{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YYL5VV47NKULOB637LLCYFJ42F","short_pith_number":"pith:YYL5VV47","schema_version":"1.0","canonical_sha256":"c617dad79f6aa8b707dbfad62c153cd162ee1893450cdb475c3e1531f97cc8ed","source":{"kind":"arxiv","id":"2503.01215","version":1},"attestation_state":"computed","paper":{"title":"Architectural and Inferential Inductive Biases For Exchangeable Sequence Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ang Li, Daksh Mittal, Daniel Guetta, Hongseok Namkoong, Tzu-Ching Yen","submitted_at":"2025-03-03T06:25:44Z","abstract_excerpt":"Autoregressive models have emerged as a powerful framework for modeling exchangeable sequences - i.i.d. observations when conditioned on some latent factor - enabling direct modeling of uncertainty from missing data (rather than a latent). Motivated by the critical role posterior inference plays as a subroutine in decision-making (e.g., active learning, bandits), we study the inferential and architectural inductive biases that are most effective for exchangeable sequence modeling. For the inference stage, we highlight a fundamental limitation of the prevalent single-step generation approach: i"},"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":"2503.01215","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-03T06:25:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"99784cb818a94c9443732cf3b225a5004ac36fe9980e2c693a68844a2f025907","abstract_canon_sha256":"d4f1140ace5b512165f3096cff5801efcc1befbb22637583ed25d554d9469411"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:01.882715Z","signature_b64":"PLiBgG9GDTSS749yWydhKNdVNuG//JXCyYy4p9Nz46hJq6OKAHKgJ+gmibCasV7EO9jC3E0WvwPn2MsicqHfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c617dad79f6aa8b707dbfad62c153cd162ee1893450cdb475c3e1531f97cc8ed","last_reissued_at":"2026-07-05T10:23:01.882073Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:01.882073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Architectural and Inferential Inductive Biases For Exchangeable Sequence Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ang Li, Daksh Mittal, Daniel Guetta, Hongseok Namkoong, Tzu-Ching Yen","submitted_at":"2025-03-03T06:25:44Z","abstract_excerpt":"Autoregressive models have emerged as a powerful framework for modeling exchangeable sequences - i.i.d. observations when conditioned on some latent factor - enabling direct modeling of uncertainty from missing data (rather than a latent). Motivated by the critical role posterior inference plays as a subroutine in decision-making (e.g., active learning, bandits), we study the inferential and architectural inductive biases that are most effective for exchangeable sequence modeling. For the inference stage, we highlight a fundamental limitation of the prevalent single-step generation approach: i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01215","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/2503.01215/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":"2503.01215","created_at":"2026-07-05T10:23:01.882146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.01215v1","created_at":"2026-07-05T10:23:01.882146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01215","created_at":"2026-07-05T10:23:01.882146+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYL5VV47NKUL","created_at":"2026-07-05T10:23:01.882146+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYL5VV47NKULOB63","created_at":"2026-07-05T10:23:01.882146+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYL5VV47","created_at":"2026-07-05T10:23:01.882146+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/YYL5VV47NKULOB637LLCYFJ42F","json":"https://pith.science/pith/YYL5VV47NKULOB637LLCYFJ42F.json","graph_json":"https://pith.science/api/pith-number/YYL5VV47NKULOB637LLCYFJ42F/graph.json","events_json":"https://pith.science/api/pith-number/YYL5VV47NKULOB637LLCYFJ42F/events.json","paper":"https://pith.science/paper/YYL5VV47"},"agent_actions":{"view_html":"https://pith.science/pith/YYL5VV47NKULOB637LLCYFJ42F","download_json":"https://pith.science/pith/YYL5VV47NKULOB637LLCYFJ42F.json","view_paper":"https://pith.science/paper/YYL5VV47","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.01215&json=true","fetch_graph":"https://pith.science/api/pith-number/YYL5VV47NKULOB637LLCYFJ42F/graph.json","fetch_events":"https://pith.science/api/pith-number/YYL5VV47NKULOB637LLCYFJ42F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYL5VV47NKULOB637LLCYFJ42F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYL5VV47NKULOB637LLCYFJ42F/action/storage_attestation","attest_author":"https://pith.science/pith/YYL5VV47NKULOB637LLCYFJ42F/action/author_attestation","sign_citation":"https://pith.science/pith/YYL5VV47NKULOB637LLCYFJ42F/action/citation_signature","submit_replication":"https://pith.science/pith/YYL5VV47NKULOB637LLCYFJ42F/action/replication_record"}},"created_at":"2026-07-05T10:23:01.882146+00:00","updated_at":"2026-07-05T10:23:01.882146+00:00"}