{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DAQZWHZLK4F3TZNWBPO7UCREOQ","short_pith_number":"pith:DAQZWHZL","canonical_record":{"source":{"id":"2408.10189","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T17:48:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6426238307fdd96fa0a76d17e628ed893ab4de964f677d4b09da4cc4f3e2d677","abstract_canon_sha256":"f7fa038d62418447d24285240533171fd0b73b37ad80233f277384a9cd17020f"},"schema_version":"1.0"},"canonical_sha256":"18219b1f2b570bb9e5b60bddfa0a24741ab0ea339cff35547da0c65da2d2ce2e","source":{"kind":"arxiv","id":"2408.10189","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10189","created_at":"2026-07-05T10:11:23Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10189v2","created_at":"2026-07-05T10:11:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10189","created_at":"2026-07-05T10:11:23Z"},{"alias_kind":"pith_short_12","alias_value":"DAQZWHZLK4F3","created_at":"2026-07-05T10:11:23Z"},{"alias_kind":"pith_short_16","alias_value":"DAQZWHZLK4F3TZNW","created_at":"2026-07-05T10:11:23Z"},{"alias_kind":"pith_short_8","alias_value":"DAQZWHZL","created_at":"2026-07-05T10:11:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DAQZWHZLK4F3TZNWBPO7UCREOQ","target":"record","payload":{"canonical_record":{"source":{"id":"2408.10189","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T17:48:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6426238307fdd96fa0a76d17e628ed893ab4de964f677d4b09da4cc4f3e2d677","abstract_canon_sha256":"f7fa038d62418447d24285240533171fd0b73b37ad80233f277384a9cd17020f"},"schema_version":"1.0"},"canonical_sha256":"18219b1f2b570bb9e5b60bddfa0a24741ab0ea339cff35547da0c65da2d2ce2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:23.194706Z","signature_b64":"cZMm6okBjblu5XSGhVdm0QwZZwRm7LeJt5BxaFrPF9jZ1qjQlcTtVm2TJ1vaa+hVuZka3kt0w9cHNPmhRt43Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18219b1f2b570bb9e5b60bddfa0a24741ab0ea339cff35547da0c65da2d2ce2e","last_reissued_at":"2026-07-05T10:11:23.194199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:23.194199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.10189","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":"2026-07-05T10:11:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3puVqeZKpgPEYZ2T/SgfZ+a1Qw81EUx5QhX302J6BD6clHz6WiLO9FQZCosd3Ukf9O7bQHYvRm0DoziX2zR+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:11:56.706587Z"},"content_sha256":"77112a16d36d3619c8521fd9c10d472169383bdfab00d079086eafcbf1668c70","schema_version":"1.0","event_id":"sha256:77112a16d36d3619c8521fd9c10d472169383bdfab00d079086eafcbf1668c70"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DAQZWHZLK4F3TZNWBPO7UCREOQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Albert Gu, Aviv Bick, Eric P. Xing, J. Zico Kolter, Kevin Y. Li","submitted_at":"2024-08-19T17:48:11Z","abstract_excerpt":"Transformer architectures have become a dominant paradigm for domains like language modeling but suffer in many inference settings due to their quadratic-time self-attention. Recently proposed subquadratic architectures, such as Mamba, have shown promise, but have been pretrained with substantially less computational resources than the strongest Transformer models. In this work, we present a method that is able to distill a pretrained Transformer architecture into alternative architectures such as state space models (SSMs). The key idea to our approach is that we can view both Transformers and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10189","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/2408.10189/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":"2026-07-05T10:11:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dTjwmwI5nRC+r2Vh76Sp+X4yyvru0c8k7lhPJOurTSZK1DgB07D2AKxtEoutvbjpMXPbYQW32kqTufaz4mW7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:11:56.707532Z"},"content_sha256":"69a36addd5f91f33505dc78234de5b5784e00cef623a8158e40c7e3f2247f9ed","schema_version":"1.0","event_id":"sha256:69a36addd5f91f33505dc78234de5b5784e00cef623a8158e40c7e3f2247f9ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DAQZWHZLK4F3TZNWBPO7UCREOQ/bundle.json","state_url":"https://pith.science/pith/DAQZWHZLK4F3TZNWBPO7UCREOQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DAQZWHZLK4F3TZNWBPO7UCREOQ/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":"2026-08-08T11:11:56Z","links":{"resolver":"https://pith.science/pith/DAQZWHZLK4F3TZNWBPO7UCREOQ","bundle":"https://pith.science/pith/DAQZWHZLK4F3TZNWBPO7UCREOQ/bundle.json","state":"https://pith.science/pith/DAQZWHZLK4F3TZNWBPO7UCREOQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DAQZWHZLK4F3TZNWBPO7UCREOQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DAQZWHZLK4F3TZNWBPO7UCREOQ","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":"f7fa038d62418447d24285240533171fd0b73b37ad80233f277384a9cd17020f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T17:48:11Z","title_canon_sha256":"6426238307fdd96fa0a76d17e628ed893ab4de964f677d4b09da4cc4f3e2d677"},"schema_version":"1.0","source":{"id":"2408.10189","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10189","created_at":"2026-07-05T10:11:23Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10189v2","created_at":"2026-07-05T10:11:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10189","created_at":"2026-07-05T10:11:23Z"},{"alias_kind":"pith_short_12","alias_value":"DAQZWHZLK4F3","created_at":"2026-07-05T10:11:23Z"},{"alias_kind":"pith_short_16","alias_value":"DAQZWHZLK4F3TZNW","created_at":"2026-07-05T10:11:23Z"},{"alias_kind":"pith_short_8","alias_value":"DAQZWHZL","created_at":"2026-07-05T10:11:23Z"}],"graph_snapshots":[{"event_id":"sha256:69a36addd5f91f33505dc78234de5b5784e00cef623a8158e40c7e3f2247f9ed","target":"graph","created_at":"2026-07-05T10:11:23Z","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/2408.10189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer architectures have become a dominant paradigm for domains like language modeling but suffer in many inference settings due to their quadratic-time self-attention. Recently proposed subquadratic architectures, such as Mamba, have shown promise, but have been pretrained with substantially less computational resources than the strongest Transformer models. In this work, we present a method that is able to distill a pretrained Transformer architecture into alternative architectures such as state space models (SSMs). The key idea to our approach is that we can view both Transformers and","authors_text":"Albert Gu, Aviv Bick, Eric P. Xing, J. Zico Kolter, Kevin Y. Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T17:48:11Z","title":"Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10189","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":"sha256:77112a16d36d3619c8521fd9c10d472169383bdfab00d079086eafcbf1668c70","target":"record","created_at":"2026-07-05T10:11:23Z","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":"f7fa038d62418447d24285240533171fd0b73b37ad80233f277384a9cd17020f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T17:48:11Z","title_canon_sha256":"6426238307fdd96fa0a76d17e628ed893ab4de964f677d4b09da4cc4f3e2d677"},"schema_version":"1.0","source":{"id":"2408.10189","kind":"arxiv","version":2}},"canonical_sha256":"18219b1f2b570bb9e5b60bddfa0a24741ab0ea339cff35547da0c65da2d2ce2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18219b1f2b570bb9e5b60bddfa0a24741ab0ea339cff35547da0c65da2d2ce2e","first_computed_at":"2026-07-05T10:11:23.194199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:23.194199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cZMm6okBjblu5XSGhVdm0QwZZwRm7LeJt5BxaFrPF9jZ1qjQlcTtVm2TJ1vaa+hVuZka3kt0w9cHNPmhRt43Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:23.194706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10189","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77112a16d36d3619c8521fd9c10d472169383bdfab00d079086eafcbf1668c70","sha256:69a36addd5f91f33505dc78234de5b5784e00cef623a8158e40c7e3f2247f9ed"],"state_sha256":"2510f6bde3ae5d1645d273e51b0fe81bc2c9482f19749b97af0d2b6667f3f023"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8lMGwoMz8fR/Io09P4d9ks2rxTBMGbNLwyOYvXve93emXuTq+6pPOCjJJ/K1MA7wbUCPP4iepay0wLePtHfuAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:11:56.715530Z","bundle_sha256":"b34d6d4cdbcb71486e2c1ec3e642a72811c496bc1d297041ce447439760c1d7c"}}