{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KESZMUKDFJS2RRXTBLFM6BTGN4","short_pith_number":"pith:KESZMUKD","schema_version":"1.0","canonical_sha256":"51259651432a65a8c6f30acacf06666f2652073d150ae9ebfeb3b8ba931cdb1b","source":{"kind":"arxiv","id":"2306.12198","version":1},"attestation_state":"computed","paper":{"title":"Opening the Black Box: Analyzing Attention Weights and Hidden States in Pre-trained Language Models for Non-language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Gunther Heidemann, Kai-Uwe K\\\"uhnberger, Mohamad Ballout, Ulf Krumnack","submitted_at":"2023-06-21T11:48:07Z","abstract_excerpt":"Investigating deep learning language models has always been a significant research area due to the ``black box\" nature of most advanced models. With the recent advancements in pre-trained language models based on transformers and their increasing integration into daily life, addressing this issue has become more pressing. In order to achieve an explainable AI model, it is essential to comprehend the procedural steps involved and compare them with human thought processes. Thus, in this paper, we use simple, well-understood non-language tasks to explore these models' inner workings. Specifically"},"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":"2306.12198","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-21T11:48:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b58cc8c074badb1a6eca0daf30e0b67bcd159ec38f9a604872f96d8ec02751ac","abstract_canon_sha256":"ae250506c3e516dc35c35beb59864563486b73951f478376f6d2aa85395ad85b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:11.683303Z","signature_b64":"VVZ1SGRqZ2prHo9ELgOPhc3zydfphKstcAzo35jzfVgQ0h+SxEhhV6bwordn9rMQr6Sl2wCrTJIUhYk23Z3TCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51259651432a65a8c6f30acacf06666f2652073d150ae9ebfeb3b8ba931cdb1b","last_reissued_at":"2026-07-05T06:23:11.682964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:11.682964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Opening the Black Box: Analyzing Attention Weights and Hidden States in Pre-trained Language Models for Non-language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Gunther Heidemann, Kai-Uwe K\\\"uhnberger, Mohamad Ballout, Ulf Krumnack","submitted_at":"2023-06-21T11:48:07Z","abstract_excerpt":"Investigating deep learning language models has always been a significant research area due to the ``black box\" nature of most advanced models. With the recent advancements in pre-trained language models based on transformers and their increasing integration into daily life, addressing this issue has become more pressing. In order to achieve an explainable AI model, it is essential to comprehend the procedural steps involved and compare them with human thought processes. Thus, in this paper, we use simple, well-understood non-language tasks to explore these models' inner workings. Specifically"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12198","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/2306.12198/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":"2306.12198","created_at":"2026-07-05T06:23:11.683018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.12198v1","created_at":"2026-07-05T06:23:11.683018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12198","created_at":"2026-07-05T06:23:11.683018+00:00"},{"alias_kind":"pith_short_12","alias_value":"KESZMUKDFJS2","created_at":"2026-07-05T06:23:11.683018+00:00"},{"alias_kind":"pith_short_16","alias_value":"KESZMUKDFJS2RRXT","created_at":"2026-07-05T06:23:11.683018+00:00"},{"alias_kind":"pith_short_8","alias_value":"KESZMUKD","created_at":"2026-07-05T06:23:11.683018+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/KESZMUKDFJS2RRXTBLFM6BTGN4","json":"https://pith.science/pith/KESZMUKDFJS2RRXTBLFM6BTGN4.json","graph_json":"https://pith.science/api/pith-number/KESZMUKDFJS2RRXTBLFM6BTGN4/graph.json","events_json":"https://pith.science/api/pith-number/KESZMUKDFJS2RRXTBLFM6BTGN4/events.json","paper":"https://pith.science/paper/KESZMUKD"},"agent_actions":{"view_html":"https://pith.science/pith/KESZMUKDFJS2RRXTBLFM6BTGN4","download_json":"https://pith.science/pith/KESZMUKDFJS2RRXTBLFM6BTGN4.json","view_paper":"https://pith.science/paper/KESZMUKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.12198&json=true","fetch_graph":"https://pith.science/api/pith-number/KESZMUKDFJS2RRXTBLFM6BTGN4/graph.json","fetch_events":"https://pith.science/api/pith-number/KESZMUKDFJS2RRXTBLFM6BTGN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KESZMUKDFJS2RRXTBLFM6BTGN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KESZMUKDFJS2RRXTBLFM6BTGN4/action/storage_attestation","attest_author":"https://pith.science/pith/KESZMUKDFJS2RRXTBLFM6BTGN4/action/author_attestation","sign_citation":"https://pith.science/pith/KESZMUKDFJS2RRXTBLFM6BTGN4/action/citation_signature","submit_replication":"https://pith.science/pith/KESZMUKDFJS2RRXTBLFM6BTGN4/action/replication_record"}},"created_at":"2026-07-05T06:23:11.683018+00:00","updated_at":"2026-07-05T06:23:11.683018+00:00"}