{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XSEYM7GXMPUOQTO7VRPSFG5RGK","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2daaf69549900073b90201ecc3e04e9ed72ca8440e64efdbf5d710c0e8aed5d3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T22:06:19Z","title_canon_sha256":"34b3faf6d729c068e174cd2e13269eea47a8aae162d2157bded2f7bc657b75a0"},"schema_version":"1.0","source":{"id":"2606.19625","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19625","created_at":"2026-06-19T16:12:30Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19625v1","created_at":"2026-06-19T16:12:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19625","created_at":"2026-06-19T16:12:30Z"},{"alias_kind":"pith_short_12","alias_value":"XSEYM7GXMPUO","created_at":"2026-06-19T16:12:30Z"},{"alias_kind":"pith_short_16","alias_value":"XSEYM7GXMPUOQTO7","created_at":"2026-06-19T16:12:30Z"},{"alias_kind":"pith_short_8","alias_value":"XSEYM7GX","created_at":"2026-06-19T16:12:30Z"}],"graph_snapshots":[{"event_id":"sha256:f49d951336f27b544fd84791c2eb3a6bf99e63e42766cad2bcca9ee80daf8078","target":"graph","created_at":"2026-06-19T16:12:30Z","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/2606.19625/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We use training-data attribution as an interpretable tool for capability discovery, mapping which regions of the pretraining corpus support social-reasoning versus STEM-reasoning in OLMo3-7B. Training-data attribution measures how strongly each training document influences a model's predictions on a benchmark, but document-level scores are too noisy to identify which corpus regions support which capabilities, and prior work has emphasized factual knowledge rather than reasoning. We compute gradient-based attribution (TrackStar via Bergson) over a working set drawn from the de-duplicated Dolma3","authors_text":"Alvin Deng, Chandreyi Chakraborty, Glenn Matlin, Louis Jaburi, Lucia Quirke, Mark Riedl, Mika Okamoto, Rayan Castilla, Saehee Eom, Stella Biderman, Taywon Min","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T22:06:19Z","title":"Where Does Social Reasoning Come From? Capability Provenance in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19625","kind":"arxiv","version":1},"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":"sha256:9c7a79b2593c6e03b1024ad74312fa68bd4832d1f70828de6a6452d135c0d5f6","target":"record","created_at":"2026-06-19T16:12:30Z","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":"2daaf69549900073b90201ecc3e04e9ed72ca8440e64efdbf5d710c0e8aed5d3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T22:06:19Z","title_canon_sha256":"34b3faf6d729c068e174cd2e13269eea47a8aae162d2157bded2f7bc657b75a0"},"schema_version":"1.0","source":{"id":"2606.19625","kind":"arxiv","version":1}},"canonical_sha256":"bc89867cd763e8e84ddfac5f229bb132bdf3c9f0801c300cffdda4b97c96aada","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc89867cd763e8e84ddfac5f229bb132bdf3c9f0801c300cffdda4b97c96aada","first_computed_at":"2026-06-19T16:12:30.629717Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:30.629717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1md33XJfZGWhDQL/u/Y06crFJYixGyQEx+BCrofRcUQ+B9Wj+GVuIMnWDSOCAe0ChNT+UeKPRbjlkbHLZkOjDQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:30.630109Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19625","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c7a79b2593c6e03b1024ad74312fa68bd4832d1f70828de6a6452d135c0d5f6","sha256:f49d951336f27b544fd84791c2eb3a6bf99e63e42766cad2bcca9ee80daf8078","sha256:15e3fc02039d7319ae395b636fcf06328e7d2358da4ff41d038821a7eb354277"],"state_sha256":"9927591f4d16ce911984e13a943d54927a82d6e1eeb6a6001676e9a180789051"}