{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4PV4OE5QZMTF7HINWQHP7OEGKR","short_pith_number":"pith:4PV4OE5Q","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"},"canonical_sha256":"e3ebc713b0cb265f9d0db40effb8865479a477637e1c330ca76f96dc244af79a","source":{"kind":"arxiv","id":"2604.10639","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.10639","created_at":"2026-06-11T01:10:35Z"},{"alias_kind":"arxiv_version","alias_value":"2604.10639v2","created_at":"2026-06-11T01:10:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.10639","created_at":"2026-06-11T01:10:35Z"},{"alias_kind":"pith_short_12","alias_value":"4PV4OE5QZMTF","created_at":"2026-06-11T01:10:35Z"},{"alias_kind":"pith_short_16","alias_value":"4PV4OE5QZMTF7HIN","created_at":"2026-06-11T01:10:35Z"},{"alias_kind":"pith_short_8","alias_value":"4PV4OE5Q","created_at":"2026-06-11T01:10:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4PV4OE5QZMTF7HINWQHP7OEGKR","target":"record","payload":{"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"},"canonical_sha256":"e3ebc713b0cb265f9d0db40effb8865479a477637e1c330ca76f96dc244af79a","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"},"source_kind":"arxiv","source_id":"2604.10639","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-11T01:10:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Aw2QJyA0zoIFJFnZfwRSR62vwyVlNt9jz7NAGj8BLNRGK2U0NUeJoMsmd4E9mh+fP/H4G+2AInbYegpFxSagDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T04:34:14.981110Z"},"content_sha256":"7163d0150c10843f78ee66eb69400025892aa83ec9d37c12cb9140cca4f7f9eb","schema_version":"1.0","event_id":"sha256:7163d0150c10843f78ee66eb69400025892aa83ec9d37c12cb9140cca4f7f9eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4PV4OE5QZMTF7HINWQHP7OEGKR","target":"graph","payload":{"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"},"verdict_id":"faeef505-c98c-496f-8d0c-529c041240b0"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-11T01:10:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"03PoGIwraBKL2S11smAQBpO/4n2t8QRq+Rn5SghaDu6E9WFaTlwuI5cJHar3+iKci4bHBnIHF4Mr+yrJJ9aFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T04:34:14.981574Z"},"content_sha256":"c40e129aad9bdc18102d1ef9fa6cde2f90f879c6b4ca8da558cd715316934009","schema_version":"1.0","event_id":"sha256:c40e129aad9bdc18102d1ef9fa6cde2f90f879c6b4ca8da558cd715316934009"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4PV4OE5QZMTF7HINWQHP7OEGKR/bundle.json","state_url":"https://pith.science/pith/4PV4OE5QZMTF7HINWQHP7OEGKR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4PV4OE5QZMTF7HINWQHP7OEGKR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-27T04:34:14Z","links":{"resolver":"https://pith.science/pith/4PV4OE5QZMTF7HINWQHP7OEGKR","bundle":"https://pith.science/pith/4PV4OE5QZMTF7HINWQHP7OEGKR/bundle.json","state":"https://pith.science/pith/4PV4OE5QZMTF7HINWQHP7OEGKR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4PV4OE5QZMTF7HINWQHP7OEGKR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4PV4OE5QZMTF7HINWQHP7OEGKR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5b3e78e1d313b9a712c9a174f40e6769652b5b2c3df54502da262e0983b0b674","cross_cats_sorted":["cs.ET"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.NE","submitted_at":"2026-04-12T13:39:17Z","title_canon_sha256":"cfbcfdb0193add918aaaed68c3fee93648f9c0f75e0ab9a4a40956aac7938876"},"schema_version":"1.0","source":{"id":"2604.10639","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.10639","created_at":"2026-06-11T01:10:35Z"},{"alias_kind":"arxiv_version","alias_value":"2604.10639v2","created_at":"2026-06-11T01:10:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.10639","created_at":"2026-06-11T01:10:35Z"},{"alias_kind":"pith_short_12","alias_value":"4PV4OE5QZMTF","created_at":"2026-06-11T01:10:35Z"},{"alias_kind":"pith_short_16","alias_value":"4PV4OE5QZMTF7HIN","created_at":"2026-06-11T01:10:35Z"},{"alias_kind":"pith_short_8","alias_value":"4PV4OE5Q","created_at":"2026-06-11T01:10:35Z"}],"graph_snapshots":[{"event_id":"sha256:c40e129aad9bdc18102d1ef9fa6cde2f90f879c6b4ca8da558cd715316934009","target":"graph","created_at":"2026-06-11T01:10:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Neural cellular automata often show simple behavioral manifolds at the full-state level but complex ones when broken down to individual cells."}],"snapshot_sha256":"b7e95c3122564da93caf90528dd272363339964b9641017e7102163b863aea59"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.10639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexander Mordvintsev, Harald Michael Ludwig, James Stovold, Mia-Katrin Kvalsund, Varun Sharma","cross_cats":["cs.ET"],"headline":"Neural cellular automata often show simple behavioral manifolds at the full-state level but complex ones when broken down to individual cells.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.NE","submitted_at":"2026-04-12T13:39:17Z","title":"Visualising the Attractor Landscape of Neural Cellular Automata"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.10639","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T15:48:36.700178Z","id":"faeef505-c98c-496f-8d0c-529c041240b0","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"faeef505-c98c-496f-8d0c-529c041240b0"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7163d0150c10843f78ee66eb69400025892aa83ec9d37c12cb9140cca4f7f9eb","target":"record","created_at":"2026-06-11T01:10:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5b3e78e1d313b9a712c9a174f40e6769652b5b2c3df54502da262e0983b0b674","cross_cats_sorted":["cs.ET"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.NE","submitted_at":"2026-04-12T13:39:17Z","title_canon_sha256":"cfbcfdb0193add918aaaed68c3fee93648f9c0f75e0ab9a4a40956aac7938876"},"schema_version":"1.0","source":{"id":"2604.10639","kind":"arxiv","version":2}},"canonical_sha256":"e3ebc713b0cb265f9d0db40effb8865479a477637e1c330ca76f96dc244af79a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3ebc713b0cb265f9d0db40effb8865479a477637e1c330ca76f96dc244af79a","first_computed_at":"2026-06-11T01:10:35.983644Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:10:35.983644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v31+YcCFvTHnGwdlH3CBJsYi28aGC1MePyw2F2SLRebf6WB2tApYy8eizsHZT18LPBmq72Fy3bzAaNHE7y36CQ==","signature_status":"signed_v1","signed_at":"2026-06-11T01:10:35.984639Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.10639","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7163d0150c10843f78ee66eb69400025892aa83ec9d37c12cb9140cca4f7f9eb","sha256:c40e129aad9bdc18102d1ef9fa6cde2f90f879c6b4ca8da558cd715316934009"],"state_sha256":"3ca14adf081e9fb13d59f44adceae72bb4f0724c1eaa9ab217a88c2aa9ab2772"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iHn/LX9FhMfG9bf8lfl5mcmBwyw0nVCz6MxuaYv2i7p39elC6RBDyBtEUlfjaUExfskb5LDRNDraEuTQTSInBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T04:34:14.983820Z","bundle_sha256":"6b8efae0c32793730d3821dc58e80a21fc7367d1fbdf43f998010cc8563c132c"}}