{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EHSOLIZB7VBX5LWCWMLSSZZSME","short_pith_number":"pith:EHSOLIZB","schema_version":"1.0","canonical_sha256":"21e4e5a321fd437eaec2b3172967326116daa6ff7b74770b214bedb8a4d64b9b","source":{"kind":"arxiv","id":"2606.10794","version":1},"attestation_state":"computed","paper":{"title":"READER: Robust Evidence-based Authorship Decoding via Extracted Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dong Huang, Jiaxu Liu, Jie Zhang, Jing Shao, Liuyin Wang, Sunnan Mu","submitted_at":"2026-06-09T12:43:49Z","abstract_excerpt":"As agentic applications increasingly route user tasks through official and third-party LLM APIs, provenance becomes an operational question: which model generated a given black-box response? We study Dynamic Black-Box LLM Provenance: identifying the source LLM from generations elicited by query-varying, non-predefined prompts rather than a fixed input set or benchmark suite. This setting is difficult because prompt semantics dominate the text, while model-specific authorship traces are weak and inconsistent at the surface level. We introduce READER (Robust Evidence-based Authorship Decoding vi"},"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":"2606.10794","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T12:43:49Z","cross_cats_sorted":[],"title_canon_sha256":"db667cffcb58d66b7975398cc606abba77cac58149a6bb24af6f2be4f1540b24","abstract_canon_sha256":"f0ecf51ed0cf8d44cd2190b1d29e4dc88d0a2b84c512b142a41307435c806732"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:40.957472Z","signature_b64":"nvvx5ue1WnLtflP/4tiyQxDjUPqyaAWfHswxi3roZphzOeCV5+gUv8s2TRpiBBBBF9MjOzDx3p8Qr5jP7rmKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21e4e5a321fd437eaec2b3172967326116daa6ff7b74770b214bedb8a4d64b9b","last_reissued_at":"2026-06-10T01:10:40.956607Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:40.956607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"READER: Robust Evidence-based Authorship Decoding via Extracted Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dong Huang, Jiaxu Liu, Jie Zhang, Jing Shao, Liuyin Wang, Sunnan Mu","submitted_at":"2026-06-09T12:43:49Z","abstract_excerpt":"As agentic applications increasingly route user tasks through official and third-party LLM APIs, provenance becomes an operational question: which model generated a given black-box response? We study Dynamic Black-Box LLM Provenance: identifying the source LLM from generations elicited by query-varying, non-predefined prompts rather than a fixed input set or benchmark suite. This setting is difficult because prompt semantics dominate the text, while model-specific authorship traces are weak and inconsistent at the surface level. We introduce READER (Robust Evidence-based Authorship Decoding vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10794","kind":"arxiv","version":1},"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/2606.10794/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":"2606.10794","created_at":"2026-06-10T01:10:40.956739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10794v1","created_at":"2026-06-10T01:10:40.956739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10794","created_at":"2026-06-10T01:10:40.956739+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHSOLIZB7VBX","created_at":"2026-06-10T01:10:40.956739+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHSOLIZB7VBX5LWC","created_at":"2026-06-10T01:10:40.956739+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHSOLIZB","created_at":"2026-06-10T01:10:40.956739+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/EHSOLIZB7VBX5LWCWMLSSZZSME","json":"https://pith.science/pith/EHSOLIZB7VBX5LWCWMLSSZZSME.json","graph_json":"https://pith.science/api/pith-number/EHSOLIZB7VBX5LWCWMLSSZZSME/graph.json","events_json":"https://pith.science/api/pith-number/EHSOLIZB7VBX5LWCWMLSSZZSME/events.json","paper":"https://pith.science/paper/EHSOLIZB"},"agent_actions":{"view_html":"https://pith.science/pith/EHSOLIZB7VBX5LWCWMLSSZZSME","download_json":"https://pith.science/pith/EHSOLIZB7VBX5LWCWMLSSZZSME.json","view_paper":"https://pith.science/paper/EHSOLIZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10794&json=true","fetch_graph":"https://pith.science/api/pith-number/EHSOLIZB7VBX5LWCWMLSSZZSME/graph.json","fetch_events":"https://pith.science/api/pith-number/EHSOLIZB7VBX5LWCWMLSSZZSME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHSOLIZB7VBX5LWCWMLSSZZSME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHSOLIZB7VBX5LWCWMLSSZZSME/action/storage_attestation","attest_author":"https://pith.science/pith/EHSOLIZB7VBX5LWCWMLSSZZSME/action/author_attestation","sign_citation":"https://pith.science/pith/EHSOLIZB7VBX5LWCWMLSSZZSME/action/citation_signature","submit_replication":"https://pith.science/pith/EHSOLIZB7VBX5LWCWMLSSZZSME/action/replication_record"}},"created_at":"2026-06-10T01:10:40.956739+00:00","updated_at":"2026-06-10T01:10:40.956739+00:00"}