{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:J3DBLRFOFO7QU5R7XM2SNJSDSD","short_pith_number":"pith:J3DBLRFO","canonical_record":{"source":{"id":"2002.08799","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T15:24:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cd609910327ad57e6a19c6851d09a935d53eb5f9949293fab8ee702611cfa778","abstract_canon_sha256":"01206f67a17fd5d37a8f81fee519563602cbe944a8be645278a5bfd02662dc66"},"schema_version":"1.0"},"canonical_sha256":"4ec615c4ae2bbf0a763fbb3526a64390c6bd4c81342393bb8e9ffa44157474e6","source":{"kind":"arxiv","id":"2002.08799","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.08799","created_at":"2026-07-05T01:43:55Z"},{"alias_kind":"arxiv_version","alias_value":"2002.08799v2","created_at":"2026-07-05T01:43:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.08799","created_at":"2026-07-05T01:43:55Z"},{"alias_kind":"pith_short_12","alias_value":"J3DBLRFOFO7Q","created_at":"2026-07-05T01:43:55Z"},{"alias_kind":"pith_short_16","alias_value":"J3DBLRFOFO7QU5R7","created_at":"2026-07-05T01:43:55Z"},{"alias_kind":"pith_short_8","alias_value":"J3DBLRFO","created_at":"2026-07-05T01:43:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:J3DBLRFOFO7QU5R7XM2SNJSDSD","target":"record","payload":{"canonical_record":{"source":{"id":"2002.08799","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T15:24:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cd609910327ad57e6a19c6851d09a935d53eb5f9949293fab8ee702611cfa778","abstract_canon_sha256":"01206f67a17fd5d37a8f81fee519563602cbe944a8be645278a5bfd02662dc66"},"schema_version":"1.0"},"canonical_sha256":"4ec615c4ae2bbf0a763fbb3526a64390c6bd4c81342393bb8e9ffa44157474e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:55.677066Z","signature_b64":"amYw2fL0DjB92fUYKMlvtRjL8aqs13Wg4xAW38puqdzktMJwJZGcUTEpb2gLZ0nWNUhOHxyY29+Hxzl+y5D8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ec615c4ae2bbf0a763fbb3526a64390c6bd4c81342393bb8e9ffa44157474e6","last_reissued_at":"2026-07-05T01:43:55.676639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:55.676639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.08799","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":"2026-07-05T01:43:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L0/2YOLSSgkVoVInjSluOUfpcFiE5Mhq/tcv1zIa4h3aa2ZBfIKoeqJ2gh5VIVDQVyPPTWqdjm1Qb9TBMSlDCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:28:14.227996Z"},"content_sha256":"1398ebfb31491dc5dc1eaf316c7a36309da7238d4141d39744668325de075b0e","schema_version":"1.0","event_id":"sha256:1398ebfb31491dc5dc1eaf316c7a36309da7238d4141d39744668325de075b0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:J3DBLRFOFO7QU5R7XM2SNJSDSD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structured Prediction for Conditional Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Carlo Ciliberto, Ruohan Wang, Yiannis Demiris","submitted_at":"2020-02-20T15:24:15Z","abstract_excerpt":"The goal of optimization-based meta-learning is to find a single initialization shared across a distribution of tasks to speed up the process of learning new tasks. Conditional meta-learning seeks task-specific initialization to better capture complex task distributions and improve performance. However, many existing conditional methods are difficult to generalize and lack theoretical guarantees. In this work, we propose a new perspective on conditional meta-learning via structured prediction. We derive task-adaptive structured meta-learning (TASML), a principled framework that yields task-spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.08799","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/2002.08799/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":"2026-07-05T01:43:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+3tctQzLjNL5SF0BcyB7jpWtzNMjVSayZXgfBnrsCwEEUop40cEBkSvQ6nyt1aL2Kb9RuBlVDKhX2VErMuHbAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:28:14.228300Z"},"content_sha256":"bb3ca45b5105318bc648d4a91864a8911b55bc8f0bef93a22ecaccc9c9f716a3","schema_version":"1.0","event_id":"sha256:bb3ca45b5105318bc648d4a91864a8911b55bc8f0bef93a22ecaccc9c9f716a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J3DBLRFOFO7QU5R7XM2SNJSDSD/bundle.json","state_url":"https://pith.science/pith/J3DBLRFOFO7QU5R7XM2SNJSDSD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J3DBLRFOFO7QU5R7XM2SNJSDSD/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":"2026-08-01T07:28:14Z","links":{"resolver":"https://pith.science/pith/J3DBLRFOFO7QU5R7XM2SNJSDSD","bundle":"https://pith.science/pith/J3DBLRFOFO7QU5R7XM2SNJSDSD/bundle.json","state":"https://pith.science/pith/J3DBLRFOFO7QU5R7XM2SNJSDSD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J3DBLRFOFO7QU5R7XM2SNJSDSD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:J3DBLRFOFO7QU5R7XM2SNJSDSD","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":"01206f67a17fd5d37a8f81fee519563602cbe944a8be645278a5bfd02662dc66","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T15:24:15Z","title_canon_sha256":"cd609910327ad57e6a19c6851d09a935d53eb5f9949293fab8ee702611cfa778"},"schema_version":"1.0","source":{"id":"2002.08799","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.08799","created_at":"2026-07-05T01:43:55Z"},{"alias_kind":"arxiv_version","alias_value":"2002.08799v2","created_at":"2026-07-05T01:43:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.08799","created_at":"2026-07-05T01:43:55Z"},{"alias_kind":"pith_short_12","alias_value":"J3DBLRFOFO7Q","created_at":"2026-07-05T01:43:55Z"},{"alias_kind":"pith_short_16","alias_value":"J3DBLRFOFO7QU5R7","created_at":"2026-07-05T01:43:55Z"},{"alias_kind":"pith_short_8","alias_value":"J3DBLRFO","created_at":"2026-07-05T01:43:55Z"}],"graph_snapshots":[{"event_id":"sha256:bb3ca45b5105318bc648d4a91864a8911b55bc8f0bef93a22ecaccc9c9f716a3","target":"graph","created_at":"2026-07-05T01:43:55Z","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/2002.08799/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of optimization-based meta-learning is to find a single initialization shared across a distribution of tasks to speed up the process of learning new tasks. Conditional meta-learning seeks task-specific initialization to better capture complex task distributions and improve performance. However, many existing conditional methods are difficult to generalize and lack theoretical guarantees. In this work, we propose a new perspective on conditional meta-learning via structured prediction. We derive task-adaptive structured meta-learning (TASML), a principled framework that yields task-spe","authors_text":"Carlo Ciliberto, Ruohan Wang, Yiannis Demiris","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T15:24:15Z","title":"Structured Prediction for Conditional Meta-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.08799","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":"sha256:1398ebfb31491dc5dc1eaf316c7a36309da7238d4141d39744668325de075b0e","target":"record","created_at":"2026-07-05T01:43:55Z","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":"01206f67a17fd5d37a8f81fee519563602cbe944a8be645278a5bfd02662dc66","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T15:24:15Z","title_canon_sha256":"cd609910327ad57e6a19c6851d09a935d53eb5f9949293fab8ee702611cfa778"},"schema_version":"1.0","source":{"id":"2002.08799","kind":"arxiv","version":2}},"canonical_sha256":"4ec615c4ae2bbf0a763fbb3526a64390c6bd4c81342393bb8e9ffa44157474e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ec615c4ae2bbf0a763fbb3526a64390c6bd4c81342393bb8e9ffa44157474e6","first_computed_at":"2026-07-05T01:43:55.676639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:43:55.676639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"amYw2fL0DjB92fUYKMlvtRjL8aqs13Wg4xAW38puqdzktMJwJZGcUTEpb2gLZ0nWNUhOHxyY29+Hxzl+y5D8BA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:43:55.677066Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.08799","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1398ebfb31491dc5dc1eaf316c7a36309da7238d4141d39744668325de075b0e","sha256:bb3ca45b5105318bc648d4a91864a8911b55bc8f0bef93a22ecaccc9c9f716a3"],"state_sha256":"7d6eb21ddf81a6ff6ad75b47526fd9fe0a2c6abd5598e2b5f9b1f62dcbf17409"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yWuxmjcm4/MJzG0fl0CTXJBrpnmTG6K7BNZhXYuFII6kL6Kmjl4tQx4OVuQG8BSZvgHy+iClyJKsLkeSDEcJBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T07:28:14.231760Z","bundle_sha256":"b43c8f521468e2d4fd1eb6b003599a4be95234633119a0fde07b9cbf4fe60812"}}