{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TBQ5GCTTHR3UDZU7PHGC6RB24O","short_pith_number":"pith:TBQ5GCTT","schema_version":"1.0","canonical_sha256":"9861d30a733c7741e69f79cc2f443ae3a0060ac1d419f7339f5d60539bf2f955","source":{"kind":"arxiv","id":"2606.00016","version":1},"attestation_state":"computed","paper":{"title":"AEyeDE: An Attention-Based Attribution Framework for AI-Generated Text Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adelaide Danilov, Aria Nourbakhsh, Christoph Schommer, Salima Lamsiyah","submitted_at":"2026-04-13T19:30:40Z","abstract_excerpt":"Detecting AI-generated text is becoming increasingly challenging as modern language models approach human-level fluency and can evade detectors that rely on surface statistics or likelihood-based signals. We propose \\textsc{AEyeDE}, an attribution-driven approach to human-AI authorship detection that leverages model attention as a discriminative signal. Specifically, we extract attention-based attribution matrices for both human- and AI-generated text using a \\emph{proxy} Transformer model with white-box access and train a lightweight Convolutional Neural Network to learn representations from "},"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":"2606.00016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-13T19:30:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fd2cee41d21fd44180c12758c42de50e4dac68c31b63d61f2c9a678e7acaf10a","abstract_canon_sha256":"2d973d3e6e154e1dd76f4d56a2c592dd7775685f06be56b4c63a94efe58d3367"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T00:03:12.367610Z","signature_b64":"ipLrKBOfSekjxTN4NsvlLGamwaUVKZzTnWxjYU9RQ5s8sTe06Sf5ezEmXejtgxjBB+UIrV2mC2AfYYVrpLyuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9861d30a733c7741e69f79cc2f443ae3a0060ac1d419f7339f5d60539bf2f955","last_reissued_at":"2026-06-02T00:03:12.366952Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T00:03:12.366952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AEyeDE: An Attention-Based Attribution Framework for AI-Generated Text Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adelaide Danilov, Aria Nourbakhsh, Christoph Schommer, Salima Lamsiyah","submitted_at":"2026-04-13T19:30:40Z","abstract_excerpt":"Detecting AI-generated text is becoming increasingly challenging as modern language models approach human-level fluency and can evade detectors that rely on surface statistics or likelihood-based signals. We propose \\textsc{AEyeDE}, an attribution-driven approach to human-AI authorship detection that leverages model attention as a discriminative signal. Specifically, we extract attention-based attribution matrices for both human- and AI-generated text using a \\emph{proxy} Transformer model with white-box access and train a lightweight Convolutional Neural Network to learn representations from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00016","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/2606.00016/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":"2606.00016","created_at":"2026-06-02T00:03:12.367029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00016v1","created_at":"2026-06-02T00:03:12.367029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00016","created_at":"2026-06-02T00:03:12.367029+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBQ5GCTTHR3U","created_at":"2026-06-02T00:03:12.367029+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBQ5GCTTHR3UDZU7","created_at":"2026-06-02T00:03:12.367029+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBQ5GCTT","created_at":"2026-06-02T00:03:12.367029+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/TBQ5GCTTHR3UDZU7PHGC6RB24O","json":"https://pith.science/pith/TBQ5GCTTHR3UDZU7PHGC6RB24O.json","graph_json":"https://pith.science/api/pith-number/TBQ5GCTTHR3UDZU7PHGC6RB24O/graph.json","events_json":"https://pith.science/api/pith-number/TBQ5GCTTHR3UDZU7PHGC6RB24O/events.json","paper":"https://pith.science/paper/TBQ5GCTT"},"agent_actions":{"view_html":"https://pith.science/pith/TBQ5GCTTHR3UDZU7PHGC6RB24O","download_json":"https://pith.science/pith/TBQ5GCTTHR3UDZU7PHGC6RB24O.json","view_paper":"https://pith.science/paper/TBQ5GCTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00016&json=true","fetch_graph":"https://pith.science/api/pith-number/TBQ5GCTTHR3UDZU7PHGC6RB24O/graph.json","fetch_events":"https://pith.science/api/pith-number/TBQ5GCTTHR3UDZU7PHGC6RB24O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBQ5GCTTHR3UDZU7PHGC6RB24O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBQ5GCTTHR3UDZU7PHGC6RB24O/action/storage_attestation","attest_author":"https://pith.science/pith/TBQ5GCTTHR3UDZU7PHGC6RB24O/action/author_attestation","sign_citation":"https://pith.science/pith/TBQ5GCTTHR3UDZU7PHGC6RB24O/action/citation_signature","submit_replication":"https://pith.science/pith/TBQ5GCTTHR3UDZU7PHGC6RB24O/action/replication_record"}},"created_at":"2026-06-02T00:03:12.367029+00:00","updated_at":"2026-06-02T00:03:12.367029+00:00"}