{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:IUKXACZLPCWPDFSO47J2L45EFA","short_pith_number":"pith:IUKXACZL","canonical_record":{"source":{"id":"1706.02332","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-07T18:40:26Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"7353f3ecb63dd7840077f75151f836824d55229e30a384bc3747abdfe8438caf","abstract_canon_sha256":"1c9faddabff99b8888e65d2cd187254767a206447182a6483735c32fa7d39b18"},"schema_version":"1.0"},"canonical_sha256":"4515700b2b78acf1964ee7d3a5f3a4281471a0837bd41ca9332b95265d1fddc1","source":{"kind":"arxiv","id":"1706.02332","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.02332","created_at":"2026-05-18T00:13:11Z"},{"alias_kind":"arxiv_version","alias_value":"1706.02332v3","created_at":"2026-05-18T00:13:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.02332","created_at":"2026-05-18T00:13:11Z"},{"alias_kind":"pith_short_12","alias_value":"IUKXACZLPCWP","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IUKXACZLPCWPDFSO","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IUKXACZL","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:IUKXACZLPCWPDFSO47J2L45EFA","target":"record","payload":{"canonical_record":{"source":{"id":"1706.02332","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-07T18:40:26Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"7353f3ecb63dd7840077f75151f836824d55229e30a384bc3747abdfe8438caf","abstract_canon_sha256":"1c9faddabff99b8888e65d2cd187254767a206447182a6483735c32fa7d39b18"},"schema_version":"1.0"},"canonical_sha256":"4515700b2b78acf1964ee7d3a5f3a4281471a0837bd41ca9332b95265d1fddc1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:11.164419Z","signature_b64":"dmeoVS7PrbpbQU3dnSYjGMYTFWRlmKpCZ2LcNlyISmgJBYbxzQhbPTjeOoiBUhdJKBnmvj0Lzpyyid/JGCpeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4515700b2b78acf1964ee7d3a5f3a4281471a0837bd41ca9332b95265d1fddc1","last_reissued_at":"2026-05-18T00:13:11.163599Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:11.163599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.02332","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ujdu97Wko1HWidsE0bLaW6ENHlr4zs7au2rIpSpnqS4tw4YkNGQtBRJn5ge9AkzHKg32H3iXP9zXk1IcF6oOCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T20:19:52.213612Z"},"content_sha256":"6ad674e25793830f091b4053223d7c1fb9705359f6c719deace132e31e6244d6","schema_version":"1.0","event_id":"sha256:6ad674e25793830f091b4053223d7c1fb9705359f6c719deace132e31e6244d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:IUKXACZLPCWPDFSO47J2L45EFA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Low-shot learning with large-scale diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Arthur Szlam, Bharath Hariharan, Herv\\'e J\\'egou, Matthijs Douze","submitted_at":"2017-06-07T18:40:26Z","abstract_excerpt":"This paper considers the problem of inferring image labels from images when only a few annotated examples are available at training time. This setup is often referred to as low-shot learning, where a standard approach is to re-train the last few layers of a convolutional neural network learned on separate classes for which training examples are abundant. We consider a semi-supervised setting based on a large collection of images to support label propagation. This is possible by leveraging the recent advances on large-scale similarity graph construction.\n  We show that despite its conceptual si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.02332","kind":"arxiv","version":3},"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":"2026-05-18T00:13:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gM2NxVOpQDllA9Pi+B3639o4FTG+nRe/tbaMKZTdm6vnlni6yiiVpSBQUG7AqRiomQvRJkSbGaG3+PV0DyrMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T20:19:52.214099Z"},"content_sha256":"66e65376ad378c1b71f1062c66df722bae178de2b4acfb431fe2ad5c0cf82142","schema_version":"1.0","event_id":"sha256:66e65376ad378c1b71f1062c66df722bae178de2b4acfb431fe2ad5c0cf82142"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IUKXACZLPCWPDFSO47J2L45EFA/bundle.json","state_url":"https://pith.science/pith/IUKXACZLPCWPDFSO47J2L45EFA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IUKXACZLPCWPDFSO47J2L45EFA/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":"2026-07-31T20:19:52Z","links":{"resolver":"https://pith.science/pith/IUKXACZLPCWPDFSO47J2L45EFA","bundle":"https://pith.science/pith/IUKXACZLPCWPDFSO47J2L45EFA/bundle.json","state":"https://pith.science/pith/IUKXACZLPCWPDFSO47J2L45EFA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IUKXACZLPCWPDFSO47J2L45EFA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:IUKXACZLPCWPDFSO47J2L45EFA","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":"1c9faddabff99b8888e65d2cd187254767a206447182a6483735c32fa7d39b18","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-07T18:40:26Z","title_canon_sha256":"7353f3ecb63dd7840077f75151f836824d55229e30a384bc3747abdfe8438caf"},"schema_version":"1.0","source":{"id":"1706.02332","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.02332","created_at":"2026-05-18T00:13:11Z"},{"alias_kind":"arxiv_version","alias_value":"1706.02332v3","created_at":"2026-05-18T00:13:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.02332","created_at":"2026-05-18T00:13:11Z"},{"alias_kind":"pith_short_12","alias_value":"IUKXACZLPCWP","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IUKXACZLPCWPDFSO","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IUKXACZL","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:66e65376ad378c1b71f1062c66df722bae178de2b4acfb431fe2ad5c0cf82142","target":"graph","created_at":"2026-05-18T00:13:11Z","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":"This paper considers the problem of inferring image labels from images when only a few annotated examples are available at training time. This setup is often referred to as low-shot learning, where a standard approach is to re-train the last few layers of a convolutional neural network learned on separate classes for which training examples are abundant. We consider a semi-supervised setting based on a large collection of images to support label propagation. This is possible by leveraging the recent advances on large-scale similarity graph construction.\n  We show that despite its conceptual si","authors_text":"Arthur Szlam, Bharath Hariharan, Herv\\'e J\\'egou, Matthijs Douze","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-07T18:40:26Z","title":"Low-shot learning with large-scale diffusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.02332","kind":"arxiv","version":3},"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":"sha256:6ad674e25793830f091b4053223d7c1fb9705359f6c719deace132e31e6244d6","target":"record","created_at":"2026-05-18T00:13:11Z","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":"1c9faddabff99b8888e65d2cd187254767a206447182a6483735c32fa7d39b18","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-07T18:40:26Z","title_canon_sha256":"7353f3ecb63dd7840077f75151f836824d55229e30a384bc3747abdfe8438caf"},"schema_version":"1.0","source":{"id":"1706.02332","kind":"arxiv","version":3}},"canonical_sha256":"4515700b2b78acf1964ee7d3a5f3a4281471a0837bd41ca9332b95265d1fddc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4515700b2b78acf1964ee7d3a5f3a4281471a0837bd41ca9332b95265d1fddc1","first_computed_at":"2026-05-18T00:13:11.163599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:11.163599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dmeoVS7PrbpbQU3dnSYjGMYTFWRlmKpCZ2LcNlyISmgJBYbxzQhbPTjeOoiBUhdJKBnmvj0Lzpyyid/JGCpeAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:11.164419Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.02332","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ad674e25793830f091b4053223d7c1fb9705359f6c719deace132e31e6244d6","sha256:66e65376ad378c1b71f1062c66df722bae178de2b4acfb431fe2ad5c0cf82142"],"state_sha256":"88c6a3279dfc89f6f0a3e1644154d049abcc8fa37319ecfeeb59bce1957746d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tY8sFiDCax0LUVYQGM5phiUnSfxGpD86FZxbcVrNqH/MGXSGokJNhhlVpDfp1lCcuwzP0xlANEaI0gJPiB80BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T20:19:52.220963Z","bundle_sha256":"a0aefefe37cf2525a77ae5a2688d0642655dd073050b62a46b1795e9dc0ee96c"}}