{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FMARRVA3ORHKC6XX6XM3EXRS2C","short_pith_number":"pith:FMARRVA3","schema_version":"1.0","canonical_sha256":"2b0118d41b744ea17af7f5d9b25e32d08a8cc67261e83a1c5b30d276dbae4ca5","source":{"kind":"arxiv","id":"2305.15001","version":3},"attestation_state":"computed","paper":{"title":"Contrastive Training of Complex-Valued Autoencoders for Object Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Aleksandar Stani\\'c, Anand Gopalakrishnan, J\\\"urgen Schmidhuber, Kazuki Irie","submitted_at":"2023-05-24T10:37:43Z","abstract_excerpt":"Current state-of-the-art object-centric models use slots and attention-based routing for binding. However, this class of models has several conceptual limitations: the number of slots is hardwired; all slots have equal capacity; training has high computational cost; there are no object-level relational factors within slots. Synchrony-based models in principle can address these limitations by using complex-valued activations which store binding information in their phase components. However, working examples of such synchrony-based models have been developed only very recently, and are still li"},"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":"2305.15001","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-24T10:37:43Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"b63b7bc65faeef397f4722d731be3c07556c17115b9cc4fefd351ff93ac5ceeb","abstract_canon_sha256":"1a4ed9450e0c4e65c28d8a3f055d0448d8d9a60969580d698bf6ba89d7852e03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:48.045892Z","signature_b64":"dxldw1lSukoVJql0XyBauT2T1SowBmL6TisYStaa0EM6qpOLdP8aC5ZvCKmeeIrBXALkM/AqiG4TxZoI3NiXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b0118d41b744ea17af7f5d9b25e32d08a8cc67261e83a1c5b30d276dbae4ca5","last_reissued_at":"2026-07-05T07:10:48.045421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:48.045421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Training of Complex-Valued Autoencoders for Object Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Aleksandar Stani\\'c, Anand Gopalakrishnan, J\\\"urgen Schmidhuber, Kazuki Irie","submitted_at":"2023-05-24T10:37:43Z","abstract_excerpt":"Current state-of-the-art object-centric models use slots and attention-based routing for binding. However, this class of models has several conceptual limitations: the number of slots is hardwired; all slots have equal capacity; training has high computational cost; there are no object-level relational factors within slots. Synchrony-based models in principle can address these limitations by using complex-valued activations which store binding information in their phase components. However, working examples of such synchrony-based models have been developed only very recently, and are still li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15001","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/2305.15001/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":"2305.15001","created_at":"2026-07-05T07:10:48.045478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15001v3","created_at":"2026-07-05T07:10:48.045478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15001","created_at":"2026-07-05T07:10:48.045478+00:00"},{"alias_kind":"pith_short_12","alias_value":"FMARRVA3ORHK","created_at":"2026-07-05T07:10:48.045478+00:00"},{"alias_kind":"pith_short_16","alias_value":"FMARRVA3ORHKC6XX","created_at":"2026-07-05T07:10:48.045478+00:00"},{"alias_kind":"pith_short_8","alias_value":"FMARRVA3","created_at":"2026-07-05T07:10:48.045478+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03531","citing_title":"Multimodal Alignment with Cross-Attentive GRUs for Fine-Grained Video Understanding","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FMARRVA3ORHKC6XX6XM3EXRS2C","json":"https://pith.science/pith/FMARRVA3ORHKC6XX6XM3EXRS2C.json","graph_json":"https://pith.science/api/pith-number/FMARRVA3ORHKC6XX6XM3EXRS2C/graph.json","events_json":"https://pith.science/api/pith-number/FMARRVA3ORHKC6XX6XM3EXRS2C/events.json","paper":"https://pith.science/paper/FMARRVA3"},"agent_actions":{"view_html":"https://pith.science/pith/FMARRVA3ORHKC6XX6XM3EXRS2C","download_json":"https://pith.science/pith/FMARRVA3ORHKC6XX6XM3EXRS2C.json","view_paper":"https://pith.science/paper/FMARRVA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15001&json=true","fetch_graph":"https://pith.science/api/pith-number/FMARRVA3ORHKC6XX6XM3EXRS2C/graph.json","fetch_events":"https://pith.science/api/pith-number/FMARRVA3ORHKC6XX6XM3EXRS2C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FMARRVA3ORHKC6XX6XM3EXRS2C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FMARRVA3ORHKC6XX6XM3EXRS2C/action/storage_attestation","attest_author":"https://pith.science/pith/FMARRVA3ORHKC6XX6XM3EXRS2C/action/author_attestation","sign_citation":"https://pith.science/pith/FMARRVA3ORHKC6XX6XM3EXRS2C/action/citation_signature","submit_replication":"https://pith.science/pith/FMARRVA3ORHKC6XX6XM3EXRS2C/action/replication_record"}},"created_at":"2026-07-05T07:10:48.045478+00:00","updated_at":"2026-07-05T07:10:48.045478+00:00"}