{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZPTH6N7ZTLWW3QYKEHHVOVZTJU","short_pith_number":"pith:ZPTH6N7Z","canonical_record":{"source":{"id":"2310.13289","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-20T05:41:57Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"cdacaa27bbc9bce6460f12a6c006abeccafde899b701042a49d025b06b52a1c6","abstract_canon_sha256":"7f9ea9a8ff0eecb8730a49a2cb8035ebc631f4056e9f12d15bb2451e31dd7724"},"schema_version":"1.0"},"canonical_sha256":"cbe67f37f99aed6dc30a21cf5757334d0be0944f324e16ee864e6f225b8a7b4e","source":{"kind":"arxiv","id":"2310.13289","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13289","created_at":"2026-05-18T02:23:34Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13289v2","created_at":"2026-05-18T02:23:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13289","created_at":"2026-05-18T02:23:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZPTH6N7ZTLWW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZPTH6N7ZTLWW3QYK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZPTH6N7Z","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZPTH6N7ZTLWW3QYKEHHVOVZTJU","target":"record","payload":{"canonical_record":{"source":{"id":"2310.13289","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-20T05:41:57Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"cdacaa27bbc9bce6460f12a6c006abeccafde899b701042a49d025b06b52a1c6","abstract_canon_sha256":"7f9ea9a8ff0eecb8730a49a2cb8035ebc631f4056e9f12d15bb2451e31dd7724"},"schema_version":"1.0"},"canonical_sha256":"cbe67f37f99aed6dc30a21cf5757334d0be0944f324e16ee864e6f225b8a7b4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:23:34.307102Z","signature_b64":"NcJo8AiIJoN9b01SsBlI4Io7oVGJeQ7XnKKPc1ZJAVr1WPT7s9CBasGrVWFv7oggQbpY/Q2sLgW5CNbbKaocAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbe67f37f99aed6dc30a21cf5757334d0be0944f324e16ee864e6f225b8a7b4e","last_reissued_at":"2026-05-18T02:23:34.306445Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:23:34.306445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.13289","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":"2026-05-18T02:23:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J90zv4qbZFNR1bOO3b8w7okA+4mCjRuRh/zIUt82vn4daQQgKyPV1L20Brg6sUOWRuqrbFKfLeIHvrXHsks+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T12:10:40.858588Z"},"content_sha256":"59e733d8aef0a25fc796041e828a20e51877d3bb5e7f21934ad7fc603d6ca2c5","schema_version":"1.0","event_id":"sha256:59e733d8aef0a25fc796041e828a20e51877d3bb5e7f21934ad7fc603d6ca2c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZPTH6N7ZTLWW3QYKEHHVOVZTJU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Changli Tang, Chao Zhang, Guangzhi Sun, Lu Lu, Tian Tan, Wei Li, Wenyi Yu, Xianzhao Chen, Zejun Ma","submitted_at":"2023-10-20T05:41:57Z","abstract_excerpt":"Hearing is arguably an essential ability of artificial intelligence (AI) agents in the physical world, which refers to the perception and understanding of general auditory information consisting of at least three types of sounds: speech, audio events, and music. In this paper, we propose SALMONN, a speech audio language music open neural network, built by integrating a pre-trained text-based large language model (LLM) with speech and audio encoders into a single multimodal model. SALMONN enables the LLM to directly process and understand general audio inputs and achieve competitive performance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13289","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":""},"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":"2026-05-18T02:23:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TWJ1gGo4kni/xRfRnhB4u3toQCdp0Rw/LKIFUYnW3v+l+QAwePIYhPnq766Q3QoynrPsIKUkfa5DdlZiwhDBDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T12:10:40.859189Z"},"content_sha256":"c3567346ffc6d3ef629aba5868cfc78c97f0e2074d0a124891e62fd331699da6","schema_version":"1.0","event_id":"sha256:c3567346ffc6d3ef629aba5868cfc78c97f0e2074d0a124891e62fd331699da6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZPTH6N7ZTLWW3QYKEHHVOVZTJU/bundle.json","state_url":"https://pith.science/pith/ZPTH6N7ZTLWW3QYKEHHVOVZTJU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZPTH6N7ZTLWW3QYKEHHVOVZTJU/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":"2026-05-20T12:10:40Z","links":{"resolver":"https://pith.science/pith/ZPTH6N7ZTLWW3QYKEHHVOVZTJU","bundle":"https://pith.science/pith/ZPTH6N7ZTLWW3QYKEHHVOVZTJU/bundle.json","state":"https://pith.science/pith/ZPTH6N7ZTLWW3QYKEHHVOVZTJU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZPTH6N7ZTLWW3QYKEHHVOVZTJU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZPTH6N7ZTLWW3QYKEHHVOVZTJU","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":"7f9ea9a8ff0eecb8730a49a2cb8035ebc631f4056e9f12d15bb2451e31dd7724","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-20T05:41:57Z","title_canon_sha256":"cdacaa27bbc9bce6460f12a6c006abeccafde899b701042a49d025b06b52a1c6"},"schema_version":"1.0","source":{"id":"2310.13289","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13289","created_at":"2026-05-18T02:23:34Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13289v2","created_at":"2026-05-18T02:23:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13289","created_at":"2026-05-18T02:23:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZPTH6N7ZTLWW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZPTH6N7ZTLWW3QYK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZPTH6N7Z","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c3567346ffc6d3ef629aba5868cfc78c97f0e2074d0a124891e62fd331699da6","target":"graph","created_at":"2026-05-18T02:23:34Z","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"},"paper":{"abstract_excerpt":"Hearing is arguably an essential ability of artificial intelligence (AI) agents in the physical world, which refers to the perception and understanding of general auditory information consisting of at least three types of sounds: speech, audio events, and music. In this paper, we propose SALMONN, a speech audio language music open neural network, built by integrating a pre-trained text-based large language model (LLM) with speech and audio encoders into a single multimodal model. SALMONN enables the LLM to directly process and understand general audio inputs and achieve competitive performance","authors_text":"Changli Tang, Chao Zhang, Guangzhi Sun, Lu Lu, Tian Tan, Wei Li, Wenyi Yu, Xianzhao Chen, Zejun Ma","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-20T05:41:57Z","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13289","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":"sha256:59e733d8aef0a25fc796041e828a20e51877d3bb5e7f21934ad7fc603d6ca2c5","target":"record","created_at":"2026-05-18T02:23:34Z","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":"7f9ea9a8ff0eecb8730a49a2cb8035ebc631f4056e9f12d15bb2451e31dd7724","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-20T05:41:57Z","title_canon_sha256":"cdacaa27bbc9bce6460f12a6c006abeccafde899b701042a49d025b06b52a1c6"},"schema_version":"1.0","source":{"id":"2310.13289","kind":"arxiv","version":2}},"canonical_sha256":"cbe67f37f99aed6dc30a21cf5757334d0be0944f324e16ee864e6f225b8a7b4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbe67f37f99aed6dc30a21cf5757334d0be0944f324e16ee864e6f225b8a7b4e","first_computed_at":"2026-05-18T02:23:34.306445Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:23:34.306445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NcJo8AiIJoN9b01SsBlI4Io7oVGJeQ7XnKKPc1ZJAVr1WPT7s9CBasGrVWFv7oggQbpY/Q2sLgW5CNbbKaocAA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:23:34.307102Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.13289","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59e733d8aef0a25fc796041e828a20e51877d3bb5e7f21934ad7fc603d6ca2c5","sha256:c3567346ffc6d3ef629aba5868cfc78c97f0e2074d0a124891e62fd331699da6"],"state_sha256":"4963523dcbb3c4cdd6872eb81a3dad294eafb7256a700f1321a36b8d395c1dfb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vj++gCUjXiEdORmLLS1XYnELQ036pgpF50rVBHMQW3zQZmK/uUzmD+ed/9ppZbVGUgjnx0364GsZi6JbrX/XCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T12:10:40.861403Z","bundle_sha256":"e73b0c99cd184ebac243b0d6c7405260b2f147a2030c4f84ac19b027185d4c5c"}}