{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3I2DJ7VORE546PVKSOWIP6AJLA","short_pith_number":"pith:3I2DJ7VO","schema_version":"1.0","canonical_sha256":"da3434feae893bcf3eaa93ac87f8095822f3ed7636867734f6e708d868d562a5","source":{"kind":"arxiv","id":"1805.09547","version":1},"attestation_state":"computed","paper":{"title":"Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kentaro Inui, Ran Tian, Ryo Takahashi","submitted_at":"2018-05-24T08:32:53Z","abstract_excerpt":"Embedding models for entities and relations are extremely useful for recovering missing facts in a knowledge base. Intuitively, a relation can be modeled by a matrix mapping entity vectors. However, relations reside on low dimension sub-manifolds in the parameter space of arbitrary matrices---for one reason, composition of two relations $\\boldsymbol{M}_1,\\boldsymbol{M}_2$ may match a third $\\boldsymbol{M}_3$ (e.g. composition of relations currency_of_country and country_of_film usually matches currency_of_film_budget), which imposes compositional constraints to be satisfied by the parameters ("},"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":"1805.09547","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-24T08:32:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"95e5a6b5cea5fd6e45aa13bec931245ee29561e636045a5e4ccb9657f56990a5","abstract_canon_sha256":"f109d6dda3e5ee8face492800a57488d03d8b4777927f2b0fed16e7a0794372c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:03.611477Z","signature_b64":"gOx56LvqtFxb8D7Fq2LR9ZrFgXkQnJ0yiCQRqXthvO/8VAYRpFrZSXn0lg8Bml1tFwQENiRbh/1CUowTRE9YAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da3434feae893bcf3eaa93ac87f8095822f3ed7636867734f6e708d868d562a5","last_reissued_at":"2026-05-18T00:15:03.610718Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:03.610718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kentaro Inui, Ran Tian, Ryo Takahashi","submitted_at":"2018-05-24T08:32:53Z","abstract_excerpt":"Embedding models for entities and relations are extremely useful for recovering missing facts in a knowledge base. Intuitively, a relation can be modeled by a matrix mapping entity vectors. However, relations reside on low dimension sub-manifolds in the parameter space of arbitrary matrices---for one reason, composition of two relations $\\boldsymbol{M}_1,\\boldsymbol{M}_2$ may match a third $\\boldsymbol{M}_3$ (e.g. composition of relations currency_of_country and country_of_film usually matches currency_of_film_budget), which imposes compositional constraints to be satisfied by the parameters ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09547","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":""},"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":"1805.09547","created_at":"2026-05-18T00:15:03.610857+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.09547v1","created_at":"2026-05-18T00:15:03.610857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09547","created_at":"2026-05-18T00:15:03.610857+00:00"},{"alias_kind":"pith_short_12","alias_value":"3I2DJ7VORE54","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"3I2DJ7VORE546PVK","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"3I2DJ7VO","created_at":"2026-05-18T12:32:02.567920+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/3I2DJ7VORE546PVKSOWIP6AJLA","json":"https://pith.science/pith/3I2DJ7VORE546PVKSOWIP6AJLA.json","graph_json":"https://pith.science/api/pith-number/3I2DJ7VORE546PVKSOWIP6AJLA/graph.json","events_json":"https://pith.science/api/pith-number/3I2DJ7VORE546PVKSOWIP6AJLA/events.json","paper":"https://pith.science/paper/3I2DJ7VO"},"agent_actions":{"view_html":"https://pith.science/pith/3I2DJ7VORE546PVKSOWIP6AJLA","download_json":"https://pith.science/pith/3I2DJ7VORE546PVKSOWIP6AJLA.json","view_paper":"https://pith.science/paper/3I2DJ7VO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.09547&json=true","fetch_graph":"https://pith.science/api/pith-number/3I2DJ7VORE546PVKSOWIP6AJLA/graph.json","fetch_events":"https://pith.science/api/pith-number/3I2DJ7VORE546PVKSOWIP6AJLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3I2DJ7VORE546PVKSOWIP6AJLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3I2DJ7VORE546PVKSOWIP6AJLA/action/storage_attestation","attest_author":"https://pith.science/pith/3I2DJ7VORE546PVKSOWIP6AJLA/action/author_attestation","sign_citation":"https://pith.science/pith/3I2DJ7VORE546PVKSOWIP6AJLA/action/citation_signature","submit_replication":"https://pith.science/pith/3I2DJ7VORE546PVKSOWIP6AJLA/action/replication_record"}},"created_at":"2026-05-18T00:15:03.610857+00:00","updated_at":"2026-05-18T00:15:03.610857+00:00"}