{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y7PEQKMHKLOCTMP33G6GWIUHBI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5083f84523e83898d81be11d187eeeea0a18d59f97c94b3094ea835812021a2c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-29T17:06:54Z","title_canon_sha256":"6cd57045873082b291747d2fee2c1e62415bcb4957e503ed982cbb0ef2819a2b"},"schema_version":"1.0","source":{"id":"2601.21996","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21996","created_at":"2026-06-09T01:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21996v2","created_at":"2026-06-09T01:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21996","created_at":"2026-06-09T01:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"Y7PEQKMHKLOC","created_at":"2026-06-09T01:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"Y7PEQKMHKLOCTMP3","created_at":"2026-06-09T01:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"Y7PEQKMH","created_at":"2026-06-09T01:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:654d8b1f0501079cf67cec0587ed8d6f6031d0f33a1adbc5cc52f6ebe078647c","target":"graph","created_at":"2026-06-09T01:05:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.21996/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Mechanistic Interpretability has identified interpretable circuits in LLMs, their causal origins in training data remain elusive. We introduce Mechanistic Data Attribution (MDA), a scalable framework that employs Influence Functions to trace interpretable units back to specific training samples. Through extensive experiments on the Pythia family, we causally validate that targeted intervention--removing or augmenting a small fraction of high-influence samples--significantly modulates the emergence of interpretable heads, whereas random interventions show no effect. Our analysis reveals t","authors_text":"Jianhui Chen, Liangming Pan, Yuzhang Luo","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-29T17:06:54Z","title":"Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21996","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:adc5f6ab128f9d2a95bc57c16f8026f17fd1dce3eb03f4642528a99204580f0c","target":"record","created_at":"2026-06-09T01:05:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5083f84523e83898d81be11d187eeeea0a18d59f97c94b3094ea835812021a2c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-29T17:06:54Z","title_canon_sha256":"6cd57045873082b291747d2fee2c1e62415bcb4957e503ed982cbb0ef2819a2b"},"schema_version":"1.0","source":{"id":"2601.21996","kind":"arxiv","version":2}},"canonical_sha256":"c7de48298752dc29b1fbd9bc6b22870a2241731ff3b1747595d16029d522d007","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7de48298752dc29b1fbd9bc6b22870a2241731ff3b1747595d16029d522d007","first_computed_at":"2026-06-09T01:05:13.442071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:13.442071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XBH9hE+eJT24gGxERyIU087EeVqAGDFxSprbsQ/rSqPGUdZQspAanPrm3tp2C+QYEo9N4w+tfT5i94nH9GakBA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:13.442606Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.21996","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adc5f6ab128f9d2a95bc57c16f8026f17fd1dce3eb03f4642528a99204580f0c","sha256:654d8b1f0501079cf67cec0587ed8d6f6031d0f33a1adbc5cc52f6ebe078647c"],"state_sha256":"7a4733db037c3d07f9d2511e97129f57fc1e2389b2aad0d26eb35427745d678b"}