{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5NKNT24ZD7MIWX4DTF46TSR3JP","short_pith_number":"pith:5NKNT24Z","canonical_record":{"source":{"id":"2411.15685","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-24T02:21:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fe91a6850043c72daea034045a61e61b94862e60f1e187b312b1f4ed237f3fff","abstract_canon_sha256":"d165fc964a7d847fc42667a70e12b0cb0c4a1fab5c498e2ff5391eb3d5b8c733"},"schema_version":"1.0"},"canonical_sha256":"eb54d9eb991fd88b5f839979e9ca3b4bcf3fae4897b29a96e62ed943926480ad","source":{"kind":"arxiv","id":"2411.15685","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15685","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15685v1","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15685","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_12","alias_value":"5NKNT24ZD7MI","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_16","alias_value":"5NKNT24ZD7MIWX4D","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_8","alias_value":"5NKNT24Z","created_at":"2026-07-05T09:39:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5NKNT24ZD7MIWX4DTF46TSR3JP","target":"record","payload":{"canonical_record":{"source":{"id":"2411.15685","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-24T02:21:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fe91a6850043c72daea034045a61e61b94862e60f1e187b312b1f4ed237f3fff","abstract_canon_sha256":"d165fc964a7d847fc42667a70e12b0cb0c4a1fab5c498e2ff5391eb3d5b8c733"},"schema_version":"1.0"},"canonical_sha256":"eb54d9eb991fd88b5f839979e9ca3b4bcf3fae4897b29a96e62ed943926480ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:39.264643Z","signature_b64":"rYMpoFoSyXrsLAyubp8lRkDJeH80vH3XzXwGaObZhEDu+N87G1Enz7g1nFpjKEujp1X+BUABIerIWbu8VyXzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb54d9eb991fd88b5f839979e9ca3b4bcf3fae4897b29a96e62ed943926480ad","last_reissued_at":"2026-07-05T09:39:39.264129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:39.264129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.15685","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":"2026-07-05T09:39:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GBZKiy0ogOAtmiM5vq8mY9j5ups3+0LS8NNsYsSoYNJhDRqmd8VCrd8uAmNG/NrXne3iAiflt/fvDPYsTVMrAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:57:33.134784Z"},"content_sha256":"b8d24fe72c0e80c116e6765058399201926ac9efc622044c606fc969a48abd09","schema_version":"1.0","event_id":"sha256:b8d24fe72c0e80c116e6765058399201926ac9efc622044c606fc969a48abd09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5NKNT24ZD7MIWX4DTF46TSR3JP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"State-Space Large Audio Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.AS","authors_text":"Hilde Kuehne, James Glass, Leonid Karlinsky, Rogerio Feris, Saurabhchand Bhati, Yuan Gong","submitted_at":"2024-11-24T02:21:28Z","abstract_excerpt":"Large Audio Language Models (LALM) combine the audio perception models and the Large Language Models (LLM) and show a remarkable ability to reason about the input audio, infer the meaning, and understand the intent. However, these systems rely on Transformers which scale quadratically with the input sequence lengths which poses computational challenges in deploying these systems in memory and time-constrained scenarios. Recently, the state-space models (SSMs) have emerged as an alternative to transformer networks.\n  While there have been successful attempts to replace transformer-based audio p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15685","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/2411.15685/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":"2026-07-05T09:39:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vs61DR6wFH+md+0lJ3jGwMBOfjd/QCHJJg3rjKIvHaKPZdBjajZZkz9EQsYkgzDXPeQ0mmX9nROjM7SlaZ2BDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:57:33.135288Z"},"content_sha256":"9497f5e377685ce4bda4a547369ade867e700825f5904a9f7834e27d0bf02950","schema_version":"1.0","event_id":"sha256:9497f5e377685ce4bda4a547369ade867e700825f5904a9f7834e27d0bf02950"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5NKNT24ZD7MIWX4DTF46TSR3JP/bundle.json","state_url":"https://pith.science/pith/5NKNT24ZD7MIWX4DTF46TSR3JP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5NKNT24ZD7MIWX4DTF46TSR3JP/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":"2026-08-08T22:57:33Z","links":{"resolver":"https://pith.science/pith/5NKNT24ZD7MIWX4DTF46TSR3JP","bundle":"https://pith.science/pith/5NKNT24ZD7MIWX4DTF46TSR3JP/bundle.json","state":"https://pith.science/pith/5NKNT24ZD7MIWX4DTF46TSR3JP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5NKNT24ZD7MIWX4DTF46TSR3JP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5NKNT24ZD7MIWX4DTF46TSR3JP","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":"d165fc964a7d847fc42667a70e12b0cb0c4a1fab5c498e2ff5391eb3d5b8c733","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-24T02:21:28Z","title_canon_sha256":"fe91a6850043c72daea034045a61e61b94862e60f1e187b312b1f4ed237f3fff"},"schema_version":"1.0","source":{"id":"2411.15685","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15685","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15685v1","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15685","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_12","alias_value":"5NKNT24ZD7MI","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_16","alias_value":"5NKNT24ZD7MIWX4D","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_8","alias_value":"5NKNT24Z","created_at":"2026-07-05T09:39:39Z"}],"graph_snapshots":[{"event_id":"sha256:9497f5e377685ce4bda4a547369ade867e700825f5904a9f7834e27d0bf02950","target":"graph","created_at":"2026-07-05T09:39:39Z","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/2411.15685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Audio Language Models (LALM) combine the audio perception models and the Large Language Models (LLM) and show a remarkable ability to reason about the input audio, infer the meaning, and understand the intent. However, these systems rely on Transformers which scale quadratically with the input sequence lengths which poses computational challenges in deploying these systems in memory and time-constrained scenarios. Recently, the state-space models (SSMs) have emerged as an alternative to transformer networks.\n  While there have been successful attempts to replace transformer-based audio p","authors_text":"Hilde Kuehne, James Glass, Leonid Karlinsky, Rogerio Feris, Saurabhchand Bhati, Yuan Gong","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-24T02:21:28Z","title":"State-Space Large Audio Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15685","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:b8d24fe72c0e80c116e6765058399201926ac9efc622044c606fc969a48abd09","target":"record","created_at":"2026-07-05T09:39:39Z","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":"d165fc964a7d847fc42667a70e12b0cb0c4a1fab5c498e2ff5391eb3d5b8c733","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-24T02:21:28Z","title_canon_sha256":"fe91a6850043c72daea034045a61e61b94862e60f1e187b312b1f4ed237f3fff"},"schema_version":"1.0","source":{"id":"2411.15685","kind":"arxiv","version":1}},"canonical_sha256":"eb54d9eb991fd88b5f839979e9ca3b4bcf3fae4897b29a96e62ed943926480ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb54d9eb991fd88b5f839979e9ca3b4bcf3fae4897b29a96e62ed943926480ad","first_computed_at":"2026-07-05T09:39:39.264129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:39.264129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rYMpoFoSyXrsLAyubp8lRkDJeH80vH3XzXwGaObZhEDu+N87G1Enz7g1nFpjKEujp1X+BUABIerIWbu8VyXzDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:39.264643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15685","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8d24fe72c0e80c116e6765058399201926ac9efc622044c606fc969a48abd09","sha256:9497f5e377685ce4bda4a547369ade867e700825f5904a9f7834e27d0bf02950"],"state_sha256":"ad3d9c74536eb491dfd2706d88f48fd066beb41542c85c268d4db250a3185440"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ePEVBzbXf8U3HFZAMChcrpEVWegwVX3WXv2s+DMuBp178cEJ5CzDjQWkEoHPnAErDCTGsde9WDI59aay/RPxCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:57:33.140240Z","bundle_sha256":"b0af5d17a8f01dbb5064ea19765960635a857a7133f58c14d1d839ac88323dc3"}}