{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KKAI33WZLZNXUKXVL7G5TJ5E3P","short_pith_number":"pith:KKAI33WZ","schema_version":"1.0","canonical_sha256":"52808deed95e5b7a2af55fcdd9a7a4dbcf1ed4574d7b8cca1da44e0a1ab4b1b1","source":{"kind":"arxiv","id":"2402.01629","version":1},"attestation_state":"computed","paper":{"title":"Position Paper: Generalized grammar rules and structure-based generalization beyond classical equivariance for lexical tasks and transduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Mircea Petrache, Shubhendu Trivedi","submitted_at":"2024-02-02T18:44:37Z","abstract_excerpt":"Compositional generalization is one of the main properties which differentiates lexical learning in humans from state-of-art neural networks. We propose a general framework for building models that can generalize compositionally using the concept of Generalized Grammar Rules (GGRs), a class of symmetry-based compositional constraints for transduction tasks, which we view as a transduction analogue of equivariance constraints in physics-inspired tasks. Besides formalizing generalized notions of symmetry for language transduction, our framework is general enough to contain many existing works as"},"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":"2402.01629","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T18:44:37Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"fbef092d754e823efb95caf78c69dfa869812c32e169a2bc30e302e463b6b8e8","abstract_canon_sha256":"9eb99aeeee9fd9c0c70995820c1a27b103700c1ad4c27dcfdf2a9a358fd12c0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:46.626823Z","signature_b64":"T7YWCIJJRtjHmVBMASITwvlU8hqvMZJAgaI4Y+ZPsnygbyIQwfcTJO3arVUMCp50EX/HcLuwsHC1gXjsau/NCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52808deed95e5b7a2af55fcdd9a7a4dbcf1ed4574d7b8cca1da44e0a1ab4b1b1","last_reissued_at":"2026-07-05T07:40:46.626342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:46.626342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Position Paper: Generalized grammar rules and structure-based generalization beyond classical equivariance for lexical tasks and transduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Mircea Petrache, Shubhendu Trivedi","submitted_at":"2024-02-02T18:44:37Z","abstract_excerpt":"Compositional generalization is one of the main properties which differentiates lexical learning in humans from state-of-art neural networks. We propose a general framework for building models that can generalize compositionally using the concept of Generalized Grammar Rules (GGRs), a class of symmetry-based compositional constraints for transduction tasks, which we view as a transduction analogue of equivariance constraints in physics-inspired tasks. Besides formalizing generalized notions of symmetry for language transduction, our framework is general enough to contain many existing works as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01629","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/2402.01629/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":"2402.01629","created_at":"2026-07-05T07:40:46.626400+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01629v1","created_at":"2026-07-05T07:40:46.626400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01629","created_at":"2026-07-05T07:40:46.626400+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKAI33WZLZNX","created_at":"2026-07-05T07:40:46.626400+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKAI33WZLZNXUKXV","created_at":"2026-07-05T07:40:46.626400+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKAI33WZ","created_at":"2026-07-05T07:40:46.626400+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10837","citing_title":"A Diagrammatic Approach to Improve Computational Efficiency in Group Equivariant Neural Networks","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KKAI33WZLZNXUKXVL7G5TJ5E3P","json":"https://pith.science/pith/KKAI33WZLZNXUKXVL7G5TJ5E3P.json","graph_json":"https://pith.science/api/pith-number/KKAI33WZLZNXUKXVL7G5TJ5E3P/graph.json","events_json":"https://pith.science/api/pith-number/KKAI33WZLZNXUKXVL7G5TJ5E3P/events.json","paper":"https://pith.science/paper/KKAI33WZ"},"agent_actions":{"view_html":"https://pith.science/pith/KKAI33WZLZNXUKXVL7G5TJ5E3P","download_json":"https://pith.science/pith/KKAI33WZLZNXUKXVL7G5TJ5E3P.json","view_paper":"https://pith.science/paper/KKAI33WZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01629&json=true","fetch_graph":"https://pith.science/api/pith-number/KKAI33WZLZNXUKXVL7G5TJ5E3P/graph.json","fetch_events":"https://pith.science/api/pith-number/KKAI33WZLZNXUKXVL7G5TJ5E3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKAI33WZLZNXUKXVL7G5TJ5E3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKAI33WZLZNXUKXVL7G5TJ5E3P/action/storage_attestation","attest_author":"https://pith.science/pith/KKAI33WZLZNXUKXVL7G5TJ5E3P/action/author_attestation","sign_citation":"https://pith.science/pith/KKAI33WZLZNXUKXVL7G5TJ5E3P/action/citation_signature","submit_replication":"https://pith.science/pith/KKAI33WZLZNXUKXVL7G5TJ5E3P/action/replication_record"}},"created_at":"2026-07-05T07:40:46.626400+00:00","updated_at":"2026-07-05T07:40:46.626400+00:00"}