{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:VW7RI5QEZDKD26UN3SLFDTARQV","short_pith_number":"pith:VW7RI5QE","canonical_record":{"source":{"id":"1904.08502","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-09T20:20:38Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"8983985a87847467930596eb5448f77ad0784b06240603b342097065b043e1d8","abstract_canon_sha256":"c871a01b5524e306f9167a2884dbb5a76987cb63881469cd3399bfa55a35e594"},"schema_version":"1.0"},"canonical_sha256":"adbf147604c8d43d7a8ddc9651cc11856d9d95547eb4a9163f92e9c3842c2187","source":{"kind":"arxiv","id":"1904.08502","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.08502","created_at":"2026-05-17T23:41:42Z"},{"alias_kind":"arxiv_version","alias_value":"1904.08502v2","created_at":"2026-05-17T23:41:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08502","created_at":"2026-05-17T23:41:42Z"},{"alias_kind":"pith_short_12","alias_value":"VW7RI5QEZDKD","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"VW7RI5QEZDKD26UN","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"VW7RI5QE","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:VW7RI5QEZDKD26UN3SLFDTARQV","target":"record","payload":{"canonical_record":{"source":{"id":"1904.08502","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-09T20:20:38Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"8983985a87847467930596eb5448f77ad0784b06240603b342097065b043e1d8","abstract_canon_sha256":"c871a01b5524e306f9167a2884dbb5a76987cb63881469cd3399bfa55a35e594"},"schema_version":"1.0"},"canonical_sha256":"adbf147604c8d43d7a8ddc9651cc11856d9d95547eb4a9163f92e9c3842c2187","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:42.340693Z","signature_b64":"TIcrMbXnIHXRwwE4mFO3S6wbY2l9+j4ROwxZdYL0SbUxjV7weg3cfxbd0vPOMl4CD/ANelc7i+5T0+gt2TbwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adbf147604c8d43d7a8ddc9651cc11856d9d95547eb4a9163f92e9c3842c2187","last_reissued_at":"2026-05-17T23:41:42.340285Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:42.340285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.08502","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":"2026-05-17T23:41:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fYgAkaT181xdlZ+xTOwRX+OJ+BvE1e0heofFQGGx2ATSpK54WqoEh0YQ/aeKnA1NGKHDRKhtc729Y1GNpx4KBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T22:22:21.745608Z"},"content_sha256":"a0ca6f6f33e58a28aa8334f86f48941fef4258a191d097e2fa9f0e6e7086b4a5","schema_version":"1.0","event_id":"sha256:a0ca6f6f33e58a28aa8334f86f48941fef4258a191d097e2fa9f0e6e7086b4a5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:VW7RI5QEZDKD26UN3SLFDTARQV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Few-Shot Learning with Localization in Realistic Settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Davis Wertheimer","submitted_at":"2019-04-09T20:20:38Z","abstract_excerpt":"Traditional recognition methods typically require large, artificially-balanced training classes, while few-shot learning methods are tested on artificially small ones. In contrast to both extremes, real world recognition problems exhibit heavy-tailed class distributions, with cluttered scenes and a mix of coarse and fine-grained class distinctions. We show that prior methods designed for few-shot learning do not work out of the box in these challenging conditions, based on a new \"meta-iNat\" benchmark. We introduce three parameter-free improvements: (a) better training procedures based on adapt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08502","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":"2026-05-17T23:41:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ezh0eNBP6TH3/Nu2HnvnDgxDwIz6ESypt5ZgfTpAQQSjCSW0DBcV9Dchp7dD15+GLKGaLr1IOwauXbhMRBGRCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T22:22:21.745997Z"},"content_sha256":"17c6000a4207772bc6abbc10084d409fd44a0c470bfdd76ffe0b2f00396e24f8","schema_version":"1.0","event_id":"sha256:17c6000a4207772bc6abbc10084d409fd44a0c470bfdd76ffe0b2f00396e24f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VW7RI5QEZDKD26UN3SLFDTARQV/bundle.json","state_url":"https://pith.science/pith/VW7RI5QEZDKD26UN3SLFDTARQV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VW7RI5QEZDKD26UN3SLFDTARQV/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":"2026-06-01T22:22:21Z","links":{"resolver":"https://pith.science/pith/VW7RI5QEZDKD26UN3SLFDTARQV","bundle":"https://pith.science/pith/VW7RI5QEZDKD26UN3SLFDTARQV/bundle.json","state":"https://pith.science/pith/VW7RI5QEZDKD26UN3SLFDTARQV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VW7RI5QEZDKD26UN3SLFDTARQV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:VW7RI5QEZDKD26UN3SLFDTARQV","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":"c871a01b5524e306f9167a2884dbb5a76987cb63881469cd3399bfa55a35e594","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-09T20:20:38Z","title_canon_sha256":"8983985a87847467930596eb5448f77ad0784b06240603b342097065b043e1d8"},"schema_version":"1.0","source":{"id":"1904.08502","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.08502","created_at":"2026-05-17T23:41:42Z"},{"alias_kind":"arxiv_version","alias_value":"1904.08502v2","created_at":"2026-05-17T23:41:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08502","created_at":"2026-05-17T23:41:42Z"},{"alias_kind":"pith_short_12","alias_value":"VW7RI5QEZDKD","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"VW7RI5QEZDKD26UN","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"VW7RI5QE","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:17c6000a4207772bc6abbc10084d409fd44a0c470bfdd76ffe0b2f00396e24f8","target":"graph","created_at":"2026-05-17T23:41:42Z","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":"Traditional recognition methods typically require large, artificially-balanced training classes, while few-shot learning methods are tested on artificially small ones. In contrast to both extremes, real world recognition problems exhibit heavy-tailed class distributions, with cluttered scenes and a mix of coarse and fine-grained class distinctions. We show that prior methods designed for few-shot learning do not work out of the box in these challenging conditions, based on a new \"meta-iNat\" benchmark. We introduce three parameter-free improvements: (a) better training procedures based on adapt","authors_text":"Bharath Hariharan, Davis Wertheimer","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-09T20:20:38Z","title":"Few-Shot Learning with Localization in Realistic Settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08502","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:a0ca6f6f33e58a28aa8334f86f48941fef4258a191d097e2fa9f0e6e7086b4a5","target":"record","created_at":"2026-05-17T23:41:42Z","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":"c871a01b5524e306f9167a2884dbb5a76987cb63881469cd3399bfa55a35e594","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-09T20:20:38Z","title_canon_sha256":"8983985a87847467930596eb5448f77ad0784b06240603b342097065b043e1d8"},"schema_version":"1.0","source":{"id":"1904.08502","kind":"arxiv","version":2}},"canonical_sha256":"adbf147604c8d43d7a8ddc9651cc11856d9d95547eb4a9163f92e9c3842c2187","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"adbf147604c8d43d7a8ddc9651cc11856d9d95547eb4a9163f92e9c3842c2187","first_computed_at":"2026-05-17T23:41:42.340285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:42.340285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TIcrMbXnIHXRwwE4mFO3S6wbY2l9+j4ROwxZdYL0SbUxjV7weg3cfxbd0vPOMl4CD/ANelc7i+5T0+gt2TbwCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:42.340693Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.08502","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0ca6f6f33e58a28aa8334f86f48941fef4258a191d097e2fa9f0e6e7086b4a5","sha256:17c6000a4207772bc6abbc10084d409fd44a0c470bfdd76ffe0b2f00396e24f8"],"state_sha256":"4901b17bae0953db9d1efbba0087af5ad9c713885e141f0ee0311b3d3dd211be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/lzdeFGPfueupB3EtwRnNxMWzGC6eVoL+tO7OhnHXMG2hM+pFfWReVAT7B3le3fuhJ5T8lb1z9ifqyqBH+lLCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T22:22:21.749295Z","bundle_sha256":"6e1bbb5834fcf8ed24a3af83a2f1796b5a24251d236e546a55ba4f8ab5b37c6d"}}