{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NULWGSXB6LRIWFT2IBLFTT4NGB","short_pith_number":"pith:NULWGSXB","canonical_record":{"source":{"id":"2102.10271","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T06:41:08Z","cross_cats_sorted":[],"title_canon_sha256":"794c92b93083d890e2a3f54b3b7d2c3c6be28a8424a849661a6c8187bffae113","abstract_canon_sha256":"1823e86981afcffae9bc22c01f5893c5b174aec78440f24588fc9bed85a9a15d"},"schema_version":"1.0"},"canonical_sha256":"6d17634ae1f2e28b167a405659cf8d305bc50db7380c38cbc65a51dc77507d05","source":{"kind":"arxiv","id":"2102.10271","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10271","created_at":"2026-07-05T05:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10271v5","created_at":"2026-07-05T05:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10271","created_at":"2026-07-05T05:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"NULWGSXB6LRI","created_at":"2026-07-05T05:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"NULWGSXB6LRIWFT2","created_at":"2026-07-05T05:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"NULWGSXB","created_at":"2026-07-05T05:05:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NULWGSXB6LRIWFT2IBLFTT4NGB","target":"record","payload":{"canonical_record":{"source":{"id":"2102.10271","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T06:41:08Z","cross_cats_sorted":[],"title_canon_sha256":"794c92b93083d890e2a3f54b3b7d2c3c6be28a8424a849661a6c8187bffae113","abstract_canon_sha256":"1823e86981afcffae9bc22c01f5893c5b174aec78440f24588fc9bed85a9a15d"},"schema_version":"1.0"},"canonical_sha256":"6d17634ae1f2e28b167a405659cf8d305bc50db7380c38cbc65a51dc77507d05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:43.196510Z","signature_b64":"aiL64A2/P5bM3mm0RZ09m/3oXjdD/0zP8N3UYRRKgNnr4LNNqmTcwyMi6PVhsL3Oq1ccZX/zXbisoLEHbPe5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d17634ae1f2e28b167a405659cf8d305bc50db7380c38cbc65a51dc77507d05","last_reissued_at":"2026-07-05T05:05:43.195998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:43.195998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.10271","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SEa8eV7pOnmD0m1j3Zm9rpEbx8TtxF/89g+DPVPHYZ45qO7YylqQ3CH0lWjCVx0epoNCgvd0ov5DCWXuXYhpDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T16:50:08.486631Z"},"content_sha256":"f01a82f3c919b34d8266f596e067276988be837d62ded5e3cc16d21e7c34ecf1","schema_version":"1.0","event_id":"sha256:f01a82f3c919b34d8266f596e067276988be837d62ded5e3cc16d21e7c34ecf1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NULWGSXB6LRIWFT2IBLFTT4NGB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-Learning Dynamics Forecasting Using Task Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Robin Walters, Rose Yu, Rui Wang","submitted_at":"2021-02-20T06:41:08Z","abstract_excerpt":"Current deep learning models for dynamics forecasting struggle with generalization. They can only forecast in a specific domain and fail when applied to systems with different parameters, external forces, or boundary conditions. We propose a model-based meta-learning method called DyAd which can generalize across heterogeneous domains by partitioning them into different tasks. DyAd has two parts: an encoder which infers the time-invariant hidden features of the task with weak supervision, and a forecaster which learns the shared dynamics of the entire domain. The encoder adapts and controls th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10271","kind":"arxiv","version":5},"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/2102.10271/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":"2026-07-05T05:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V5dH8nfJE/4OBofAziof/WViTUFL/ZpV4MsoBbxc3e0aC7//6cITPNtgRrjjmcVRlRC6+t5tLOudoWnw3GeNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T16:50:08.487163Z"},"content_sha256":"0035dbda9e2d44332ae5cc272a49f0efaa274b33642ef4d9a6846623608b2231","schema_version":"1.0","event_id":"sha256:0035dbda9e2d44332ae5cc272a49f0efaa274b33642ef4d9a6846623608b2231"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NULWGSXB6LRIWFT2IBLFTT4NGB/bundle.json","state_url":"https://pith.science/pith/NULWGSXB6LRIWFT2IBLFTT4NGB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NULWGSXB6LRIWFT2IBLFTT4NGB/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":"2026-08-11T16:50:08Z","links":{"resolver":"https://pith.science/pith/NULWGSXB6LRIWFT2IBLFTT4NGB","bundle":"https://pith.science/pith/NULWGSXB6LRIWFT2IBLFTT4NGB/bundle.json","state":"https://pith.science/pith/NULWGSXB6LRIWFT2IBLFTT4NGB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NULWGSXB6LRIWFT2IBLFTT4NGB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NULWGSXB6LRIWFT2IBLFTT4NGB","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":"1823e86981afcffae9bc22c01f5893c5b174aec78440f24588fc9bed85a9a15d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T06:41:08Z","title_canon_sha256":"794c92b93083d890e2a3f54b3b7d2c3c6be28a8424a849661a6c8187bffae113"},"schema_version":"1.0","source":{"id":"2102.10271","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10271","created_at":"2026-07-05T05:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10271v5","created_at":"2026-07-05T05:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10271","created_at":"2026-07-05T05:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"NULWGSXB6LRI","created_at":"2026-07-05T05:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"NULWGSXB6LRIWFT2","created_at":"2026-07-05T05:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"NULWGSXB","created_at":"2026-07-05T05:05:43Z"}],"graph_snapshots":[{"event_id":"sha256:0035dbda9e2d44332ae5cc272a49f0efaa274b33642ef4d9a6846623608b2231","target":"graph","created_at":"2026-07-05T05:05:43Z","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/2102.10271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current deep learning models for dynamics forecasting struggle with generalization. They can only forecast in a specific domain and fail when applied to systems with different parameters, external forces, or boundary conditions. We propose a model-based meta-learning method called DyAd which can generalize across heterogeneous domains by partitioning them into different tasks. DyAd has two parts: an encoder which infers the time-invariant hidden features of the task with weak supervision, and a forecaster which learns the shared dynamics of the entire domain. The encoder adapts and controls th","authors_text":"Robin Walters, Rose Yu, Rui Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T06:41:08Z","title":"Meta-Learning Dynamics Forecasting Using Task Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10271","kind":"arxiv","version":5},"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:f01a82f3c919b34d8266f596e067276988be837d62ded5e3cc16d21e7c34ecf1","target":"record","created_at":"2026-07-05T05:05:43Z","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":"1823e86981afcffae9bc22c01f5893c5b174aec78440f24588fc9bed85a9a15d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T06:41:08Z","title_canon_sha256":"794c92b93083d890e2a3f54b3b7d2c3c6be28a8424a849661a6c8187bffae113"},"schema_version":"1.0","source":{"id":"2102.10271","kind":"arxiv","version":5}},"canonical_sha256":"6d17634ae1f2e28b167a405659cf8d305bc50db7380c38cbc65a51dc77507d05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d17634ae1f2e28b167a405659cf8d305bc50db7380c38cbc65a51dc77507d05","first_computed_at":"2026-07-05T05:05:43.195998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:43.195998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aiL64A2/P5bM3mm0RZ09m/3oXjdD/0zP8N3UYRRKgNnr4LNNqmTcwyMi6PVhsL3Oq1ccZX/zXbisoLEHbPe5Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:43.196510Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.10271","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f01a82f3c919b34d8266f596e067276988be837d62ded5e3cc16d21e7c34ecf1","sha256:0035dbda9e2d44332ae5cc272a49f0efaa274b33642ef4d9a6846623608b2231"],"state_sha256":"66663e20cbcca692c388010ed7a1c73cd8a449a11e853778ed481e8e1d655c30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eja7ByxhjS7sOCUG6ykw+Vnma9jgzSPsFmrjNRuPqe0dcdOeJhcWHPgNFmV8Mn8kFRdBLJ4TNkxRn0+SRvm5Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T16:50:08.492420Z","bundle_sha256":"bb0b5b62aca7044a9832e7057a6e303dbb8dcace20b86c6ab93aa0972be7676d"}}