{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UPQDV2VNSRQK2ANCXGRMXWNBIH","short_pith_number":"pith:UPQDV2VN","canonical_record":{"source":{"id":"1905.04042","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-10T09:57:23Z","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"a268fd57515997adce209cff0f4f4216c242bd149e64bcd4b932000b03b77425","abstract_canon_sha256":"0cd2a96dab8096f111c071bc8a1ef4f975f3fa823a95881cd69c6fd8824fd5b2"},"schema_version":"1.0"},"canonical_sha256":"a3e03aeaad9460ad01a2b9a2cbd9a141c2b13bdd542709280e631074a35f9393","source":{"kind":"arxiv","id":"1905.04042","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.04042","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"arxiv_version","alias_value":"1905.04042v2","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.04042","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"pith_short_12","alias_value":"UPQDV2VNSRQK","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UPQDV2VNSRQK2ANC","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UPQDV2VN","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UPQDV2VNSRQK2ANCXGRMXWNBIH","target":"record","payload":{"canonical_record":{"source":{"id":"1905.04042","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-10T09:57:23Z","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"a268fd57515997adce209cff0f4f4216c242bd149e64bcd4b932000b03b77425","abstract_canon_sha256":"0cd2a96dab8096f111c071bc8a1ef4f975f3fa823a95881cd69c6fd8824fd5b2"},"schema_version":"1.0"},"canonical_sha256":"a3e03aeaad9460ad01a2b9a2cbd9a141c2b13bdd542709280e631074a35f9393","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:28.582447Z","signature_b64":"S6SEZJMV4UoxB8UZ0E/oA58BZWDEFUuwF682vuhqHRENw2uxfejdZ/ciY/mQ3KW1+tGaNvLBtZcEZyDshrl0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3e03aeaad9460ad01a2b9a2cbd9a141c2b13bdd542709280e631074a35f9393","last_reissued_at":"2026-05-17T23:44:28.581878Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:28.581878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.04042","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":"2026-05-17T23:44:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"taXSjemMaVxgaZqtM9HITNzyh5Z7mdj6q02wCMUk7McIYKCQXZDbpFgOceRYT3zUWONHavkKkUyNpqJkfA2gCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:39:54.569026Z"},"content_sha256":"bad9d7f3463e3021633c20c9d70a9970e48e35d6fbf2f6246d94beb8790d7e51","schema_version":"1.0","event_id":"sha256:bad9d7f3463e3021633c20c9d70a9970e48e35d6fbf2f6246d94beb8790d7e51"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UPQDV2VNSRQK2ANCXGRMXWNBIH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chengqi Zhang, Guodong Long, Jing Jiang, Lina Yao, Lu Liu, Tianyi Zhou","submitted_at":"2019-05-10T09:57:23Z","abstract_excerpt":"A variety of machine learning applications expect to achieve rapid learning from a limited number of labeled data. However, the success of most current models is the result of heavy training on big data. Meta-learning addresses this problem by extracting common knowledge across different tasks that can be quickly adapted to new tasks. However, they do not fully explore weakly-supervised information, which is usually free or cheap to collect. In this paper, we show that weakly-labeled data can significantly improve the performance of meta-learning on few-shot classification. We propose prototyp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.04042","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":"2026-05-17T23:44:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6HVpWAljvvqPd/54GSzvQhz+mHM+m7RDK6pb2oL0UC1xrqMvAXQBFZbjmOnWRPcxLnNwc432UqOBmPgYUEYHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:39:54.569806Z"},"content_sha256":"c2309d46ba4450d1c2251cbe24812b2a87fa117341298dfe4eb69d82402e773e","schema_version":"1.0","event_id":"sha256:c2309d46ba4450d1c2251cbe24812b2a87fa117341298dfe4eb69d82402e773e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UPQDV2VNSRQK2ANCXGRMXWNBIH/bundle.json","state_url":"https://pith.science/pith/UPQDV2VNSRQK2ANCXGRMXWNBIH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UPQDV2VNSRQK2ANCXGRMXWNBIH/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":"2026-05-27T22:39:54Z","links":{"resolver":"https://pith.science/pith/UPQDV2VNSRQK2ANCXGRMXWNBIH","bundle":"https://pith.science/pith/UPQDV2VNSRQK2ANCXGRMXWNBIH/bundle.json","state":"https://pith.science/pith/UPQDV2VNSRQK2ANCXGRMXWNBIH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UPQDV2VNSRQK2ANCXGRMXWNBIH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UPQDV2VNSRQK2ANCXGRMXWNBIH","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":"0cd2a96dab8096f111c071bc8a1ef4f975f3fa823a95881cd69c6fd8824fd5b2","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-10T09:57:23Z","title_canon_sha256":"a268fd57515997adce209cff0f4f4216c242bd149e64bcd4b932000b03b77425"},"schema_version":"1.0","source":{"id":"1905.04042","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.04042","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"arxiv_version","alias_value":"1905.04042v2","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.04042","created_at":"2026-05-17T23:44:28Z"},{"alias_kind":"pith_short_12","alias_value":"UPQDV2VNSRQK","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UPQDV2VNSRQK2ANC","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UPQDV2VN","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:c2309d46ba4450d1c2251cbe24812b2a87fa117341298dfe4eb69d82402e773e","target":"graph","created_at":"2026-05-17T23:44:28Z","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":"A variety of machine learning applications expect to achieve rapid learning from a limited number of labeled data. However, the success of most current models is the result of heavy training on big data. Meta-learning addresses this problem by extracting common knowledge across different tasks that can be quickly adapted to new tasks. However, they do not fully explore weakly-supervised information, which is usually free or cheap to collect. In this paper, we show that weakly-labeled data can significantly improve the performance of meta-learning on few-shot classification. We propose prototyp","authors_text":"Chengqi Zhang, Guodong Long, Jing Jiang, Lina Yao, Lu Liu, Tianyi Zhou","cross_cats":["cs.CV","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-10T09:57:23Z","title":"Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.04042","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:bad9d7f3463e3021633c20c9d70a9970e48e35d6fbf2f6246d94beb8790d7e51","target":"record","created_at":"2026-05-17T23:44:28Z","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":"0cd2a96dab8096f111c071bc8a1ef4f975f3fa823a95881cd69c6fd8824fd5b2","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-10T09:57:23Z","title_canon_sha256":"a268fd57515997adce209cff0f4f4216c242bd149e64bcd4b932000b03b77425"},"schema_version":"1.0","source":{"id":"1905.04042","kind":"arxiv","version":2}},"canonical_sha256":"a3e03aeaad9460ad01a2b9a2cbd9a141c2b13bdd542709280e631074a35f9393","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3e03aeaad9460ad01a2b9a2cbd9a141c2b13bdd542709280e631074a35f9393","first_computed_at":"2026-05-17T23:44:28.581878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:28.581878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S6SEZJMV4UoxB8UZ0E/oA58BZWDEFUuwF682vuhqHRENw2uxfejdZ/ciY/mQ3KW1+tGaNvLBtZcEZyDshrl0Dw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:28.582447Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.04042","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bad9d7f3463e3021633c20c9d70a9970e48e35d6fbf2f6246d94beb8790d7e51","sha256:c2309d46ba4450d1c2251cbe24812b2a87fa117341298dfe4eb69d82402e773e"],"state_sha256":"dd813ac12c18c3cf001a7b3b28ae77a8e5ef04888bb679f808fb600ea6a8f9fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nKlQefDdbeAXTFfnskne9uyrwiKb1s0BVF7Mp8yWq8mYQCPcdMj+g5tQR08JQ6FqWGILHYd9c/DHE5Xn7mM1AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T22:39:54.572682Z","bundle_sha256":"ed01790787267c377c8cd358cf6f8e724c49dc6b1a5bd8338d6d401a22d41607"}}