{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VUT7IF36PSDN7YSXNDHD62SGXL","short_pith_number":"pith:VUT7IF36","schema_version":"1.0","canonical_sha256":"ad27f4177e7c86dfe25768ce3f6a46bae76fe39f4a63829c89864d6c008af1a6","source":{"kind":"arxiv","id":"2501.18797","version":2},"attestation_state":"computed","paper":{"title":"Compositional Generalization via Forced Rendering of Disentangled Latents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daoyuan Qian, Ila Fiete, Liu Ziyin, Qiyao Liang","submitted_at":"2025-01-30T23:20:41Z","abstract_excerpt":"Composition-the ability to generate myriad variations from finite means-is believed to underlie powerful generalization. However, compositional generalization remains a key challenge for deep learning. A widely held assumption is that learning disentangled (factorized) representations naturally supports this kind of extrapolation. Yet, empirical results are mixed, with many generative models failing to recognize and compose factors to generate out-of-distribution (OOD) samples. In this work, we investigate a controlled 2D Gaussian \"bump\" generation task with fully disentangled (x,y) inputs, de"},"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":"2501.18797","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T23:20:41Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6de4f80a85d68c60270079bde691343a52abf0a3a2d1abfa9c956df2df3c1972","abstract_canon_sha256":"ed26257bd2f223d2c202ba189fa7fd7557205d00892053a32915783a2d6b53f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:39.848205Z","signature_b64":"mrZegMl1Nl/jwf6K9ZnoMl7+k1tFI8mJyiZVNPk6TIBSuKDnciX7Ii5Um0qcNerMI90nExPK8ETW11eI6EF2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad27f4177e7c86dfe25768ce3f6a46bae76fe39f4a63829c89864d6c008af1a6","last_reissued_at":"2026-07-05T11:08:39.847719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:39.847719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional Generalization via Forced Rendering of Disentangled Latents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daoyuan Qian, Ila Fiete, Liu Ziyin, Qiyao Liang","submitted_at":"2025-01-30T23:20:41Z","abstract_excerpt":"Composition-the ability to generate myriad variations from finite means-is believed to underlie powerful generalization. However, compositional generalization remains a key challenge for deep learning. A widely held assumption is that learning disentangled (factorized) representations naturally supports this kind of extrapolation. Yet, empirical results are mixed, with many generative models failing to recognize and compose factors to generate out-of-distribution (OOD) samples. In this work, we investigate a controlled 2D Gaussian \"bump\" generation task with fully disentangled (x,y) inputs, de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18797","kind":"arxiv","version":2},"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/2501.18797/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":"2501.18797","created_at":"2026-07-05T11:08:39.847779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18797v2","created_at":"2026-07-05T11:08:39.847779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18797","created_at":"2026-07-05T11:08:39.847779+00:00"},{"alias_kind":"pith_short_12","alias_value":"VUT7IF36PSDN","created_at":"2026-07-05T11:08:39.847779+00:00"},{"alias_kind":"pith_short_16","alias_value":"VUT7IF36PSDN7YSX","created_at":"2026-07-05T11:08:39.847779+00:00"},{"alias_kind":"pith_short_8","alias_value":"VUT7IF36","created_at":"2026-07-05T11:08:39.847779+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/VUT7IF36PSDN7YSXNDHD62SGXL","json":"https://pith.science/pith/VUT7IF36PSDN7YSXNDHD62SGXL.json","graph_json":"https://pith.science/api/pith-number/VUT7IF36PSDN7YSXNDHD62SGXL/graph.json","events_json":"https://pith.science/api/pith-number/VUT7IF36PSDN7YSXNDHD62SGXL/events.json","paper":"https://pith.science/paper/VUT7IF36"},"agent_actions":{"view_html":"https://pith.science/pith/VUT7IF36PSDN7YSXNDHD62SGXL","download_json":"https://pith.science/pith/VUT7IF36PSDN7YSXNDHD62SGXL.json","view_paper":"https://pith.science/paper/VUT7IF36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18797&json=true","fetch_graph":"https://pith.science/api/pith-number/VUT7IF36PSDN7YSXNDHD62SGXL/graph.json","fetch_events":"https://pith.science/api/pith-number/VUT7IF36PSDN7YSXNDHD62SGXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VUT7IF36PSDN7YSXNDHD62SGXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VUT7IF36PSDN7YSXNDHD62SGXL/action/storage_attestation","attest_author":"https://pith.science/pith/VUT7IF36PSDN7YSXNDHD62SGXL/action/author_attestation","sign_citation":"https://pith.science/pith/VUT7IF36PSDN7YSXNDHD62SGXL/action/citation_signature","submit_replication":"https://pith.science/pith/VUT7IF36PSDN7YSXNDHD62SGXL/action/replication_record"}},"created_at":"2026-07-05T11:08:39.847779+00:00","updated_at":"2026-07-05T11:08:39.847779+00:00"}