_version":"1.0","source":{"id":"1709.01353","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.01353","created_at":"2026-05-17T23:48:57Z"},{"alias_kind":"arxiv_version","alias_value":"1709.01353v2","created_at":"2026-05-17T23:48:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.01353","created_at":"2026-05-17T23:48:57Z"},{"alias_kind":"pith_short_12","alias_value":"ACCEBVP6GHOO","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"ACCEBVP6GHOOISPN","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"ACCEBVP6","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:832aea0308782913e4fde7c92aaeeec421d592aed032e5562c7d75866f55e194","target":"graph","created_at":"2026-05-17T23:48:57Z","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":"Measuring visual similarity between two or more instances within a data distribution is a fundamental task in image retrieval. Theoretically, non-metric distances are able to generate a more complex and accurate similarity model than metric distances, provided that the non-linear data distribution is precisely captured by the system. In this work, we explore neural networks models for learning a non-metric similarity function for instance search. We argue that non-metric similarity functions based on neural networks can build a better model of human visual perception than standard metric dista","authors_text":"George Vogiatzis, Noa Garcia","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-05T12:39:30Z","title":"Learning Non-Metric Visual Similarity for Image Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.01353","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:eb01242e3c42b2061be456a6135e2fb5f9747353336cb85fd3302cfbe76983c8","target":"record","created_at":"2026-05-17T23:48:57Z","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":"67dc471fe529547b7e1e10a64f8730e30abe7b6788ff0407d4c59f6871ea7094","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-05T12:39:30Z","title_canon_sha256":"b8817780717f595055b8e0b5fbdfaa5a65d28d1f5860d3b5c1b92c8740ac2fa1"},"schema_version":"1.0","source":{"id":"1709.01353","kind":"arxiv","version":2}},"canonical_sha256":"008440d5fe31dce449ed4d43ef6a3aa5abbbd899a325c706264443b1bf9f6ba3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"008440d5fe31dce449ed4d43ef6a3aa5abbbd899a325c706264443b1bf9f6ba3","first_computed_at":"2026-05-17T23:48:57.440499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:57.440499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t1PILuRXRhqas0M53zcD5Z1QOnW1i9q6emHZszvmi2G0aPuh+Sfdbj8xqiyeBk6o8NzgklyVSSEeKdOiqTtfDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:57.441038Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.01353","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb01242e3c42b2061be456a6135e2fb5f9747353336cb85fd3302cfbe76983c8","sha256:832aea0308782913e4fde7c92aaeeec421d592aed032e5562c7d75866f55e194"],"state_sha256":"f77b4c97c8f0cfaad362010e4d7043b072dfdc59196b84cfb0f0ce518f1e91e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SGdFfmH7XcbITtVyohYo53s7oPZ8dq3ujPuNtahFADrx8FNkJfb/cNQgO5/gystu8DHBEboI+kGEz2JP4HliBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T20:32:31.511733Z","bundle_sha256":"b523702c074e4e8b3ab95bff5e40212f5efddb9d843f79b7f52d394e3ff2574c"}}