{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CH2YKO6UAEQK6ZUWAMIP5UZGC6","short_pith_number":"pith:CH2YKO6U","schema_version":"1.0","canonical_sha256":"11f5853bd40120af66960310fed3261794a41730d50bf9996bc556e6ca0f508a","source":{"kind":"arxiv","id":"2608.08644","version":1},"attestation_state":"computed","paper":{"title":"Path-dependent Discrete Amortized Inference","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Esmeralda S. Whitammer, Salem Lahlou, Tiago da Silva","submitted_at":"2026-08-09T11:35:05Z","abstract_excerpt":"We consider the problem of sampling compositional and discrete objects from a given unnormalized posterior distribution. Notably, recent studies have shown that this problem can be efficiently solved by learning a deterministic Markov Decision Process (MDP) that progressively builds each object in proportion to the posterior. In this work, however, we demonstrate that the Markovian assumption can both hamper signal propagation during training and catastrophically reduce the learned sampler's expressivity due to state aliasing. To address these issues, we propose lifting the MDP with a learnabl"},"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":"2608.08644","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-09T11:35:05Z","cross_cats_sorted":[],"title_canon_sha256":"883a9afc118c89a89c2f44924c4f4bf666541f9c8ed36f60be7636d31f46ce89","abstract_canon_sha256":"5550235799f7f8fed6a0b9193bd9b90c6dc60785fe2c0ede5774b9c59729125a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:23:15.712722Z","signature_b64":"R9Bhgq+5jesFAEQEUGttPWlfT+Kdow8ZtswKZFbFp1KQgpPtdbTXwtUkPMcwiEgQ0jzPHVFqSYd0q52Ep7XMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11f5853bd40120af66960310fed3261794a41730d50bf9996bc556e6ca0f508a","last_reissued_at":"2026-08-11T01:23:15.710354Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:23:15.710354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Path-dependent Discrete Amortized Inference","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Esmeralda S. Whitammer, Salem Lahlou, Tiago da Silva","submitted_at":"2026-08-09T11:35:05Z","abstract_excerpt":"We consider the problem of sampling compositional and discrete objects from a given unnormalized posterior distribution. Notably, recent studies have shown that this problem can be efficiently solved by learning a deterministic Markov Decision Process (MDP) that progressively builds each object in proportion to the posterior. In this work, however, we demonstrate that the Markovian assumption can both hamper signal propagation during training and catastrophically reduce the learned sampler's expressivity due to state aliasing. To address these issues, we propose lifting the MDP with a learnabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08644","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/2608.08644/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":"2608.08644","created_at":"2026-08-11T01:23:15.711116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08644v1","created_at":"2026-08-11T01:23:15.711116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08644","created_at":"2026-08-11T01:23:15.711116+00:00"},{"alias_kind":"pith_short_12","alias_value":"CH2YKO6UAEQK","created_at":"2026-08-11T01:23:15.711116+00:00"},{"alias_kind":"pith_short_16","alias_value":"CH2YKO6UAEQK6ZUW","created_at":"2026-08-11T01:23:15.711116+00:00"},{"alias_kind":"pith_short_8","alias_value":"CH2YKO6U","created_at":"2026-08-11T01:23:15.711116+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/CH2YKO6UAEQK6ZUWAMIP5UZGC6","json":"https://pith.science/pith/CH2YKO6UAEQK6ZUWAMIP5UZGC6.json","graph_json":"https://pith.science/api/pith-number/CH2YKO6UAEQK6ZUWAMIP5UZGC6/graph.json","events_json":"https://pith.science/api/pith-number/CH2YKO6UAEQK6ZUWAMIP5UZGC6/events.json","paper":"https://pith.science/paper/CH2YKO6U"},"agent_actions":{"view_html":"https://pith.science/pith/CH2YKO6UAEQK6ZUWAMIP5UZGC6","download_json":"https://pith.science/pith/CH2YKO6UAEQK6ZUWAMIP5UZGC6.json","view_paper":"https://pith.science/paper/CH2YKO6U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08644&json=true","fetch_graph":"https://pith.science/api/pith-number/CH2YKO6UAEQK6ZUWAMIP5UZGC6/graph.json","fetch_events":"https://pith.science/api/pith-number/CH2YKO6UAEQK6ZUWAMIP5UZGC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CH2YKO6UAEQK6ZUWAMIP5UZGC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CH2YKO6UAEQK6ZUWAMIP5UZGC6/action/storage_attestation","attest_author":"https://pith.science/pith/CH2YKO6UAEQK6ZUWAMIP5UZGC6/action/author_attestation","sign_citation":"https://pith.science/pith/CH2YKO6UAEQK6ZUWAMIP5UZGC6/action/citation_signature","submit_replication":"https://pith.science/pith/CH2YKO6UAEQK6ZUWAMIP5UZGC6/action/replication_record"}},"created_at":"2026-08-11T01:23:15.711116+00:00","updated_at":"2026-08-11T01:23:15.711116+00:00"}