{"_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_87e38167abaa11982de1877e9a0a31f3dcbeeefde2911f594d6f7957911f2507","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_87e38167abaa11982de1877e9a0a31f3dcbeeefde2911f594d6f7957911f2507","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"fe2685e823d54a0ad1aa6f6aba91ba2e83626d91bcfc97e7bef9d7efb704e420","published":"Tue, 21 Jul 2026 00:00:00 -0400","receipt_hash":"fe2685e823d54a0ad1aa6f6aba91ba2e83626d91bcfc97e7bef9d7efb704e420","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":"fe2685e823d54a0ad1aa6f6aba91ba2e83626d91bcfc97e7bef9d7efb704e420","observed_at":"2026-07-21T04:43:35.036805Z","parent_run_hash":"03e944014de2697434479833d15ea9303e014945afc230ecc7f207824493b589","published":"Tue, 21 Jul 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:2607.14905v2 Announce Type: replace-cross \nAbstract: Given the current trend to employ large language models (LLMs) in almost any imaginable context, LLM-generated text detection and authorship attribution have become a pressing issue. Prior work has primarily focused on surface-level linguistic features, an approach shown to be susceptible to paraphrasing and other obfuscation techniques. In this paper, we go beyond the linguistic surface, extracting and analysing reasoning structures in LLM-generated texts with the goal of capturing more complex signals of LLM authorship. We propose a graph neural network approach that leverages reasoning graphs extracted by an argument mining pipeline, demonstrating improved robustness and generalisation over a traditional Longformer baseline. Our approach outperforms the baseline by up to 27 percentage points under the obfuscation attacks such as paraphrasing and backtranslation, and 19 percentage points when evaluated on the texts generated ","title":"Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution","url":"https://arxiv.org/abs/2607.14905","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.14905v2 Announce Type: replace-cross \nAbstract: Given the current trend to employ large language models (LLMs) in almost any imaginable context, LLM-generated text detection and authorship attribution have become a pressing issue. Prior work has primarily focused on surface-level linguistic features, an approach shown to be susceptible to paraphrasing and other obfuscation techniques. In this paper, we go beyond the linguistic surface, extracting and analysing reasoning structures in LLM-generated texts with the goal of capturing more complex signals of LLM authorship. We propose a graph neural network approach that leverages reasoning graphs extracted by an argument mining pipeline, demonstrating improved robustness and generalisation over a traditional Longformer baseline. Our approach outperforms the baseline by up to 27 percentage points under the obfuscation attacks such as paraphrasing and backtranslation, and 19 percentage points when evaluated on the texts generated ","title":"Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-21T04:43:35Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.14905"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:93ac148d1620bb1834d7a078a829d07fbc9f548c8106c7780abeb2b8975462158c17a3475405dc0b4942e8184d14aeca101dcc60ea17edaef60d36fdf3f9dd02","signer":"crovia.substrate","subject":{"observed_at":"2026-07-21T04:43:35Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.14905"},"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":"9726e49dcfc54d69a2a5a5adcf14913f42171f1ce08b4ca7c2e6d0a4d27c3fb9","leaf_index":337024,"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":"c35ab0bfd9922de825e7a9c663acdd4ef81d23eb6a4a13c9ec18fe082054fcd2","side":"right"},{"sibling":"cb19a618544dc7d785aadf4bd08f0bfe87f57c1d2c4a98b3dad685baf24fd6fa","side":"right"},{"sibling":"93950eb8d20c10e8189b17f96bcd7c776877794ecc9f4a755b99fc145aeed8b6","side":"right"},{"sibling":"82fc4e123831919e8594eeb6b6dfceae7361cbff3447575bcf2dfb853433ff63","side":"right"},{"sibling":"a3a3c5939cd7fce5f56f815fa3f3c09a51a79194d21fce9526db8476b6d80443","side":"right"},{"sibling":"ed6f2ce33045c7ab27e0b72522dffa1fd31ce923e954d40b610306bf13df3bd3","side":"right"},{"sibling":"59945243e82094746cd1aa6ad86ef40e6f0d74fbf32f07d149cd990c0d4f9c87","side":"right"},{"sibling":"b6e06667a397121b2a21eae3090fea2e5d909fd87df785ea1048653e0cf48f07","side":"left"},{"sibling":"1298242aa509bc13b92160250ead2d95a721941ca6310e33b9eb0bf0821557d0","side":"right"},{"sibling":"61d44c6d16b87de577db53cff0dba2f003c50c036d92dc335120aa70124c8788","side":"right"},{"sibling":"5d0b792dbe69fd0a7cd8d79b467aa10204d1f25be602c06190f3423bc22727b8","side":"left"},{"sibling":"9eb5077edfb3dc553857d4794b925bfce117e0f8a1d049af5d0dd9026b470eef","side":"right"},{"sibling":"414b1a70fd1dcb25489a194714b97492b066684b15d0b7a48a176c4b9b5bc713","side":"right"},{"sibling":"21d66dd41003813f710b7617944f1bfba3258658a5d3370c21cad8f9e945bc99","side":"left"},{"sibling":"613f015699131eb89bd755dee67133be95af25cf5f16c1c8ce4b99d963b8dd86","side":"right"},{"sibling":"a729b574b1135956436ded5eef1fe8f08014ff6a0729749d307ab1bca93fcdc9","side":"right"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"4bf21052e085e8ac81f1dec1d2b310bd12bf948992de6177d12e9d2fda8d39f0","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":337144,"merkle_root":"5e969cc01afa67e4dbe5d37b712cdb10f4aa1fd74404e02eab724cf487c8d6d9","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260721T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-21T05:38:38Z","sig_algorithm":"ed25519","signature":"5c0c1a8dd2793d787ccd5e49e8b4d70eed136352555518589f05c74be357fc171702e42a76c3a556d90e3d51ff36cb3d292aaac83c66566de7b943f318bda50c","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_87e38167abaa11982de1877e9a0a31f3dcbeeefde2911f594d6f7957911f2507"}}