{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:25CUZAWOU3HCE3Y5KHHKALQUUH","short_pith_number":"pith:25CUZAWO","schema_version":"1.0","canonical_sha256":"d7454c82cea6ce226f1d51cea02e14a1f17258359dbb8de1602c5dcaeda6b22b","source":{"kind":"arxiv","id":"2506.04668","version":3},"attestation_state":"computed","paper":{"title":"Feature-Based Lie Group Transformer for Real-World Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kayato Nishitsunoi, Takayuki Komatsu, Yasuo Kuniyoshi, Yoshiyuki Ohmura","submitted_at":"2025-06-05T06:30:11Z","abstract_excerpt":"The main goal of representation learning is to acquire meaningful representations from real-world sensory inputs without supervision. Representation learning explains some aspects of human development. Various neural network (NN) models have been proposed that acquire empirically good representations. However, the formulation of a good representation has not been established. We recently proposed a method for categorizing changes between a pair of sensory inputs. A unique feature of this approach is that transformations between two sensory inputs are learned to satisfy algebraic structural con"},"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":"2506.04668","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T06:30:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1d7bb99a57a6d1467626cac44ce2c0d95c27167b2e6e1c871c6c93cbcae7c1b1","abstract_canon_sha256":"68b5e87e0d41407b6512b1138570418123ddec3193f8ced0a8b4a74dc819958f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:23.102743Z","signature_b64":"Hs9Cj07gPAYkbQk5TGe8OygAO9jF5hsyMOGnZuSpiiCVXnbmAhBnBtVuPzSmrxQ9eCUXokdr8Mg3qbVFzo3cDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7454c82cea6ce226f1d51cea02e14a1f17258359dbb8de1602c5dcaeda6b22b","last_reissued_at":"2026-07-05T11:18:23.102240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:23.102240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature-Based Lie Group Transformer for Real-World Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kayato Nishitsunoi, Takayuki Komatsu, Yasuo Kuniyoshi, Yoshiyuki Ohmura","submitted_at":"2025-06-05T06:30:11Z","abstract_excerpt":"The main goal of representation learning is to acquire meaningful representations from real-world sensory inputs without supervision. Representation learning explains some aspects of human development. Various neural network (NN) models have been proposed that acquire empirically good representations. However, the formulation of a good representation has not been established. We recently proposed a method for categorizing changes between a pair of sensory inputs. A unique feature of this approach is that transformations between two sensory inputs are learned to satisfy algebraic structural con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04668","kind":"arxiv","version":3},"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/2506.04668/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":"2506.04668","created_at":"2026-07-05T11:18:23.102300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04668v3","created_at":"2026-07-05T11:18:23.102300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04668","created_at":"2026-07-05T11:18:23.102300+00:00"},{"alias_kind":"pith_short_12","alias_value":"25CUZAWOU3HC","created_at":"2026-07-05T11:18:23.102300+00:00"},{"alias_kind":"pith_short_16","alias_value":"25CUZAWOU3HCE3Y5","created_at":"2026-07-05T11:18:23.102300+00:00"},{"alias_kind":"pith_short_8","alias_value":"25CUZAWO","created_at":"2026-07-05T11:18:23.102300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20925","citing_title":"Unsupervised Learning of Inter-Object Relationships via Group Homomorphism","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/25CUZAWOU3HCE3Y5KHHKALQUUH","json":"https://pith.science/pith/25CUZAWOU3HCE3Y5KHHKALQUUH.json","graph_json":"https://pith.science/api/pith-number/25CUZAWOU3HCE3Y5KHHKALQUUH/graph.json","events_json":"https://pith.science/api/pith-number/25CUZAWOU3HCE3Y5KHHKALQUUH/events.json","paper":"https://pith.science/paper/25CUZAWO"},"agent_actions":{"view_html":"https://pith.science/pith/25CUZAWOU3HCE3Y5KHHKALQUUH","download_json":"https://pith.science/pith/25CUZAWOU3HCE3Y5KHHKALQUUH.json","view_paper":"https://pith.science/paper/25CUZAWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04668&json=true","fetch_graph":"https://pith.science/api/pith-number/25CUZAWOU3HCE3Y5KHHKALQUUH/graph.json","fetch_events":"https://pith.science/api/pith-number/25CUZAWOU3HCE3Y5KHHKALQUUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25CUZAWOU3HCE3Y5KHHKALQUUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25CUZAWOU3HCE3Y5KHHKALQUUH/action/storage_attestation","attest_author":"https://pith.science/pith/25CUZAWOU3HCE3Y5KHHKALQUUH/action/author_attestation","sign_citation":"https://pith.science/pith/25CUZAWOU3HCE3Y5KHHKALQUUH/action/citation_signature","submit_replication":"https://pith.science/pith/25CUZAWOU3HCE3Y5KHHKALQUUH/action/replication_record"}},"created_at":"2026-07-05T11:18:23.102300+00:00","updated_at":"2026-07-05T11:18:23.102300+00:00"}