{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:G74GQGQTM4XXSCTTVYMJTTH73Q","short_pith_number":"pith:G74GQGQT","canonical_record":{"source":{"id":"2307.15317","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-28T05:32:56Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"a9abb61eac9897ec9039a491808bb5db1c648241e97b9c66cdaa60a872cfcdb8","abstract_canon_sha256":"29993dccfa8b7b70cf6d983c72b772141a350b440d10b78623cbe056398ae87a"},"schema_version":"1.0"},"canonical_sha256":"37f8681a13672f790a73ae1899ccffdc3d35bf281c4fc9deb63a1d01302e32f7","source":{"kind":"arxiv","id":"2307.15317","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15317","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15317v2","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15317","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"G74GQGQTM4XX","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"pith_short_16","alias_value":"G74GQGQTM4XXSCTT","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"pith_short_8","alias_value":"G74GQGQT","created_at":"2026-07-05T07:04:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:G74GQGQTM4XXSCTTVYMJTTH73Q","target":"record","payload":{"canonical_record":{"source":{"id":"2307.15317","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-28T05:32:56Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"a9abb61eac9897ec9039a491808bb5db1c648241e97b9c66cdaa60a872cfcdb8","abstract_canon_sha256":"29993dccfa8b7b70cf6d983c72b772141a350b440d10b78623cbe056398ae87a"},"schema_version":"1.0"},"canonical_sha256":"37f8681a13672f790a73ae1899ccffdc3d35bf281c4fc9deb63a1d01302e32f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:18.443260Z","signature_b64":"WyfBqLDbceo5uwGS9f15waEybb7f1KqYg0irVoMt+mI455+OLhVN5RXwlC9vIhXXB+MXKB1NpKwsPeQUKVezDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37f8681a13672f790a73ae1899ccffdc3d35bf281c4fc9deb63a1d01302e32f7","last_reissued_at":"2026-07-05T07:04:18.442753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:18.442753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.15317","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":"2026-07-05T07:04:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tpeC1eHycs6M/A7q6/Zh0Mz0ZbxyC6iBPfrF/mW1Hg6jwEQsgibCUlSY2HQ3vl/eyilCC/bZ/loxbnC0pdFVAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:37:38.355752Z"},"content_sha256":"0b013ad51acb3a53327dbdf3cfe2073248457f948525bdb2d7e142930ac31838","schema_version":"1.0","event_id":"sha256:0b013ad51acb3a53327dbdf3cfe2073248457f948525bdb2d7e142930ac31838"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:G74GQGQTM4XXSCTTVYMJTTH73Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Huishuai Zhang, Kaipeng Zheng, Weiran Huang","submitted_at":"2023-07-28T05:32:56Z","abstract_excerpt":"Few-shot learning aims to adapt models trained on the base dataset to novel tasks where the categories were not seen by the model before. This often leads to a relatively uniform distribution of feature values across channels on novel classes, posing challenges in determining channel importance for novel tasks. Standard few-shot learning methods employ geometric similarity metrics such as cosine similarity and negative Euclidean distance to gauge the semantic relatedness between two features. However, features with high geometric similarities may carry distinct semantics, especially in the con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15317","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.15317/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":"2026-07-05T07:04:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/KbIN5OlR58u/ghqbCCIbpC3F8Ic9+XRQvOo5Pwunk6VPfXISr6ra3KkY4gJe/lUZIJP6MCfJtAjJcymuVt9Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:37:38.356696Z"},"content_sha256":"87cd083b77e44ee6d42decec95533ccd91dbdf60299bddad00842103f5657b48","schema_version":"1.0","event_id":"sha256:87cd083b77e44ee6d42decec95533ccd91dbdf60299bddad00842103f5657b48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G74GQGQTM4XXSCTTVYMJTTH73Q/bundle.json","state_url":"https://pith.science/pith/G74GQGQTM4XXSCTTVYMJTTH73Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G74GQGQTM4XXSCTTVYMJTTH73Q/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":"2026-08-05T16:37:38Z","links":{"resolver":"https://pith.science/pith/G74GQGQTM4XXSCTTVYMJTTH73Q","bundle":"https://pith.science/pith/G74GQGQTM4XXSCTTVYMJTTH73Q/bundle.json","state":"https://pith.science/pith/G74GQGQTM4XXSCTTVYMJTTH73Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G74GQGQTM4XXSCTTVYMJTTH73Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:G74GQGQTM4XXSCTTVYMJTTH73Q","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":"29993dccfa8b7b70cf6d983c72b772141a350b440d10b78623cbe056398ae87a","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-28T05:32:56Z","title_canon_sha256":"a9abb61eac9897ec9039a491808bb5db1c648241e97b9c66cdaa60a872cfcdb8"},"schema_version":"1.0","source":{"id":"2307.15317","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15317","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15317v2","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15317","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"G74GQGQTM4XX","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"pith_short_16","alias_value":"G74GQGQTM4XXSCTT","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"pith_short_8","alias_value":"G74GQGQT","created_at":"2026-07-05T07:04:18Z"}],"graph_snapshots":[{"event_id":"sha256:87cd083b77e44ee6d42decec95533ccd91dbdf60299bddad00842103f5657b48","target":"graph","created_at":"2026-07-05T07:04:18Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2307.15317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Few-shot learning aims to adapt models trained on the base dataset to novel tasks where the categories were not seen by the model before. This often leads to a relatively uniform distribution of feature values across channels on novel classes, posing challenges in determining channel importance for novel tasks. Standard few-shot learning methods employ geometric similarity metrics such as cosine similarity and negative Euclidean distance to gauge the semantic relatedness between two features. However, features with high geometric similarities may carry distinct semantics, especially in the con","authors_text":"Huishuai Zhang, Kaipeng Zheng, Weiran Huang","cross_cats":["cs.AI","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-28T05:32:56Z","title":"DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15317","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":"sha256:0b013ad51acb3a53327dbdf3cfe2073248457f948525bdb2d7e142930ac31838","target":"record","created_at":"2026-07-05T07:04:18Z","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":"29993dccfa8b7b70cf6d983c72b772141a350b440d10b78623cbe056398ae87a","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-28T05:32:56Z","title_canon_sha256":"a9abb61eac9897ec9039a491808bb5db1c648241e97b9c66cdaa60a872cfcdb8"},"schema_version":"1.0","source":{"id":"2307.15317","kind":"arxiv","version":2}},"canonical_sha256":"37f8681a13672f790a73ae1899ccffdc3d35bf281c4fc9deb63a1d01302e32f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37f8681a13672f790a73ae1899ccffdc3d35bf281c4fc9deb63a1d01302e32f7","first_computed_at":"2026-07-05T07:04:18.442753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:18.442753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WyfBqLDbceo5uwGS9f15waEybb7f1KqYg0irVoMt+mI455+OLhVN5RXwlC9vIhXXB+MXKB1NpKwsPeQUKVezDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:18.443260Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.15317","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b013ad51acb3a53327dbdf3cfe2073248457f948525bdb2d7e142930ac31838","sha256:87cd083b77e44ee6d42decec95533ccd91dbdf60299bddad00842103f5657b48"],"state_sha256":"9585f8d481a40b23a80a3319ac24d63a9a4dd86fbbca35c64296d5d2f1545cfa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FM3mYZZY4DojI/e/21zET61f/XjMVSsJGX/sxFYWGo/4YPfyXOBPDaMS2N5R9lM65TocdkVGkhJSEMufkSLDAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T16:37:38.362580Z","bundle_sha256":"703e0273e1d43ee1a05e66db87901bed3190b207448c558681b7fe138eb08543"}}