{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_9590b5fbb03c02c4942883a1df4916dd361eca2775c948c0a3321e99f3041ea6","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_9590b5fbb03c02c4942883a1df4916dd361eca2775c948c0a3321e99f3041ea6","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"77717251c766ca8f8444a843b3991e2220b1abae98af7c05761c2b0735975d4e","published":"Tue, 30 Jun 2026 00:00:00 -0400","receipt_hash":"77717251c766ca8f8444a843b3991e2220b1abae98af7c05761c2b0735975d4e","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"77717251c766ca8f8444a843b3991e2220b1abae98af7c05761c2b0735975d4e","observed_at":"2026-06-30T04:43:04.087680Z","parent_run_hash":"74f7ab392cc702044101fe24a76a2fdad11164cd79ce725aad6c446a477e89c5","published":"Tue, 30 Jun 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2606.30609v1 Announce Type: cross \nAbstract: Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features, but scaling to large dictionaries exposes fundamental challenges. Systematic studies reveal pervasive feature splitting that fragments coherent concepts into non-atomic latents and widespread feature absorption that creates arbitrary exceptions in general features, severely compromising latent reliability. These issues stem from inconsistent latent assignment across samples: without cross-sample constraints, per-sample optimization often allows a single underlying concept to be inconsistently distributed across multiple redundant or interfering latents. To address this, we introduce C$^2$R (\\underline{\\textbf{C}}ross-sample \\underline{\\textbf{C}}onsistency \\underline{\\textbf{R}}egularization). C$^2$R explicitly encourages that each semantic feature is consistently represented by a unified ","title":"C$^{2}$R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders","url":"https://arxiv.org/abs/2606.30609","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.30609v1 Announce Type: cross \nAbstract: Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features, but scaling to large dictionaries exposes fundamental challenges. Systematic studies reveal pervasive feature splitting that fragments coherent concepts into non-atomic latents and widespread feature absorption that creates arbitrary exceptions in general features, severely compromising latent reliability. These issues stem from inconsistent latent assignment across samples: without cross-sample constraints, per-sample optimization often allows a single underlying concept to be inconsistently distributed across multiple redundant or interfering latents. To address this, we introduce C$^2$R (\\underline{\\textbf{C}}ross-sample \\underline{\\textbf{C}}onsistency \\underline{\\textbf{R}}egularization). C$^2$R explicitly encourages that each semantic feature is consistently represented by a unified ","title":"C$^{2}$R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-30T04:43:04Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.30609"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:bfc62ecd426fa1050d7143edacdf59e720bb43a79beb9591d24ea9b34247e78aea117cbb36482b55ba1bb238fc5b3503ca0e65492f245e6eec252bd63cf5270d","signer":"crovia.substrate","subject":{"observed_at":"2026-06-30T04:43:04Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.30609"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"1f110019a42e12e2fadd0e7748b1ea7210d208d3e398b4154f079979cd346871","leaf_index":265032,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"03feebb43c8e30b54c5d85eff37a09b3ff6b1994e1cfc7ac5d9a460335f3e42e","side":"right"},{"sibling":"45f1fd6e481a930d812b445cb96f14e82d1f114cac7ee0455ccb123a0f4c95bb","side":"right"},{"sibling":"712050da73506a2378045d99a893d701e5f90b702ac95fdab3ecb2a317c77c5b","side":"right"},{"sibling":"56ddfc750828425540ea79bedcf80245980ced6e42921e44bf734c5170076301","side":"left"},{"sibling":"80b2c038f2b521f28290fbce9fde21d0413e79f42a830c25d82739cb1e2e8610","side":"right"},{"sibling":"dc3a8a976dd0fb0b2dd04e514aa7cd1d06945d1036beb7fd4d0026c9c22682cb","side":"right"},{"sibling":"5b8a0910e4e94e2a9b10497e13f92efba841a089742fa095b3d09b024957b4bc","side":"left"},{"sibling":"e3ac74800103452465231dd60eaf9671a5039238ce21e35760b324bd56f70d4e","side":"right"},{"sibling":"3f337e26f1a0c4c64b8b7ebac04427325a7e7838c802c162576de1cd617b91ce","side":"left"},{"sibling":"1549a8883ab3267f958dc2624919e40c65c82958b8005967ed6a4da1247da0ad","side":"left"},{"sibling":"23994bf0974e5c9c7f63a61b4f0a48b0ca756a4adc34a8f85f878e774c37dfbe","side":"right"},{"sibling":"f9b4bed84fa6990c71ad2887c91bda183001f05f6b648f21d1273045a26b11fd","side":"left"},{"sibling":"173d2dc4b29ee04ea41d6d0ebc334c4bc2d46e7ee4230c94765413f24fb4bc42","side":"right"},{"sibling":"112461f7c0ec411116fb5c6c90fe95cea9d8f188b9fe08afe25a837ac02d0071","side":"right"},{"sibling":"ea9488204352c49db8f7daf05eefcd7628ecf9413830346674801a99d0654a94","side":"right"},{"sibling":"6261c13b9922cb657f10d1e5d36ec15d8771cf8766e36c61dcbffb7bed57e396","side":"right"},{"sibling":"fa19aa3faf287618b820bcfceebb366152ad521dd20ef9f51e977816663e448b","side":"right"},{"sibling":"c32f943406b62d1fc59b7f7e243492174c8e1caba8c8a2705f86c773315736e0","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":265374,"merkle_root":"9636001ecab173cb6af10dc7c71eb14585daa62f9c0a6f027046f05633156891","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260630T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-30T05:38:03Z","sig_algorithm":"ed25519","signature":"6d4b8fd9b9da856cbb5fba7540877c6a63fa18a5ec3eaf28dc4d6d1c64921c9c0565f8c95f4b7aec0e7744fd7754844f051baf863db708cad768765b416a7b0c","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_9590b5fbb03c02c4942883a1df4916dd361eca2775c948c0a3321e99f3041ea6"}}