{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:E6ZJYCCY3YNFEZKRQST4M4NVEQ","short_pith_number":"pith:E6ZJYCCY","canonical_record":{"source":{"id":"2210.09922","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-18T15:06:47Z","cross_cats_sorted":[],"title_canon_sha256":"e111e6ef16b9a6d5e8564f5a16b02e062550e20b2cf6a4a70c0f9bd6b799be5e","abstract_canon_sha256":"6a5af1d7467a2d3d1cbfa9d16e868332f078f18adce6bf422389ca5f94934dc6"},"schema_version":"1.0"},"canonical_sha256":"27b29c0858de1a52655184a7c671b524333d285e58355fabc7ff73e812e09a47","source":{"kind":"arxiv","id":"2210.09922","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.09922","created_at":"2026-07-05T05:08:00Z"},{"alias_kind":"arxiv_version","alias_value":"2210.09922v1","created_at":"2026-07-05T05:08:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09922","created_at":"2026-07-05T05:08:00Z"},{"alias_kind":"pith_short_12","alias_value":"E6ZJYCCY3YNF","created_at":"2026-07-05T05:08:00Z"},{"alias_kind":"pith_short_16","alias_value":"E6ZJYCCY3YNFEZKR","created_at":"2026-07-05T05:08:00Z"},{"alias_kind":"pith_short_8","alias_value":"E6ZJYCCY","created_at":"2026-07-05T05:08:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:E6ZJYCCY3YNFEZKRQST4M4NVEQ","target":"record","payload":{"canonical_record":{"source":{"id":"2210.09922","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-18T15:06:47Z","cross_cats_sorted":[],"title_canon_sha256":"e111e6ef16b9a6d5e8564f5a16b02e062550e20b2cf6a4a70c0f9bd6b799be5e","abstract_canon_sha256":"6a5af1d7467a2d3d1cbfa9d16e868332f078f18adce6bf422389ca5f94934dc6"},"schema_version":"1.0"},"canonical_sha256":"27b29c0858de1a52655184a7c671b524333d285e58355fabc7ff73e812e09a47","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:00.877774Z","signature_b64":"zBRf3H1s35qLnY/z5mFQKzGyYwtoMlQ7DxrNfkwzt26VtxGVCKh+BVq1ASXENkLDUad3d7n/v45BZcFUFScbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27b29c0858de1a52655184a7c671b524333d285e58355fabc7ff73e812e09a47","last_reissued_at":"2026-07-05T05:08:00.877353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:00.877353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.09922","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":"2026-07-05T05:08:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C2MEbG0rr1hoHavnOSoQ4k7LzIHFEycm56zb2ZZHDu1COOw3WmzxEtHXkKIxeWdrHLxy/ITyQJq0nldildSvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:26:18.094420Z"},"content_sha256":"2d372ca6121f8dba19d70f42a0940c45b261beaa4f21e22a75ddd862bd50ec4b","schema_version":"1.0","event_id":"sha256:2d372ca6121f8dba19d70f42a0940c45b261beaa4f21e22a75ddd862bd50ec4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:E6ZJYCCY3YNFEZKRQST4M4NVEQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Few-Shot Learning of Compact Models via Task-Specific Meta Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mehrdad Hosseinzadeh, Shekhor Chanda, Yang Wang, Yong Wu, Zhi Liu","submitted_at":"2022-10-18T15:06:47Z","abstract_excerpt":"We consider a new problem of few-shot learning of compact models. Meta-learning is a popular approach for few-shot learning. Previous work in meta-learning typically assumes that the model architecture during meta-training is the same as the model architecture used for final deployment. In this paper, we challenge this basic assumption. For final deployment, we often need the model to be small. But small models usually do not have enough capacity to effectively adapt to new tasks. In the mean time, we often have access to the large dataset and extensive computing power during meta-training sin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09922","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/2210.09922/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":"2026-07-05T05:08:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Et96X7meOeMfYzxgWje3+PaBspJamTh6iK6tCIFTo1b+efPwhhbRRSdzpg+A3jR5d7160Q+bGYabeyR7neYBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:26:18.094799Z"},"content_sha256":"e527a4c974cd5f680496596b17860b3b4ceb83d164af1148b42007179758275e","schema_version":"1.0","event_id":"sha256:e527a4c974cd5f680496596b17860b3b4ceb83d164af1148b42007179758275e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E6ZJYCCY3YNFEZKRQST4M4NVEQ/bundle.json","state_url":"https://pith.science/pith/E6ZJYCCY3YNFEZKRQST4M4NVEQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E6ZJYCCY3YNFEZKRQST4M4NVEQ/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":"2026-07-07T12:26:18Z","links":{"resolver":"https://pith.science/pith/E6ZJYCCY3YNFEZKRQST4M4NVEQ","bundle":"https://pith.science/pith/E6ZJYCCY3YNFEZKRQST4M4NVEQ/bundle.json","state":"https://pith.science/pith/E6ZJYCCY3YNFEZKRQST4M4NVEQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E6ZJYCCY3YNFEZKRQST4M4NVEQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:E6ZJYCCY3YNFEZKRQST4M4NVEQ","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":"6a5af1d7467a2d3d1cbfa9d16e868332f078f18adce6bf422389ca5f94934dc6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-18T15:06:47Z","title_canon_sha256":"e111e6ef16b9a6d5e8564f5a16b02e062550e20b2cf6a4a70c0f9bd6b799be5e"},"schema_version":"1.0","source":{"id":"2210.09922","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.09922","created_at":"2026-07-05T05:08:00Z"},{"alias_kind":"arxiv_version","alias_value":"2210.09922v1","created_at":"2026-07-05T05:08:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09922","created_at":"2026-07-05T05:08:00Z"},{"alias_kind":"pith_short_12","alias_value":"E6ZJYCCY3YNF","created_at":"2026-07-05T05:08:00Z"},{"alias_kind":"pith_short_16","alias_value":"E6ZJYCCY3YNFEZKR","created_at":"2026-07-05T05:08:00Z"},{"alias_kind":"pith_short_8","alias_value":"E6ZJYCCY","created_at":"2026-07-05T05:08:00Z"}],"graph_snapshots":[{"event_id":"sha256:e527a4c974cd5f680496596b17860b3b4ceb83d164af1148b42007179758275e","target":"graph","created_at":"2026-07-05T05:08:00Z","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/2210.09922/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider a new problem of few-shot learning of compact models. Meta-learning is a popular approach for few-shot learning. Previous work in meta-learning typically assumes that the model architecture during meta-training is the same as the model architecture used for final deployment. In this paper, we challenge this basic assumption. For final deployment, we often need the model to be small. But small models usually do not have enough capacity to effectively adapt to new tasks. In the mean time, we often have access to the large dataset and extensive computing power during meta-training sin","authors_text":"Mehrdad Hosseinzadeh, Shekhor Chanda, Yang Wang, Yong Wu, Zhi Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-18T15:06:47Z","title":"Few-Shot Learning of Compact Models via Task-Specific Meta Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09922","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":"sha256:2d372ca6121f8dba19d70f42a0940c45b261beaa4f21e22a75ddd862bd50ec4b","target":"record","created_at":"2026-07-05T05:08:00Z","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":"6a5af1d7467a2d3d1cbfa9d16e868332f078f18adce6bf422389ca5f94934dc6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-18T15:06:47Z","title_canon_sha256":"e111e6ef16b9a6d5e8564f5a16b02e062550e20b2cf6a4a70c0f9bd6b799be5e"},"schema_version":"1.0","source":{"id":"2210.09922","kind":"arxiv","version":1}},"canonical_sha256":"27b29c0858de1a52655184a7c671b524333d285e58355fabc7ff73e812e09a47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27b29c0858de1a52655184a7c671b524333d285e58355fabc7ff73e812e09a47","first_computed_at":"2026-07-05T05:08:00.877353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:00.877353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zBRf3H1s35qLnY/z5mFQKzGyYwtoMlQ7DxrNfkwzt26VtxGVCKh+BVq1ASXENkLDUad3d7n/v45BZcFUFScbAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:00.877774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.09922","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d372ca6121f8dba19d70f42a0940c45b261beaa4f21e22a75ddd862bd50ec4b","sha256:e527a4c974cd5f680496596b17860b3b4ceb83d164af1148b42007179758275e"],"state_sha256":"eb388bfd66f9209c168554ec03a5b98dd07d5e4828a7bc0d7b2f144cec12725d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cIUvfmtIaQr5AQGONhcnwnzHY3XPf+ZcyBYct6gWomUEQHZtymLBlJahswpdoCy2MouDOQ8iYzq6nP5H+ylbDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:26:18.096839Z","bundle_sha256":"3a165094a8b99ba88479bed93194e1ed939814d16220532522d61692859ca45d"}}