{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:Q2TKKCDKRHVKRJWDONHTBCS6SK","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":"2e6ea1754fd06e00258ead336f77e6cbfc0de6a4fc32d7f0273776e35561bc89","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-13T02:32:19Z","title_canon_sha256":"98dfc9ed6f47cc8c3fc187f3fec26fb284e9dabb3ee3312a1246aa1bd64e3a0c"},"schema_version":"1.0","source":{"id":"2103.07601","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.07601","created_at":"2026-07-05T03:24:28Z"},{"alias_kind":"arxiv_version","alias_value":"2103.07601v3","created_at":"2026-07-05T03:24:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.07601","created_at":"2026-07-05T03:24:28Z"},{"alias_kind":"pith_short_12","alias_value":"Q2TKKCDKRHVK","created_at":"2026-07-05T03:24:28Z"},{"alias_kind":"pith_short_16","alias_value":"Q2TKKCDKRHVKRJWD","created_at":"2026-07-05T03:24:28Z"},{"alias_kind":"pith_short_8","alias_value":"Q2TKKCDK","created_at":"2026-07-05T03:24:28Z"}],"graph_snapshots":[{"event_id":"sha256:78e5b016cfb223de5c3874d8b4cae1bdbf781cdbbc1758637dcdf87f73861f2c","target":"graph","created_at":"2026-07-05T03:24:28Z","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/2103.07601/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Why do models often attend to salient words, and how does this evolve throughout training? We approximate model training as a two stage process: early on in training when the attention weights are uniform, the model learns to translate individual input word `i` to `o` if they co-occur frequently. Later, the model learns to attend to `i` while the correct output is $o$ because it knows `i` translates to `o`. To formalize, we define a model property, Knowledge to Translate Individual Words (KTIW) (e.g. knowing that `i` translates to `o`), and claim that it drives the learning of the attention. T","authors_text":"Charlie Snell, Dan Klein, Jacob Steinhardt, Ruiqi Zhong","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-13T02:32:19Z","title":"Approximating How Single Head Attention Learns"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.07601","kind":"arxiv","version":3},"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":"sha256:49798f5d8cb4e5bc5ba3ccd4ddbd7e72b850a5ccaa4c3e1e98b0652e58d9ae9b","target":"record","created_at":"2026-07-05T03:24:28Z","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":"2e6ea1754fd06e00258ead336f77e6cbfc0de6a4fc32d7f0273776e35561bc89","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-13T02:32:19Z","title_canon_sha256":"98dfc9ed6f47cc8c3fc187f3fec26fb284e9dabb3ee3312a1246aa1bd64e3a0c"},"schema_version":"1.0","source":{"id":"2103.07601","kind":"arxiv","version":3}},"canonical_sha256":"86a6a5086a89eaa8a6c3734f308a5e9296af1cc1348c4f37a5b321646270b9b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86a6a5086a89eaa8a6c3734f308a5e9296af1cc1348c4f37a5b321646270b9b7","first_computed_at":"2026-07-05T03:24:28.701302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:24:28.701302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FcPCkbCkn/jfyZMdORRgwj+039qxsTAh3ONU0dL6rs67mVJdRuWBFLz47w56H7CYtQt6XvhB3DzSJeFMzThhBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:24:28.701849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.07601","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49798f5d8cb4e5bc5ba3ccd4ddbd7e72b850a5ccaa4c3e1e98b0652e58d9ae9b","sha256:78e5b016cfb223de5c3874d8b4cae1bdbf781cdbbc1758637dcdf87f73861f2c"],"state_sha256":"ed15e27b150f2d1949fa892ff56b17310fdf9f3b57c8ce1c22b08b3a7deb1625"}