{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7XGW6WXWN4KEI6HI6NBVVWDTGG","short_pith_number":"pith:7XGW6WXW","canonical_record":{"source":{"id":"2106.04426","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T14:54:24Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d101f2a10c16896dade654f80cf7b57ae78c3c9c7584ded00cec664dd13f1664","abstract_canon_sha256":"f5ed9ee3a1979dd3bf7b019fb3a5dd716ee5df4b29d223e0b5d8353e26337c05"},"schema_version":"1.0"},"canonical_sha256":"fdcd6f5af66f144478e8f3435ad8733195508099fd5a7cc46f0b0176e36593d7","source":{"kind":"arxiv","id":"2106.04426","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.04426","created_at":"2026-07-05T02:59:22Z"},{"alias_kind":"arxiv_version","alias_value":"2106.04426v3","created_at":"2026-07-05T02:59:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04426","created_at":"2026-07-05T02:59:22Z"},{"alias_kind":"pith_short_12","alias_value":"7XGW6WXWN4KE","created_at":"2026-07-05T02:59:22Z"},{"alias_kind":"pith_short_16","alias_value":"7XGW6WXWN4KEI6HI","created_at":"2026-07-05T02:59:22Z"},{"alias_kind":"pith_short_8","alias_value":"7XGW6WXW","created_at":"2026-07-05T02:59:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7XGW6WXWN4KEI6HI6NBVVWDTGG","target":"record","payload":{"canonical_record":{"source":{"id":"2106.04426","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T14:54:24Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d101f2a10c16896dade654f80cf7b57ae78c3c9c7584ded00cec664dd13f1664","abstract_canon_sha256":"f5ed9ee3a1979dd3bf7b019fb3a5dd716ee5df4b29d223e0b5d8353e26337c05"},"schema_version":"1.0"},"canonical_sha256":"fdcd6f5af66f144478e8f3435ad8733195508099fd5a7cc46f0b0176e36593d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:22.787147Z","signature_b64":"/d2vftAtSYbj1xfpBvZW1Ox5x61tAmNQ3lJydqbRWLFHMh+i71YPTzxhsUwcbmF5jQWnwUjuBT5tJqnM+YkQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdcd6f5af66f144478e8f3435ad8733195508099fd5a7cc46f0b0176e36593d7","last_reissued_at":"2026-07-05T02:59:22.786716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:22.786716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.04426","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:59:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yYbKVxzTN+7gD2w3gkSjQz0Ge/EWUgkXlxV3LNFEBSVXMv71cTsrDoW/PCx5GMfz5W0nF/bCKPS3kdbvqrJtAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:06:30.678404Z"},"content_sha256":"5396e68c9d2927ebe220f65da006a6aa0a01bb60304cf392dd12807c5cfa7c85","schema_version":"1.0","event_id":"sha256:5396e68c9d2927ebe220f65da006a6aa0a01bb60304cf392dd12807c5cfa7c85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7XGW6WXWN4KEI6HI6NBVVWDTGG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hash Layers For Large Sparse Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Arthur Szlam, Jason Weston, Sainbayar Sukhbaatar, Stephen Roller","submitted_at":"2021-06-08T14:54:24Z","abstract_excerpt":"We investigate the training of sparse layers that use different parameters for different inputs based on hashing in large Transformer models. Specifically, we modify the feedforward layer to hash to different sets of weights depending on the current token, over all tokens in the sequence. We show that this procedure either outperforms or is competitive with learning-to-route mixture-of-expert methods such as Switch Transformers and BASE Layers, while requiring no routing parameters or extra terms in the objective function such as a load balancing loss, and no sophisticated assignment algorithm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04426","kind":"arxiv","version":3},"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/2106.04426/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":"2026-07-05T02:59:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xjWauJRaHN+oukM1Sd7eia8+nrbpEnJvTPD/GOv+36uqxofrYzUlhV2Gy/X7ZmmVhdPQkcEJlzY7GLc+lqV1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:06:30.678913Z"},"content_sha256":"b234f6b4356a0aeb830957f1e63003cba4a377f0cb3553686bdb18bf234bb239","schema_version":"1.0","event_id":"sha256:b234f6b4356a0aeb830957f1e63003cba4a377f0cb3553686bdb18bf234bb239"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7XGW6WXWN4KEI6HI6NBVVWDTGG/bundle.json","state_url":"https://pith.science/pith/7XGW6WXWN4KEI6HI6NBVVWDTGG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7XGW6WXWN4KEI6HI6NBVVWDTGG/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":"2026-08-12T14:06:30Z","links":{"resolver":"https://pith.science/pith/7XGW6WXWN4KEI6HI6NBVVWDTGG","bundle":"https://pith.science/pith/7XGW6WXWN4KEI6HI6NBVVWDTGG/bundle.json","state":"https://pith.science/pith/7XGW6WXWN4KEI6HI6NBVVWDTGG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7XGW6WXWN4KEI6HI6NBVVWDTGG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7XGW6WXWN4KEI6HI6NBVVWDTGG","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":"f5ed9ee3a1979dd3bf7b019fb3a5dd716ee5df4b29d223e0b5d8353e26337c05","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T14:54:24Z","title_canon_sha256":"d101f2a10c16896dade654f80cf7b57ae78c3c9c7584ded00cec664dd13f1664"},"schema_version":"1.0","source":{"id":"2106.04426","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.04426","created_at":"2026-07-05T02:59:22Z"},{"alias_kind":"arxiv_version","alias_value":"2106.04426v3","created_at":"2026-07-05T02:59:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04426","created_at":"2026-07-05T02:59:22Z"},{"alias_kind":"pith_short_12","alias_value":"7XGW6WXWN4KE","created_at":"2026-07-05T02:59:22Z"},{"alias_kind":"pith_short_16","alias_value":"7XGW6WXWN4KEI6HI","created_at":"2026-07-05T02:59:22Z"},{"alias_kind":"pith_short_8","alias_value":"7XGW6WXW","created_at":"2026-07-05T02:59:22Z"}],"graph_snapshots":[{"event_id":"sha256:b234f6b4356a0aeb830957f1e63003cba4a377f0cb3553686bdb18bf234bb239","target":"graph","created_at":"2026-07-05T02:59:22Z","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/2106.04426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the training of sparse layers that use different parameters for different inputs based on hashing in large Transformer models. Specifically, we modify the feedforward layer to hash to different sets of weights depending on the current token, over all tokens in the sequence. We show that this procedure either outperforms or is competitive with learning-to-route mixture-of-expert methods such as Switch Transformers and BASE Layers, while requiring no routing parameters or extra terms in the objective function such as a load balancing loss, and no sophisticated assignment algorithm","authors_text":"Arthur Szlam, Jason Weston, Sainbayar Sukhbaatar, Stephen Roller","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T14:54:24Z","title":"Hash Layers For Large Sparse Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04426","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":"sha256:5396e68c9d2927ebe220f65da006a6aa0a01bb60304cf392dd12807c5cfa7c85","target":"record","created_at":"2026-07-05T02:59:22Z","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":"f5ed9ee3a1979dd3bf7b019fb3a5dd716ee5df4b29d223e0b5d8353e26337c05","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T14:54:24Z","title_canon_sha256":"d101f2a10c16896dade654f80cf7b57ae78c3c9c7584ded00cec664dd13f1664"},"schema_version":"1.0","source":{"id":"2106.04426","kind":"arxiv","version":3}},"canonical_sha256":"fdcd6f5af66f144478e8f3435ad8733195508099fd5a7cc46f0b0176e36593d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdcd6f5af66f144478e8f3435ad8733195508099fd5a7cc46f0b0176e36593d7","first_computed_at":"2026-07-05T02:59:22.786716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:59:22.786716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/d2vftAtSYbj1xfpBvZW1Ox5x61tAmNQ3lJydqbRWLFHMh+i71YPTzxhsUwcbmF5jQWnwUjuBT5tJqnM+YkQBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:59:22.787147Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.04426","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5396e68c9d2927ebe220f65da006a6aa0a01bb60304cf392dd12807c5cfa7c85","sha256:b234f6b4356a0aeb830957f1e63003cba4a377f0cb3553686bdb18bf234bb239"],"state_sha256":"1d5d54daf05a2b3825726a766efdb07d495ce0fc8f7b0e301d0907b480e1a8a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XLz8WhVvu6XIiMEC6QqwDLnIqGvDvrz21o9KrdEXZ6Eo311XdyulHNkY+gBqDwTNIHaqB5NKl4/JMmIW38eADQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T14:06:30.683653Z","bundle_sha256":"83245f49126f8531c7600a91958348e533142c3d6e65ed55c17bd9469a3e5d61"}}