{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7PVSFTIB6DIXC5G6N5VBXOEETB","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":"d6437428277a3ebd15638091d995d0f923118ae7624a1d4c2f23cc08a751ade8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-05T08:13:09Z","title_canon_sha256":"71dea8aba5b9039ea5394c4d000350dbb30b9158b4b73e74b1b8b1a1c2253811"},"schema_version":"1.0","source":{"id":"2112.02505","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.02505","created_at":"2026-07-05T04:28:53Z"},{"alias_kind":"arxiv_version","alias_value":"2112.02505v2","created_at":"2026-07-05T04:28:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02505","created_at":"2026-07-05T04:28:53Z"},{"alias_kind":"pith_short_12","alias_value":"7PVSFTIB6DIX","created_at":"2026-07-05T04:28:53Z"},{"alias_kind":"pith_short_16","alias_value":"7PVSFTIB6DIXC5G6","created_at":"2026-07-05T04:28:53Z"},{"alias_kind":"pith_short_8","alias_value":"7PVSFTIB","created_at":"2026-07-05T04:28:53Z"}],"graph_snapshots":[{"event_id":"sha256:420d23dc46bdfaba52ea7efc446d1ad2848359698590e6909f21a50062e5eb36","target":"graph","created_at":"2026-07-05T04:28:53Z","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/2112.02505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distillation efforts have led to language models that are more compact and efficient without serious drops in performance. The standard approach to distillation trains a student model against two objectives: a task-specific objective (e.g., language modeling) and an imitation objective that encourages the hidden states of the student model to be similar to those of the larger teacher model. In this paper, we show that it is beneficial to augment distillation with a third objective that encourages the student to imitate the causal computation process of the teacher through interchange intervent","authors_text":"Atticus Geiger, Christopher Potts, Elisa Kreiss, Hanson Lu, Josh Rozner, Noah D. Goodman, Thomas Icard, Zhengxuan Wu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-05T08:13:09Z","title":"Causal Distillation for Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02505","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:eb41940fee15ed5f2556e827e12ba0c48c3e377be8a1f368267ec6dffb55baad","target":"record","created_at":"2026-07-05T04:28:53Z","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":"d6437428277a3ebd15638091d995d0f923118ae7624a1d4c2f23cc08a751ade8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-05T08:13:09Z","title_canon_sha256":"71dea8aba5b9039ea5394c4d000350dbb30b9158b4b73e74b1b8b1a1c2253811"},"schema_version":"1.0","source":{"id":"2112.02505","kind":"arxiv","version":2}},"canonical_sha256":"fbeb22cd01f0d17174de6f6a1bb884985615779ed11f24f3e927a9cb3a38026d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbeb22cd01f0d17174de6f6a1bb884985615779ed11f24f3e927a9cb3a38026d","first_computed_at":"2026-07-05T04:28:53.787767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:28:53.787767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E8j+l1Tp9TfCu07ml70c9HVqYF7S2VX9UseU82anRsF5xz0jRyJovFbG/u5N6aV58KAj/X6IaA2wfRlEKAmxBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:28:53.788230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.02505","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb41940fee15ed5f2556e827e12ba0c48c3e377be8a1f368267ec6dffb55baad","sha256:420d23dc46bdfaba52ea7efc446d1ad2848359698590e6909f21a50062e5eb36"],"state_sha256":"4d865d746a8fff96e7724eaa1eca30de5247d54ae4c3635780e10912dd569323"}