{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BC2572PVENR64JF3SWJNEWXWSJ","short_pith_number":"pith:BC2572PV","schema_version":"1.0","canonical_sha256":"08b5dfe9f52363ee24bb9592d25af6924ad03fb6904c88d3efa9a6d457338634","source":{"kind":"arxiv","id":"2109.14501","version":5},"attestation_state":"computed","paper":{"title":"Towards a theory of out-of-distribution learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ali Geisa, Carey E. Priebe, Eric Eaton, Haoyin Xu, Hayden S. Helm, Jayanta Dey, Jeffery Dick, Joshua T. Vogelstein, Ronak Mehta, Tyler M. Tomita","submitted_at":"2021-09-29T15:35:16Z","abstract_excerpt":"Learning is a process wherein a learning agent enhances its performance through exposure of experience or data. Throughout this journey, the agent may encounter diverse learning environments. For example, data may be presented to the leaner all at once, in multiple batches, or sequentially. Furthermore, the distribution of each data sample could be either identical and independent (iid) or non-iid. Additionally, there may exist computational and space constraints for the deployment of the learning algorithms. The complexity of a learning task can vary significantly, depending on the learning s"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2109.14501","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-09-29T15:35:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d5287a1d66161fb2ab7c12f4a8465c3dfa74cd99b6f7e75b5cb43a7a69cc4c1a","abstract_canon_sha256":"1442088a55999368b1c126bf72683d6eeefce0ad3e784012845b67d634280854"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:30.912453Z","signature_b64":"EmR5RjtUeHtN2QGYap1Ytew7xV62E92wNB4HvcPo2AKER8pkcoG6SHFlHEr1uyoRmOxZcRcUMfx4xmohZbUhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08b5dfe9f52363ee24bb9592d25af6924ad03fb6904c88d3efa9a6d457338634","last_reissued_at":"2026-07-05T08:28:30.912004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:30.912004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards a theory of out-of-distribution learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ali Geisa, Carey E. Priebe, Eric Eaton, Haoyin Xu, Hayden S. Helm, Jayanta Dey, Jeffery Dick, Joshua T. Vogelstein, Ronak Mehta, Tyler M. Tomita","submitted_at":"2021-09-29T15:35:16Z","abstract_excerpt":"Learning is a process wherein a learning agent enhances its performance through exposure of experience or data. Throughout this journey, the agent may encounter diverse learning environments. For example, data may be presented to the leaner all at once, in multiple batches, or sequentially. Furthermore, the distribution of each data sample could be either identical and independent (iid) or non-iid. Additionally, there may exist computational and space constraints for the deployment of the learning algorithms. The complexity of a learning task can vary significantly, depending on the learning s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.14501","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/2109.14501/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2109.14501","created_at":"2026-07-05T08:28:30.912061+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.14501v5","created_at":"2026-07-05T08:28:30.912061+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.14501","created_at":"2026-07-05T08:28:30.912061+00:00"},{"alias_kind":"pith_short_12","alias_value":"BC2572PVENR6","created_at":"2026-07-05T08:28:30.912061+00:00"},{"alias_kind":"pith_short_16","alias_value":"BC2572PVENR64JF3","created_at":"2026-07-05T08:28:30.912061+00:00"},{"alias_kind":"pith_short_8","alias_value":"BC2572PV","created_at":"2026-07-05T08:28:30.912061+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BC2572PVENR64JF3SWJNEWXWSJ","json":"https://pith.science/pith/BC2572PVENR64JF3SWJNEWXWSJ.json","graph_json":"https://pith.science/api/pith-number/BC2572PVENR64JF3SWJNEWXWSJ/graph.json","events_json":"https://pith.science/api/pith-number/BC2572PVENR64JF3SWJNEWXWSJ/events.json","paper":"https://pith.science/paper/BC2572PV"},"agent_actions":{"view_html":"https://pith.science/pith/BC2572PVENR64JF3SWJNEWXWSJ","download_json":"https://pith.science/pith/BC2572PVENR64JF3SWJNEWXWSJ.json","view_paper":"https://pith.science/paper/BC2572PV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.14501&json=true","fetch_graph":"https://pith.science/api/pith-number/BC2572PVENR64JF3SWJNEWXWSJ/graph.json","fetch_events":"https://pith.science/api/pith-number/BC2572PVENR64JF3SWJNEWXWSJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BC2572PVENR64JF3SWJNEWXWSJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BC2572PVENR64JF3SWJNEWXWSJ/action/storage_attestation","attest_author":"https://pith.science/pith/BC2572PVENR64JF3SWJNEWXWSJ/action/author_attestation","sign_citation":"https://pith.science/pith/BC2572PVENR64JF3SWJNEWXWSJ/action/citation_signature","submit_replication":"https://pith.science/pith/BC2572PVENR64JF3SWJNEWXWSJ/action/replication_record"}},"created_at":"2026-07-05T08:28:30.912061+00:00","updated_at":"2026-07-05T08:28:30.912061+00:00"}