{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WHBFWEQ5KYEKMDY5PBZKYV6ESU","short_pith_number":"pith:WHBFWEQ5","schema_version":"1.0","canonical_sha256":"b1c25b121d5608a60f1d7872ac57c4950af5f2ad6e01326c7e6cbce97cfdc3aa","source":{"kind":"arxiv","id":"2509.15680","version":3},"attestation_state":"computed","paper":{"title":"SAM: A Mamba-2 State-Space Audio-Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hyukjun Lee, Jaehan Jung, Taehan Lee","submitted_at":"2025-09-19T06:54:42Z","abstract_excerpt":"We present SAM, a State-space Audio-language Model that integrates an audio encoder with a Mamba-2 backbone. SAM-2.7B achieves 21.1 mAP on AudioSet and 17.6 SPICE on AudioCaps, matching or surpassing larger 7B transformer-based models with fewer parameters. We further provide the first systematic, representation-level analysis of how SSMs interact with audio encoder outputs: (1) joint audio encoder finetuning is essential, supported by accuracy gains and observed adaptation of token representation rank and similarity across different SSM sizes; (2) despite linear scaling, SSMs benefit more fro"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.15680","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-19T06:54:42Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"993d1112c37d873179ae70276e98865beeacb865e072bcec7a62e6b7acd13e30","abstract_canon_sha256":"6d48b7858ce5fcd82f44b3e394b9fb19d6ac36c1bf3ad2cdd53c92c469cde873"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:17.402828Z","signature_b64":"RoE5Dr1agKeFQyU66MtnjwlVo3k8k2l2M29fjey5243mH2vr0gkiwNFnhDPnVPfwFBDoDeKHMHeRgkKw7jPOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1c25b121d5608a60f1d7872ac57c4950af5f2ad6e01326c7e6cbce97cfdc3aa","last_reissued_at":"2026-06-11T01:09:17.401865Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:17.401865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAM: A Mamba-2 State-Space Audio-Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hyukjun Lee, Jaehan Jung, Taehan Lee","submitted_at":"2025-09-19T06:54:42Z","abstract_excerpt":"We present SAM, a State-space Audio-language Model that integrates an audio encoder with a Mamba-2 backbone. SAM-2.7B achieves 21.1 mAP on AudioSet and 17.6 SPICE on AudioCaps, matching or surpassing larger 7B transformer-based models with fewer parameters. We further provide the first systematic, representation-level analysis of how SSMs interact with audio encoder outputs: (1) joint audio encoder finetuning is essential, supported by accuracy gains and observed adaptation of token representation rank and similarity across different SSM sizes; (2) despite linear scaling, SSMs benefit more fro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.15680","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/2509.15680/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.15680","created_at":"2026-06-11T01:09:17.402043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.15680v3","created_at":"2026-06-11T01:09:17.402043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.15680","created_at":"2026-06-11T01:09:17.402043+00:00"},{"alias_kind":"pith_short_12","alias_value":"WHBFWEQ5KYEK","created_at":"2026-06-11T01:09:17.402043+00:00"},{"alias_kind":"pith_short_16","alias_value":"WHBFWEQ5KYEKMDY5","created_at":"2026-06-11T01:09:17.402043+00:00"},{"alias_kind":"pith_short_8","alias_value":"WHBFWEQ5","created_at":"2026-06-11T01:09:17.402043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.15680","citing_title":"SAM: A Mamba-2 State-Space Audio-Language Model","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WHBFWEQ5KYEKMDY5PBZKYV6ESU","json":"https://pith.science/pith/WHBFWEQ5KYEKMDY5PBZKYV6ESU.json","graph_json":"https://pith.science/api/pith-number/WHBFWEQ5KYEKMDY5PBZKYV6ESU/graph.json","events_json":"https://pith.science/api/pith-number/WHBFWEQ5KYEKMDY5PBZKYV6ESU/events.json","paper":"https://pith.science/paper/WHBFWEQ5"},"agent_actions":{"view_html":"https://pith.science/pith/WHBFWEQ5KYEKMDY5PBZKYV6ESU","download_json":"https://pith.science/pith/WHBFWEQ5KYEKMDY5PBZKYV6ESU.json","view_paper":"https://pith.science/paper/WHBFWEQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.15680&json=true","fetch_graph":"https://pith.science/api/pith-number/WHBFWEQ5KYEKMDY5PBZKYV6ESU/graph.json","fetch_events":"https://pith.science/api/pith-number/WHBFWEQ5KYEKMDY5PBZKYV6ESU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WHBFWEQ5KYEKMDY5PBZKYV6ESU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WHBFWEQ5KYEKMDY5PBZKYV6ESU/action/storage_attestation","attest_author":"https://pith.science/pith/WHBFWEQ5KYEKMDY5PBZKYV6ESU/action/author_attestation","sign_citation":"https://pith.science/pith/WHBFWEQ5KYEKMDY5PBZKYV6ESU/action/citation_signature","submit_replication":"https://pith.science/pith/WHBFWEQ5KYEKMDY5PBZKYV6ESU/action/replication_record"}},"created_at":"2026-06-11T01:09:17.402043+00:00","updated_at":"2026-06-11T01:09:17.402043+00:00"}