{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4PV4OE5QZMTF7HINWQHP7OEGKR","short_pith_number":"pith:4PV4OE5Q","schema_version":"1.0","canonical_sha256":"e3ebc713b0cb265f9d0db40effb8865479a477637e1c330ca76f96dc244af79a","source":{"kind":"arxiv","id":"2604.10639","version":2},"attestation_state":"computed","paper":{"title":"Visualising the Attractor Landscape of Neural Cellular Automata","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Neural cellular automata often show simple behavioral manifolds at the full-state level but complex ones when broken down to individual cells.","cross_cats":["cs.ET"],"primary_cat":"cs.NE","authors_text":"Alexander Mordvintsev, Harald Michael Ludwig, James Stovold, Mia-Katrin Kvalsund, Varun Sharma","submitted_at":"2026-04-12T13:39:17Z","abstract_excerpt":"As Neural Cellular Automata (NCAs) are increasingly applied outside of the toy models in Artificial Life, there is a pressing need to understand how they behave and to build appropriate routes to interpret what they have learnt. By their very nature, the benefits of training NCAs are balanced with a lack of interpretability: we can engineer emergent behaviour, but have limited ability to understand what has been learnt.\n  In this paper, we apply a variety of techniques to pry open the NCA black box and glean some understanding of what it has learnt to do. We apply techniques from manifold lear"},"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":"2604.10639","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.NE","submitted_at":"2026-04-12T13:39:17Z","cross_cats_sorted":["cs.ET"],"title_canon_sha256":"cfbcfdb0193add918aaaed68c3fee93648f9c0f75e0ab9a4a40956aac7938876","abstract_canon_sha256":"5b3e78e1d313b9a712c9a174f40e6769652b5b2c3df54502da262e0983b0b674"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:35.984639Z","signature_b64":"v31+YcCFvTHnGwdlH3CBJsYi28aGC1MePyw2F2SLRebf6WB2tApYy8eizsHZT18LPBmq72Fy3bzAaNHE7y36CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3ebc713b0cb265f9d0db40effb8865479a477637e1c330ca76f96dc244af79a","last_reissued_at":"2026-06-11T01:10:35.983644Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:35.983644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visualising the Attractor Landscape of Neural Cellular Automata","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Neural cellular automata often show simple behavioral manifolds at the full-state level but complex ones when broken down to individual cells.","cross_cats":["cs.ET"],"primary_cat":"cs.NE","authors_text":"Alexander Mordvintsev, Harald Michael Ludwig, James Stovold, Mia-Katrin Kvalsund, Varun Sharma","submitted_at":"2026-04-12T13:39:17Z","abstract_excerpt":"As Neural Cellular Automata (NCAs) are increasingly applied outside of the toy models in Artificial Life, there is a pressing need to understand how they behave and to build appropriate routes to interpret what they have learnt. By their very nature, the benefits of training NCAs are balanced with a lack of interpretability: we can engineer emergent behaviour, but have limited ability to understand what has been learnt.\n  In this paper, we apply a variety of techniques to pry open the NCA black box and glean some understanding of what it has learnt to do. We apply techniques from manifold lear"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"When analysis is performed at a macroscopic level (i.e. taking the entire NCA state as a single data point), the underlying manifold is often quite simple and can be captured and analysed quite well. When analysis is performed at a microscopic level (i.e. taking the state of individual cells as a single data point), the manifold is highly complex and more complicated techniques are required in order to make sense of it.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the chosen manifold learning and topological techniques faithfully recover the true behavioral manifold without significant distortion or loss of dynamics that matter for the NCA's function.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Neural Cellular Automata show simple attractor manifolds at the full-state level but complex ones at the individual-cell level when analyzed with PCA, autoencoders, and persistent homology.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Neural cellular automata often show simple behavioral manifolds at the full-state level but complex ones when broken down to individual cells.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b7e95c3122564da93caf90528dd272363339964b9641017e7102163b863aea59"},"source":{"id":"2604.10639","kind":"arxiv","version":2},"verdict":{"id":"faeef505-c98c-496f-8d0c-529c041240b0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:48:36.700178Z","strongest_claim":"When analysis is performed at a macroscopic level (i.e. taking the entire NCA state as a single data point), the underlying manifold is often quite simple and can be captured and analysed quite well. When analysis is performed at a microscopic level (i.e. taking the state of individual cells as a single data point), the manifold is highly complex and more complicated techniques are required in order to make sense of it.","one_line_summary":"Neural Cellular Automata show simple attractor manifolds at the full-state level but complex ones at the individual-cell level when analyzed with PCA, autoencoders, and persistent homology.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the chosen manifold learning and topological techniques faithfully recover the true behavioral manifold without significant distortion or loss of dynamics that matter for the NCA's function.","pith_extraction_headline":"Neural cellular automata often show simple behavioral manifolds at the full-state level but complex ones when broken down to individual cells."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.10639/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":"2604.10639","created_at":"2026-06-11T01:10:35.983781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.10639v2","created_at":"2026-06-11T01:10:35.983781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.10639","created_at":"2026-06-11T01:10:35.983781+00:00"},{"alias_kind":"pith_short_12","alias_value":"4PV4OE5QZMTF","created_at":"2026-06-11T01:10:35.983781+00:00"},{"alias_kind":"pith_short_16","alias_value":"4PV4OE5QZMTF7HIN","created_at":"2026-06-11T01:10:35.983781+00:00"},{"alias_kind":"pith_short_8","alias_value":"4PV4OE5Q","created_at":"2026-06-11T01:10:35.983781+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/4PV4OE5QZMTF7HINWQHP7OEGKR","json":"https://pith.science/pith/4PV4OE5QZMTF7HINWQHP7OEGKR.json","graph_json":"https://pith.science/api/pith-number/4PV4OE5QZMTF7HINWQHP7OEGKR/graph.json","events_json":"https://pith.science/api/pith-number/4PV4OE5QZMTF7HINWQHP7OEGKR/events.json","paper":"https://pith.science/paper/4PV4OE5Q"},"agent_actions":{"view_html":"https://pith.science/pith/4PV4OE5QZMTF7HINWQHP7OEGKR","download_json":"https://pith.science/pith/4PV4OE5QZMTF7HINWQHP7OEGKR.json","view_paper":"https://pith.science/paper/4PV4OE5Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.10639&json=true","fetch_graph":"https://pith.science/api/pith-number/4PV4OE5QZMTF7HINWQHP7OEGKR/graph.json","fetch_events":"https://pith.science/api/pith-number/4PV4OE5QZMTF7HINWQHP7OEGKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4PV4OE5QZMTF7HINWQHP7OEGKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4PV4OE5QZMTF7HINWQHP7OEGKR/action/storage_attestation","attest_author":"https://pith.science/pith/4PV4OE5QZMTF7HINWQHP7OEGKR/action/author_attestation","sign_citation":"https://pith.science/pith/4PV4OE5QZMTF7HINWQHP7OEGKR/action/citation_signature","submit_replication":"https://pith.science/pith/4PV4OE5QZMTF7HINWQHP7OEGKR/action/replication_record"}},"created_at":"2026-06-11T01:10:35.983781+00:00","updated_at":"2026-06-11T01:10:35.983781+00:00"}