{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:236CKP5X4OV3E2T5CCVZRW7RP2","short_pith_number":"pith:236CKP5X","schema_version":"1.0","canonical_sha256":"d6fc253fb7e3abb26a7d10ab98dbf17e93a5045ecdc35de1b4d2b4cf8d5adf9d","source":{"kind":"arxiv","id":"2406.01352","version":2},"attestation_state":"computed","paper":{"title":"Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.NC"],"primary_cat":"cs.AI","authors_text":"David Poeppel, Federico Adolfi, Gemma Roig, Martina G. Vilas","submitted_at":"2024-06-03T14:16:56Z","abstract_excerpt":"Inner Interpretability is a promising emerging field tasked with uncovering the inner mechanisms of AI systems, though how to develop these mechanistic theories is still much debated. Moreover, recent critiques raise issues that question its usefulness to advance the broader goals of AI. However, it has been overlooked that these issues resemble those that have been grappled with in another field: Cognitive Neuroscience. Here we draw the relevant connections and highlight lessons that can be transferred productively between fields. Based on these, we propose a general conceptual framework and "},"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":"2406.01352","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-03T14:16:56Z","cross_cats_sorted":["cs.LG","q-bio.NC"],"title_canon_sha256":"952378a239793d8a99463ff8244a6f3758a0abc970a5e29c887f3e66f824dab1","abstract_canon_sha256":"7b4d2cc4253735d4dae125272c96489b9a4bd0a6531bcf624d7b2823a9ad6b76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:29.875168Z","signature_b64":"0tDLm32foVkHU3x/qSO3pJOBmxYovsj9euUgXexWb8uaUgvDCvWYxXkRQyEco//gbGxaIs7++lQuKykH2v//Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6fc253fb7e3abb26a7d10ab98dbf17e93a5045ecdc35de1b4d2b4cf8d5adf9d","last_reissued_at":"2026-07-05T08:50:29.874691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:29.874691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.NC"],"primary_cat":"cs.AI","authors_text":"David Poeppel, Federico Adolfi, Gemma Roig, Martina G. Vilas","submitted_at":"2024-06-03T14:16:56Z","abstract_excerpt":"Inner Interpretability is a promising emerging field tasked with uncovering the inner mechanisms of AI systems, though how to develop these mechanistic theories is still much debated. Moreover, recent critiques raise issues that question its usefulness to advance the broader goals of AI. However, it has been overlooked that these issues resemble those that have been grappled with in another field: Cognitive Neuroscience. Here we draw the relevant connections and highlight lessons that can be transferred productively between fields. Based on these, we propose a general conceptual framework and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01352","kind":"arxiv","version":2},"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/2406.01352/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":"2406.01352","created_at":"2026-07-05T08:50:29.874746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01352v2","created_at":"2026-07-05T08:50:29.874746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01352","created_at":"2026-07-05T08:50:29.874746+00:00"},{"alias_kind":"pith_short_12","alias_value":"236CKP5X4OV3","created_at":"2026-07-05T08:50:29.874746+00:00"},{"alias_kind":"pith_short_16","alias_value":"236CKP5X4OV3E2T5","created_at":"2026-07-05T08:50:29.874746+00:00"},{"alias_kind":"pith_short_8","alias_value":"236CKP5X","created_at":"2026-07-05T08:50:29.874746+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24731","citing_title":"Circuit Stability Characterizes Language Model Generalization","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/236CKP5X4OV3E2T5CCVZRW7RP2","json":"https://pith.science/pith/236CKP5X4OV3E2T5CCVZRW7RP2.json","graph_json":"https://pith.science/api/pith-number/236CKP5X4OV3E2T5CCVZRW7RP2/graph.json","events_json":"https://pith.science/api/pith-number/236CKP5X4OV3E2T5CCVZRW7RP2/events.json","paper":"https://pith.science/paper/236CKP5X"},"agent_actions":{"view_html":"https://pith.science/pith/236CKP5X4OV3E2T5CCVZRW7RP2","download_json":"https://pith.science/pith/236CKP5X4OV3E2T5CCVZRW7RP2.json","view_paper":"https://pith.science/paper/236CKP5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01352&json=true","fetch_graph":"https://pith.science/api/pith-number/236CKP5X4OV3E2T5CCVZRW7RP2/graph.json","fetch_events":"https://pith.science/api/pith-number/236CKP5X4OV3E2T5CCVZRW7RP2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/236CKP5X4OV3E2T5CCVZRW7RP2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/236CKP5X4OV3E2T5CCVZRW7RP2/action/storage_attestation","attest_author":"https://pith.science/pith/236CKP5X4OV3E2T5CCVZRW7RP2/action/author_attestation","sign_citation":"https://pith.science/pith/236CKP5X4OV3E2T5CCVZRW7RP2/action/citation_signature","submit_replication":"https://pith.science/pith/236CKP5X4OV3E2T5CCVZRW7RP2/action/replication_record"}},"created_at":"2026-07-05T08:50:29.874746+00:00","updated_at":"2026-07-05T08:50:29.874746+00:00"}