{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7HWYMRYO5GE5P5VBI5OYQNZHD2","short_pith_number":"pith:7HWYMRYO","schema_version":"1.0","canonical_sha256":"f9ed86470ee989d7f6a1475d8837271eb3c076d1ccb2bae023ba98c11c1b4d27","source":{"kind":"arxiv","id":"2405.17283","version":3},"attestation_state":"computed","paper":{"title":"Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Aleksandar Stani\\'c, Anand Gopalakrishnan, J\\\"urgen Schmidhuber, Michael Curtis Mozer","submitted_at":"2024-05-27T15:47:03Z","abstract_excerpt":"Current state-of-the-art synchrony-based models encode object bindings with complex-valued activations and compute with real-valued weights in feedforward architectures. We argue for the computational advantages of a recurrent architecture with complex-valued weights. We propose a fully convolutional autoencoder, SynCx, that performs iterative constraint satisfaction: at each iteration, a hidden layer bottleneck encodes statistically regular configurations of features in particular phase relationships; over iterations, local constraints propagate and the model converges to a globally consisten"},"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":"2405.17283","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T15:47:03Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"d24a6fdcfbd25fe054f01f0e4f8d6dad1243bb483638c267b243d41d11955fba","abstract_canon_sha256":"72a21ceda63f903bdfcf84730a62f8f3b5d85c2640c71c1cd819ed5a9da7106b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:01.178984Z","signature_b64":"IjIG888bJp5+BbgTW9aen6nPQQFrkWdxX8qqkwf3IkBbVj42c0k+BVrctPaw90AKv2eE8OMx67pxTS2bQE2BCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9ed86470ee989d7f6a1475d8837271eb3c076d1ccb2bae023ba98c11c1b4d27","last_reissued_at":"2026-07-05T09:27:01.178528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:01.178528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Aleksandar Stani\\'c, Anand Gopalakrishnan, J\\\"urgen Schmidhuber, Michael Curtis Mozer","submitted_at":"2024-05-27T15:47:03Z","abstract_excerpt":"Current state-of-the-art synchrony-based models encode object bindings with complex-valued activations and compute with real-valued weights in feedforward architectures. We argue for the computational advantages of a recurrent architecture with complex-valued weights. We propose a fully convolutional autoencoder, SynCx, that performs iterative constraint satisfaction: at each iteration, a hidden layer bottleneck encodes statistically regular configurations of features in particular phase relationships; over iterations, local constraints propagate and the model converges to a globally consisten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17283","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/2405.17283/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":"2405.17283","created_at":"2026-07-05T09:27:01.178579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17283v3","created_at":"2026-07-05T09:27:01.178579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17283","created_at":"2026-07-05T09:27:01.178579+00:00"},{"alias_kind":"pith_short_12","alias_value":"7HWYMRYO5GE5","created_at":"2026-07-05T09:27:01.178579+00:00"},{"alias_kind":"pith_short_16","alias_value":"7HWYMRYO5GE5P5VB","created_at":"2026-07-05T09:27:01.178579+00:00"},{"alias_kind":"pith_short_8","alias_value":"7HWYMRYO","created_at":"2026-07-05T09:27:01.178579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16674","citing_title":"GASPnet: Global Agreement to Synchronize Phases","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7HWYMRYO5GE5P5VBI5OYQNZHD2","json":"https://pith.science/pith/7HWYMRYO5GE5P5VBI5OYQNZHD2.json","graph_json":"https://pith.science/api/pith-number/7HWYMRYO5GE5P5VBI5OYQNZHD2/graph.json","events_json":"https://pith.science/api/pith-number/7HWYMRYO5GE5P5VBI5OYQNZHD2/events.json","paper":"https://pith.science/paper/7HWYMRYO"},"agent_actions":{"view_html":"https://pith.science/pith/7HWYMRYO5GE5P5VBI5OYQNZHD2","download_json":"https://pith.science/pith/7HWYMRYO5GE5P5VBI5OYQNZHD2.json","view_paper":"https://pith.science/paper/7HWYMRYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17283&json=true","fetch_graph":"https://pith.science/api/pith-number/7HWYMRYO5GE5P5VBI5OYQNZHD2/graph.json","fetch_events":"https://pith.science/api/pith-number/7HWYMRYO5GE5P5VBI5OYQNZHD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7HWYMRYO5GE5P5VBI5OYQNZHD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7HWYMRYO5GE5P5VBI5OYQNZHD2/action/storage_attestation","attest_author":"https://pith.science/pith/7HWYMRYO5GE5P5VBI5OYQNZHD2/action/author_attestation","sign_citation":"https://pith.science/pith/7HWYMRYO5GE5P5VBI5OYQNZHD2/action/citation_signature","submit_replication":"https://pith.science/pith/7HWYMRYO5GE5P5VBI5OYQNZHD2/action/replication_record"}},"created_at":"2026-07-05T09:27:01.178579+00:00","updated_at":"2026-07-05T09:27:01.178579+00:00"}