{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4SQVWEMQNU4J2OOL5BE7D2NSGH","short_pith_number":"pith:4SQVWEMQ","schema_version":"1.0","canonical_sha256":"e4a15b11906d389d39cbe849f1e9b231cd93eedb7870facc1d896e93befcd9ae","source":{"kind":"arxiv","id":"2402.10575","version":1},"attestation_state":"computed","paper":{"title":"Symbolic Autoencoding for Self-Supervised Sequence Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amin Mansouri, Martin Josifoski, Maxime Peyrard, Mohammad Hossein Amani, Nicolas Mario Baldwin, Robert West","submitted_at":"2024-02-16T11:04:31Z","abstract_excerpt":"Traditional language models, adept at next-token prediction in text sequences, often struggle with transduction tasks between distinct symbolic systems, particularly when parallel data is scarce. Addressing this issue, we introduce \\textit{symbolic autoencoding} ($\\Sigma$AE), a self-supervised framework that harnesses the power of abundant unparallel data alongside limited parallel data. $\\Sigma$AE connects two generative models via a discrete bottleneck layer and is optimized end-to-end by minimizing reconstruction loss (simultaneously with supervised loss for the parallel data), such that th"},"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":"2402.10575","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-16T11:04:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"99d0f228304538f4d715f6cfdebc6278d85a40dfc806e3661e5b2c3c3d83dc5b","abstract_canon_sha256":"565424049bd82e432f3dd93247a36e66093745241b2ff7e58e664b340522472e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:58.139636Z","signature_b64":"hXbAyv8ZBDUWRDH0h7AKZpRmNBaPwpOeTJlZRUnWhU2h1G+TnMFvTqpt894OENNgs+POqp3EchYO/UGiHuAtBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4a15b11906d389d39cbe849f1e9b231cd93eedb7870facc1d896e93befcd9ae","last_reissued_at":"2026-07-05T07:45:58.139239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:58.139239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symbolic Autoencoding for Self-Supervised Sequence Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amin Mansouri, Martin Josifoski, Maxime Peyrard, Mohammad Hossein Amani, Nicolas Mario Baldwin, Robert West","submitted_at":"2024-02-16T11:04:31Z","abstract_excerpt":"Traditional language models, adept at next-token prediction in text sequences, often struggle with transduction tasks between distinct symbolic systems, particularly when parallel data is scarce. Addressing this issue, we introduce \\textit{symbolic autoencoding} ($\\Sigma$AE), a self-supervised framework that harnesses the power of abundant unparallel data alongside limited parallel data. $\\Sigma$AE connects two generative models via a discrete bottleneck layer and is optimized end-to-end by minimizing reconstruction loss (simultaneously with supervised loss for the parallel data), such that th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10575","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/2402.10575/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":"2402.10575","created_at":"2026-07-05T07:45:58.139296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10575v1","created_at":"2026-07-05T07:45:58.139296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10575","created_at":"2026-07-05T07:45:58.139296+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SQVWEMQNU4J","created_at":"2026-07-05T07:45:58.139296+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SQVWEMQNU4J2OOL","created_at":"2026-07-05T07:45:58.139296+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SQVWEMQ","created_at":"2026-07-05T07:45:58.139296+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/4SQVWEMQNU4J2OOL5BE7D2NSGH","json":"https://pith.science/pith/4SQVWEMQNU4J2OOL5BE7D2NSGH.json","graph_json":"https://pith.science/api/pith-number/4SQVWEMQNU4J2OOL5BE7D2NSGH/graph.json","events_json":"https://pith.science/api/pith-number/4SQVWEMQNU4J2OOL5BE7D2NSGH/events.json","paper":"https://pith.science/paper/4SQVWEMQ"},"agent_actions":{"view_html":"https://pith.science/pith/4SQVWEMQNU4J2OOL5BE7D2NSGH","download_json":"https://pith.science/pith/4SQVWEMQNU4J2OOL5BE7D2NSGH.json","view_paper":"https://pith.science/paper/4SQVWEMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10575&json=true","fetch_graph":"https://pith.science/api/pith-number/4SQVWEMQNU4J2OOL5BE7D2NSGH/graph.json","fetch_events":"https://pith.science/api/pith-number/4SQVWEMQNU4J2OOL5BE7D2NSGH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SQVWEMQNU4J2OOL5BE7D2NSGH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SQVWEMQNU4J2OOL5BE7D2NSGH/action/storage_attestation","attest_author":"https://pith.science/pith/4SQVWEMQNU4J2OOL5BE7D2NSGH/action/author_attestation","sign_citation":"https://pith.science/pith/4SQVWEMQNU4J2OOL5BE7D2NSGH/action/citation_signature","submit_replication":"https://pith.science/pith/4SQVWEMQNU4J2OOL5BE7D2NSGH/action/replication_record"}},"created_at":"2026-07-05T07:45:58.139296+00:00","updated_at":"2026-07-05T07:45:58.139296+00:00"}