{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CKWL7ZDS2ZXJWSBN4VUU5MZRIF","short_pith_number":"pith:CKWL7ZDS","canonical_record":{"source":{"id":"2502.14458","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-20T11:18:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"499b69e1616b348e3ec865f1cf13ad427827e0f1eade0e3802164b20c007981e","abstract_canon_sha256":"6cdc2cb7d205d50f312133f2d29c2e5d2984d2f0cb5c8affb6edbab9bae380e0"},"schema_version":"1.0"},"canonical_sha256":"12acbfe472d66e9b482de5694eb331415f79becf7938268e643af78eb131b2af","source":{"kind":"arxiv","id":"2502.14458","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14458","created_at":"2026-07-05T10:18:51Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14458v2","created_at":"2026-07-05T10:18:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14458","created_at":"2026-07-05T10:18:51Z"},{"alias_kind":"pith_short_12","alias_value":"CKWL7ZDS2ZXJ","created_at":"2026-07-05T10:18:51Z"},{"alias_kind":"pith_short_16","alias_value":"CKWL7ZDS2ZXJWSBN","created_at":"2026-07-05T10:18:51Z"},{"alias_kind":"pith_short_8","alias_value":"CKWL7ZDS","created_at":"2026-07-05T10:18:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CKWL7ZDS2ZXJWSBN4VUU5MZRIF","target":"record","payload":{"canonical_record":{"source":{"id":"2502.14458","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-20T11:18:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"499b69e1616b348e3ec865f1cf13ad427827e0f1eade0e3802164b20c007981e","abstract_canon_sha256":"6cdc2cb7d205d50f312133f2d29c2e5d2984d2f0cb5c8affb6edbab9bae380e0"},"schema_version":"1.0"},"canonical_sha256":"12acbfe472d66e9b482de5694eb331415f79becf7938268e643af78eb131b2af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:51.274212Z","signature_b64":"xNXIoEGKZdMybHx+Q+tVk+2d2OhHdIzlX9YZAtMbsSDy7qyqvW3BrkAnVQeYrjdMX6LG7HgJ+mxdV/UaerN0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12acbfe472d66e9b482de5694eb331415f79becf7938268e643af78eb131b2af","last_reissued_at":"2026-07-05T10:18:51.273705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:51.273705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.14458","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AzX2lbGelc1iSZVV+pkhMze/o6pHx+HcvSvAmqPdg7wL/BueexS7nZ4DBRBgMflqC7h6+tV5+QIf5fdItM9jDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T00:26:21.624610Z"},"content_sha256":"8ed105edf9d5889ada898c9e7e5186c11b4564f68eaad51c7c26fe60ceddfa1a","schema_version":"1.0","event_id":"sha256:8ed105edf9d5889ada898c9e7e5186c11b4564f68eaad51c7c26fe60ceddfa1a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CKWL7ZDS2ZXJWSBN4VUU5MZRIF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Llamba: Scaling Distilled Recurrent Models for Efficient Language Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Albert Gu, Arjun Desai, Aviv Bick, Nimit Sohoni, Tobias Katsch","submitted_at":"2025-02-20T11:18:39Z","abstract_excerpt":"We introduce Llamba, a family of efficient recurrent language models distilled from Llama-3.x into the Mamba architecture. The series includes Llamba-1B, Llamba-3B, and Llamba-8B, which achieve higher inference throughput and handle significantly larger batch sizes than Transformer-based models while maintaining comparable benchmark performance. Furthermore, Llamba demonstrates the effectiveness of cross-architecture distillation using MOHAWK (Bick et al., 2024), achieving these results with less than 0.1% of the training data typically used for models of similar size. To take full advantage o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14458","kind":"arxiv","version":2},"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/2502.14458/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":"2026-07-05T10:18:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dt/t+ikqT0nfb6wkS9MaehTzR1OhDBF4VnTBN7LZYyrQLkkF5QvjGt+UQGIcOUxmKTNGCzK/gPusAn3CXRKYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T00:26:21.625341Z"},"content_sha256":"4f668b0e3807a597a735efe41f7a678de3b24554b1703558c98652449b894b53","schema_version":"1.0","event_id":"sha256:4f668b0e3807a597a735efe41f7a678de3b24554b1703558c98652449b894b53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CKWL7ZDS2ZXJWSBN4VUU5MZRIF/bundle.json","state_url":"https://pith.science/pith/CKWL7ZDS2ZXJWSBN4VUU5MZRIF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CKWL7ZDS2ZXJWSBN4VUU5MZRIF/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":"2026-07-13T00:26:21Z","links":{"resolver":"https://pith.science/pith/CKWL7ZDS2ZXJWSBN4VUU5MZRIF","bundle":"https://pith.science/pith/CKWL7ZDS2ZXJWSBN4VUU5MZRIF/bundle.json","state":"https://pith.science/pith/CKWL7ZDS2ZXJWSBN4VUU5MZRIF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CKWL7ZDS2ZXJWSBN4VUU5MZRIF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CKWL7ZDS2ZXJWSBN4VUU5MZRIF","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":"6cdc2cb7d205d50f312133f2d29c2e5d2984d2f0cb5c8affb6edbab9bae380e0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-20T11:18:39Z","title_canon_sha256":"499b69e1616b348e3ec865f1cf13ad427827e0f1eade0e3802164b20c007981e"},"schema_version":"1.0","source":{"id":"2502.14458","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14458","created_at":"2026-07-05T10:18:51Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14458v2","created_at":"2026-07-05T10:18:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14458","created_at":"2026-07-05T10:18:51Z"},{"alias_kind":"pith_short_12","alias_value":"CKWL7ZDS2ZXJ","created_at":"2026-07-05T10:18:51Z"},{"alias_kind":"pith_short_16","alias_value":"CKWL7ZDS2ZXJWSBN","created_at":"2026-07-05T10:18:51Z"},{"alias_kind":"pith_short_8","alias_value":"CKWL7ZDS","created_at":"2026-07-05T10:18:51Z"}],"graph_snapshots":[{"event_id":"sha256:4f668b0e3807a597a735efe41f7a678de3b24554b1703558c98652449b894b53","target":"graph","created_at":"2026-07-05T10:18:51Z","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/2502.14458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Llamba, a family of efficient recurrent language models distilled from Llama-3.x into the Mamba architecture. The series includes Llamba-1B, Llamba-3B, and Llamba-8B, which achieve higher inference throughput and handle significantly larger batch sizes than Transformer-based models while maintaining comparable benchmark performance. Furthermore, Llamba demonstrates the effectiveness of cross-architecture distillation using MOHAWK (Bick et al., 2024), achieving these results with less than 0.1% of the training data typically used for models of similar size. To take full advantage o","authors_text":"Albert Gu, Arjun Desai, Aviv Bick, Nimit Sohoni, Tobias Katsch","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-20T11:18:39Z","title":"Llamba: Scaling Distilled Recurrent Models for Efficient Language Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14458","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":"sha256:8ed105edf9d5889ada898c9e7e5186c11b4564f68eaad51c7c26fe60ceddfa1a","target":"record","created_at":"2026-07-05T10:18:51Z","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":"6cdc2cb7d205d50f312133f2d29c2e5d2984d2f0cb5c8affb6edbab9bae380e0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-20T11:18:39Z","title_canon_sha256":"499b69e1616b348e3ec865f1cf13ad427827e0f1eade0e3802164b20c007981e"},"schema_version":"1.0","source":{"id":"2502.14458","kind":"arxiv","version":2}},"canonical_sha256":"12acbfe472d66e9b482de5694eb331415f79becf7938268e643af78eb131b2af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12acbfe472d66e9b482de5694eb331415f79becf7938268e643af78eb131b2af","first_computed_at":"2026-07-05T10:18:51.273705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:51.273705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xNXIoEGKZdMybHx+Q+tVk+2d2OhHdIzlX9YZAtMbsSDy7qyqvW3BrkAnVQeYrjdMX6LG7HgJ+mxdV/UaerN0BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:51.274212Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14458","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ed105edf9d5889ada898c9e7e5186c11b4564f68eaad51c7c26fe60ceddfa1a","sha256:4f668b0e3807a597a735efe41f7a678de3b24554b1703558c98652449b894b53"],"state_sha256":"443b50854017f4faa2b3177e09b3b3e758b65fe51e6111321c5d970425ac8964"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PdVbLeaboutNlPRTeGC3uar5x8ZZx7po6Ezi2h1haibEqBBRul8CvqEToTwEUo4hG+MxuDAAMv8wvid7nhzHDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T00:26:21.629876Z","bundle_sha256":"441f3e08ade99e9742889140bb7684ae87670a7d15bc89a2c627e5c88c6f814b"}}