{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DK4HEZEEIUG7IOJU24BRZIVAOO","short_pith_number":"pith:DK4HEZEE","canonical_record":{"source":{"id":"2407.16153","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-23T03:40:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fdf8e9f5fab4ceccf52f1bc309415b0f8c3ac38046cad165cfce25b3935f3f0f","abstract_canon_sha256":"612fff539d8de5119106717e3c00380bef78871bb4b4f022238063ea86e8d997"},"schema_version":"1.0"},"canonical_sha256":"1ab8726484450df43934d7031ca2a07382021543dc4f6514590aaf9d35894d94","source":{"kind":"arxiv","id":"2407.16153","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16153","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16153v1","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16153","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"pith_short_12","alias_value":"DK4HEZEEIUG7","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"pith_short_16","alias_value":"DK4HEZEEIUG7IOJU","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"pith_short_8","alias_value":"DK4HEZEE","created_at":"2026-07-05T08:47:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DK4HEZEEIUG7IOJU24BRZIVAOO","target":"record","payload":{"canonical_record":{"source":{"id":"2407.16153","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-23T03:40:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fdf8e9f5fab4ceccf52f1bc309415b0f8c3ac38046cad165cfce25b3935f3f0f","abstract_canon_sha256":"612fff539d8de5119106717e3c00380bef78871bb4b4f022238063ea86e8d997"},"schema_version":"1.0"},"canonical_sha256":"1ab8726484450df43934d7031ca2a07382021543dc4f6514590aaf9d35894d94","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:27.949041Z","signature_b64":"50/9VyZdJwW1xDZ9HngEJHMfoJQEKV7CP/E/uHK2lLxlhNYix/P6cEPLeZQXIwoD5oh6LLDNqxFqpfwTQfU/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ab8726484450df43934d7031ca2a07382021543dc4f6514590aaf9d35894d94","last_reissued_at":"2026-07-05T08:47:27.948634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:27.948634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.16153","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:47:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mE0r62Yle8UPmLqlmyy7BLBJOK8J5ZsU8FKYuA5i2o9nVfgdHC7NyR2Q5+E/O209kFUMxVu4s3X8DTo/aRT2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:46:55.637128Z"},"content_sha256":"ba1c0c3215acb8d8ab8aa063d6ebe6dc1887018c08e8e860bd7690fb2051bd3c","schema_version":"1.0","event_id":"sha256:ba1c0c3215acb8d8ab8aa063d6ebe6dc1887018c08e8e860bd7690fb2051bd3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DK4HEZEEIUG7IOJU24BRZIVAOO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Benefits of Rank in Attention Layers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gilad Yehudai, Joan Bruna, Noah Amsel","submitted_at":"2024-07-23T03:40:24Z","abstract_excerpt":"Attention-based mechanisms are widely used in machine learning, most prominently in transformers. However, hyperparameters such as the rank of the attention matrices and the number of heads are scaled nearly the same way in all realizations of this architecture, without theoretical justification. In this work we show that there are dramatic trade-offs between the rank and number of heads of the attention mechanism. Specifically, we present a simple and natural target function that can be represented using a single full-rank attention head for any context length, but that cannot be approximated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16153","kind":"arxiv","version":1},"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/2407.16153/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:47:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ABiONh1drow0NIpPHl/vTmCqQwP3CECaeQdb+WjAket6ZT/u8O7+Mq/NPRZKCro0cP994zo6IVizAU3u1iYiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:46:55.637683Z"},"content_sha256":"55ff3cab7a8ecdc464232d973124ce0f2d5271a350742665f74223b663ecb746","schema_version":"1.0","event_id":"sha256:55ff3cab7a8ecdc464232d973124ce0f2d5271a350742665f74223b663ecb746"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DK4HEZEEIUG7IOJU24BRZIVAOO/bundle.json","state_url":"https://pith.science/pith/DK4HEZEEIUG7IOJU24BRZIVAOO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DK4HEZEEIUG7IOJU24BRZIVAOO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T21:46:55Z","links":{"resolver":"https://pith.science/pith/DK4HEZEEIUG7IOJU24BRZIVAOO","bundle":"https://pith.science/pith/DK4HEZEEIUG7IOJU24BRZIVAOO/bundle.json","state":"https://pith.science/pith/DK4HEZEEIUG7IOJU24BRZIVAOO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DK4HEZEEIUG7IOJU24BRZIVAOO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DK4HEZEEIUG7IOJU24BRZIVAOO","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":"612fff539d8de5119106717e3c00380bef78871bb4b4f022238063ea86e8d997","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-23T03:40:24Z","title_canon_sha256":"fdf8e9f5fab4ceccf52f1bc309415b0f8c3ac38046cad165cfce25b3935f3f0f"},"schema_version":"1.0","source":{"id":"2407.16153","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16153","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16153v1","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16153","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"pith_short_12","alias_value":"DK4HEZEEIUG7","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"pith_short_16","alias_value":"DK4HEZEEIUG7IOJU","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"pith_short_8","alias_value":"DK4HEZEE","created_at":"2026-07-05T08:47:27Z"}],"graph_snapshots":[{"event_id":"sha256:55ff3cab7a8ecdc464232d973124ce0f2d5271a350742665f74223b663ecb746","target":"graph","created_at":"2026-07-05T08:47:27Z","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/2407.16153/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Attention-based mechanisms are widely used in machine learning, most prominently in transformers. However, hyperparameters such as the rank of the attention matrices and the number of heads are scaled nearly the same way in all realizations of this architecture, without theoretical justification. In this work we show that there are dramatic trade-offs between the rank and number of heads of the attention mechanism. Specifically, we present a simple and natural target function that can be represented using a single full-rank attention head for any context length, but that cannot be approximated","authors_text":"Gilad Yehudai, Joan Bruna, Noah Amsel","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-23T03:40:24Z","title":"On the Benefits of Rank in Attention Layers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16153","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:ba1c0c3215acb8d8ab8aa063d6ebe6dc1887018c08e8e860bd7690fb2051bd3c","target":"record","created_at":"2026-07-05T08:47:27Z","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":"612fff539d8de5119106717e3c00380bef78871bb4b4f022238063ea86e8d997","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-23T03:40:24Z","title_canon_sha256":"fdf8e9f5fab4ceccf52f1bc309415b0f8c3ac38046cad165cfce25b3935f3f0f"},"schema_version":"1.0","source":{"id":"2407.16153","kind":"arxiv","version":1}},"canonical_sha256":"1ab8726484450df43934d7031ca2a07382021543dc4f6514590aaf9d35894d94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ab8726484450df43934d7031ca2a07382021543dc4f6514590aaf9d35894d94","first_computed_at":"2026-07-05T08:47:27.948634Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:47:27.948634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"50/9VyZdJwW1xDZ9HngEJHMfoJQEKV7CP/E/uHK2lLxlhNYix/P6cEPLeZQXIwoD5oh6LLDNqxFqpfwTQfU/AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:47:27.949041Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.16153","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba1c0c3215acb8d8ab8aa063d6ebe6dc1887018c08e8e860bd7690fb2051bd3c","sha256:55ff3cab7a8ecdc464232d973124ce0f2d5271a350742665f74223b663ecb746"],"state_sha256":"f42ebbe436f03bf59139215e4cea85d1e40ba1c56d968accf837fbb03a07052c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QMfoY0WhRNVScLauB0KkMEpYJeW6P1GZAOlTRKvAoPkDcYwBLKwLHqCWUOsQsVQJ8i//96eCZ3OtrbsHIkA6BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:46:55.641481Z","bundle_sha256":"e5969738de89a7a62e8ce32ae710e66392d1d5daf9300d7138d9da4a49afce73"}}