{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FGPV2PUMSQKXEPLU5SBZI5BH5S","short_pith_number":"pith:FGPV2PUM","canonical_record":{"source":{"id":"2501.14593","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T15:56:55Z","cross_cats_sorted":[],"title_canon_sha256":"ab5502c492ec65441fca0a4bf7249b80465a346ed648901c7b998ebee0f9fc38","abstract_canon_sha256":"0ae4463efe5f81210ccb0fc902f807646c93a0d32a1384490ccded6230c8eeda"},"schema_version":"1.0"},"canonical_sha256":"299f5d3e8c9415723d74ec83947427ecb625235d337bb0b0562c283dac8c1aa3","source":{"kind":"arxiv","id":"2501.14593","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14593","created_at":"2026-07-05T10:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14593v1","created_at":"2026-07-05T10:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14593","created_at":"2026-07-05T10:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"FGPV2PUMSQKX","created_at":"2026-07-05T10:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"FGPV2PUMSQKXEPLU","created_at":"2026-07-05T10:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"FGPV2PUM","created_at":"2026-07-05T10:05:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FGPV2PUMSQKXEPLU5SBZI5BH5S","target":"record","payload":{"canonical_record":{"source":{"id":"2501.14593","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T15:56:55Z","cross_cats_sorted":[],"title_canon_sha256":"ab5502c492ec65441fca0a4bf7249b80465a346ed648901c7b998ebee0f9fc38","abstract_canon_sha256":"0ae4463efe5f81210ccb0fc902f807646c93a0d32a1384490ccded6230c8eeda"},"schema_version":"1.0"},"canonical_sha256":"299f5d3e8c9415723d74ec83947427ecb625235d337bb0b0562c283dac8c1aa3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:03.061116Z","signature_b64":"25h6vhyyU8Ze73V30p2WufLp7H1F5ba8/RNI96ndS8zfCBV36aARARFalc3ssftVFGESTTh5tydj0ISV7io1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"299f5d3e8c9415723d74ec83947427ecb625235d337bb0b0562c283dac8c1aa3","last_reissued_at":"2026-07-05T10:05:03.060784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:03.060784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.14593","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"559boYhL1wuFYT9YnFBGelnou/teSYT3PGfSmYJ9n/n2tGPWF9X5g6ZFcGrtgXjV0HttUI116loP0WKOyabJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T15:48:53.481535Z"},"content_sha256":"99565f0d508d76db55c1a7571d66606a9ff14dfc996f72fafef31d24c2810d17","schema_version":"1.0","event_id":"sha256:99565f0d508d76db55c1a7571d66606a9ff14dfc996f72fafef31d24c2810d17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FGPV2PUMSQKXEPLU5SBZI5BH5S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Geometric Mean Improves Loss For Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Takumi Kobayashi, Tong Wu","submitted_at":"2025-01-24T15:56:55Z","abstract_excerpt":"Few-shot learning (FSL) is a challenging task in machine learning, demanding a model to render discriminative classification by using only a few labeled samples. In the literature of FSL, deep models are trained in a manner of metric learning to provide metric in a feature space which is well generalizable to classify samples of novel classes; in the space, even a few amount of labeled training examples can construct an effective classifier. In this paper, we propose a novel FSL loss based on \\emph{geometric mean} to embed discriminative metric into deep features. In contrast to the other loss"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14593","kind":"arxiv","version":1},"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/2501.14593/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":"2026-07-05T10:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eVBWvqPc/mQq2rZ+nvwC8nnO48Q8OEPQ91HTfQu6RdnivSi1KoAFm4dQImvtJ5CGKJGibZrqV/bNDbQHECz6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T15:48:53.482077Z"},"content_sha256":"12ad996e6bd1ca49b2bae40b44b36f2fdfa943ef1e708fc78c1d5a86a5f2eb95","schema_version":"1.0","event_id":"sha256:12ad996e6bd1ca49b2bae40b44b36f2fdfa943ef1e708fc78c1d5a86a5f2eb95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FGPV2PUMSQKXEPLU5SBZI5BH5S/bundle.json","state_url":"https://pith.science/pith/FGPV2PUMSQKXEPLU5SBZI5BH5S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FGPV2PUMSQKXEPLU5SBZI5BH5S/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":"2026-08-15T15:48:53Z","links":{"resolver":"https://pith.science/pith/FGPV2PUMSQKXEPLU5SBZI5BH5S","bundle":"https://pith.science/pith/FGPV2PUMSQKXEPLU5SBZI5BH5S/bundle.json","state":"https://pith.science/pith/FGPV2PUMSQKXEPLU5SBZI5BH5S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FGPV2PUMSQKXEPLU5SBZI5BH5S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FGPV2PUMSQKXEPLU5SBZI5BH5S","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":"0ae4463efe5f81210ccb0fc902f807646c93a0d32a1384490ccded6230c8eeda","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T15:56:55Z","title_canon_sha256":"ab5502c492ec65441fca0a4bf7249b80465a346ed648901c7b998ebee0f9fc38"},"schema_version":"1.0","source":{"id":"2501.14593","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14593","created_at":"2026-07-05T10:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14593v1","created_at":"2026-07-05T10:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14593","created_at":"2026-07-05T10:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"FGPV2PUMSQKX","created_at":"2026-07-05T10:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"FGPV2PUMSQKXEPLU","created_at":"2026-07-05T10:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"FGPV2PUM","created_at":"2026-07-05T10:05:03Z"}],"graph_snapshots":[{"event_id":"sha256:12ad996e6bd1ca49b2bae40b44b36f2fdfa943ef1e708fc78c1d5a86a5f2eb95","target":"graph","created_at":"2026-07-05T10:05:03Z","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/2501.14593/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Few-shot learning (FSL) is a challenging task in machine learning, demanding a model to render discriminative classification by using only a few labeled samples. In the literature of FSL, deep models are trained in a manner of metric learning to provide metric in a feature space which is well generalizable to classify samples of novel classes; in the space, even a few amount of labeled training examples can construct an effective classifier. In this paper, we propose a novel FSL loss based on \\emph{geometric mean} to embed discriminative metric into deep features. In contrast to the other loss","authors_text":"Takumi Kobayashi, Tong Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T15:56:55Z","title":"Geometric Mean Improves Loss For Few-Shot Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14593","kind":"arxiv","version":1},"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":"sha256:99565f0d508d76db55c1a7571d66606a9ff14dfc996f72fafef31d24c2810d17","target":"record","created_at":"2026-07-05T10:05:03Z","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":"0ae4463efe5f81210ccb0fc902f807646c93a0d32a1384490ccded6230c8eeda","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T15:56:55Z","title_canon_sha256":"ab5502c492ec65441fca0a4bf7249b80465a346ed648901c7b998ebee0f9fc38"},"schema_version":"1.0","source":{"id":"2501.14593","kind":"arxiv","version":1}},"canonical_sha256":"299f5d3e8c9415723d74ec83947427ecb625235d337bb0b0562c283dac8c1aa3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"299f5d3e8c9415723d74ec83947427ecb625235d337bb0b0562c283dac8c1aa3","first_computed_at":"2026-07-05T10:05:03.060784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:03.060784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"25h6vhyyU8Ze73V30p2WufLp7H1F5ba8/RNI96ndS8zfCBV36aARARFalc3ssftVFGESTTh5tydj0ISV7io1AA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:03.061116Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14593","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99565f0d508d76db55c1a7571d66606a9ff14dfc996f72fafef31d24c2810d17","sha256:12ad996e6bd1ca49b2bae40b44b36f2fdfa943ef1e708fc78c1d5a86a5f2eb95"],"state_sha256":"61a4148a79d199b255c8a5c436fd1f35853d2550cc440d86fc0ba22d1e0036a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9zf0w4UDseGB0f6DkIU9p+AITr1zoCuh7e0ZVjP1Sppwcpv6+P5rdTJmfbeln5/PhnNQAM4gDhu5z5u/5zaLBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T15:48:53.485940Z","bundle_sha256":"a9d578bbebecee96bf3ead9e5daa4cd07434e9e7226c888686d032b23d1a663c"}}