{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:J5MPYTGJBAGKPDUYWSEB6V6AVC","short_pith_number":"pith:J5MPYTGJ","canonical_record":{"source":{"id":"2503.15338","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-03-19T15:34:21Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"6a21aefdb1cb342cbe0db125e41860a51b077a188ae651bd0b79876179760ef8","abstract_canon_sha256":"0d676d4a220f689a31e8a97f7ea7be9295c296505f0571e7ecd70feb443e8ac8"},"schema_version":"1.0"},"canonical_sha256":"4f58fc4cc9080ca78e98b4881f57c0a8b3874a2b0191e8993d7cc1b1ac0ace91","source":{"kind":"arxiv","id":"2503.15338","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15338","created_at":"2026-07-05T10:35:24Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15338v1","created_at":"2026-07-05T10:35:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15338","created_at":"2026-07-05T10:35:24Z"},{"alias_kind":"pith_short_12","alias_value":"J5MPYTGJBAGK","created_at":"2026-07-05T10:35:24Z"},{"alias_kind":"pith_short_16","alias_value":"J5MPYTGJBAGKPDUY","created_at":"2026-07-05T10:35:24Z"},{"alias_kind":"pith_short_8","alias_value":"J5MPYTGJ","created_at":"2026-07-05T10:35:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:J5MPYTGJBAGKPDUYWSEB6V6AVC","target":"record","payload":{"canonical_record":{"source":{"id":"2503.15338","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-03-19T15:34:21Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"6a21aefdb1cb342cbe0db125e41860a51b077a188ae651bd0b79876179760ef8","abstract_canon_sha256":"0d676d4a220f689a31e8a97f7ea7be9295c296505f0571e7ecd70feb443e8ac8"},"schema_version":"1.0"},"canonical_sha256":"4f58fc4cc9080ca78e98b4881f57c0a8b3874a2b0191e8993d7cc1b1ac0ace91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:24.313339Z","signature_b64":"sQDrl/BA1mUJ4+GqjtBMfJZMClkqiFGWpZHclaSB5DMj+ugkKsKfFPqdg8allHWgyZ9ZBo5zn2YbSJsgSkTzDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f58fc4cc9080ca78e98b4881f57c0a8b3874a2b0191e8993d7cc1b1ac0ace91","last_reissued_at":"2026-07-05T10:35:24.312183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:24.312183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.15338","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":"2026-07-05T10:35:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e0+DT5aB4jEWUtd9RNHUXx27Ln20cNHOqip6JcJ/RCYx3ykUNkRfff1I/JhG8W0JDFIAMy9cs0Mt3oaQGHtnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T11:17:24.840431Z"},"content_sha256":"7ad26744ffbc298ec755971cc3df9f29576fda102869f954fe6b900a777b6eab","schema_version":"1.0","event_id":"sha256:7ad26744ffbc298ec755971cc3df9f29576fda102869f954fe6b900a777b6eab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:J5MPYTGJBAGKPDUYWSEB6V6AVC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Solla: Towards a Speech-Oriented LLM That Hears Acoustic Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dekun Chen, Haizhou Li, Junyi Ao, Jun Zhang, Lu Lu, Wenjie Feng, Xiaohai Tian, Yuxuan Wang, Zhizheng Wu","submitted_at":"2025-03-19T15:34:21Z","abstract_excerpt":"Large Language Models (LLMs) have recently shown remarkable ability to process not only text but also multimodal inputs such as speech and audio. However, most existing models primarily focus on analyzing input signals using text instructions, overlooking scenarios in which speech instructions and audio are mixed and serve as inputs to the model. To address these challenges, we introduce Solla, a novel framework designed to understand speech-based questions and hear the acoustic context concurrently. Solla incorporates an audio tagging module to effectively identify and represent audio events,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15338","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/2503.15338/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":"2026-07-05T10:35:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UnHoeOr60BeiC0sApWvn5smvmgGdiw7U1s+IpybLtdGgzHGrndjpy3OBVvXf+5oxSL38LJHI5JEdTfREQlNlBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T11:17:24.840793Z"},"content_sha256":"1d1e33577c33e92e3e516577f00a697cab955dab3e95598e46c7a7e7aa300843","schema_version":"1.0","event_id":"sha256:1d1e33577c33e92e3e516577f00a697cab955dab3e95598e46c7a7e7aa300843"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J5MPYTGJBAGKPDUYWSEB6V6AVC/bundle.json","state_url":"https://pith.science/pith/J5MPYTGJBAGKPDUYWSEB6V6AVC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J5MPYTGJBAGKPDUYWSEB6V6AVC/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":"2026-07-19T11:17:24Z","links":{"resolver":"https://pith.science/pith/J5MPYTGJBAGKPDUYWSEB6V6AVC","bundle":"https://pith.science/pith/J5MPYTGJBAGKPDUYWSEB6V6AVC/bundle.json","state":"https://pith.science/pith/J5MPYTGJBAGKPDUYWSEB6V6AVC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J5MPYTGJBAGKPDUYWSEB6V6AVC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J5MPYTGJBAGKPDUYWSEB6V6AVC","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":"0d676d4a220f689a31e8a97f7ea7be9295c296505f0571e7ecd70feb443e8ac8","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-03-19T15:34:21Z","title_canon_sha256":"6a21aefdb1cb342cbe0db125e41860a51b077a188ae651bd0b79876179760ef8"},"schema_version":"1.0","source":{"id":"2503.15338","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15338","created_at":"2026-07-05T10:35:24Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15338v1","created_at":"2026-07-05T10:35:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15338","created_at":"2026-07-05T10:35:24Z"},{"alias_kind":"pith_short_12","alias_value":"J5MPYTGJBAGK","created_at":"2026-07-05T10:35:24Z"},{"alias_kind":"pith_short_16","alias_value":"J5MPYTGJBAGKPDUY","created_at":"2026-07-05T10:35:24Z"},{"alias_kind":"pith_short_8","alias_value":"J5MPYTGJ","created_at":"2026-07-05T10:35:24Z"}],"graph_snapshots":[{"event_id":"sha256:1d1e33577c33e92e3e516577f00a697cab955dab3e95598e46c7a7e7aa300843","target":"graph","created_at":"2026-07-05T10:35:24Z","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/2503.15338/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have recently shown remarkable ability to process not only text but also multimodal inputs such as speech and audio. However, most existing models primarily focus on analyzing input signals using text instructions, overlooking scenarios in which speech instructions and audio are mixed and serve as inputs to the model. To address these challenges, we introduce Solla, a novel framework designed to understand speech-based questions and hear the acoustic context concurrently. Solla incorporates an audio tagging module to effectively identify and represent audio events,","authors_text":"Dekun Chen, Haizhou Li, Junyi Ao, Jun Zhang, Lu Lu, Wenjie Feng, Xiaohai Tian, Yuxuan Wang, Zhizheng Wu","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-03-19T15:34:21Z","title":"Solla: Towards a Speech-Oriented LLM That Hears Acoustic Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15338","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":"sha256:7ad26744ffbc298ec755971cc3df9f29576fda102869f954fe6b900a777b6eab","target":"record","created_at":"2026-07-05T10:35:24Z","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":"0d676d4a220f689a31e8a97f7ea7be9295c296505f0571e7ecd70feb443e8ac8","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-03-19T15:34:21Z","title_canon_sha256":"6a21aefdb1cb342cbe0db125e41860a51b077a188ae651bd0b79876179760ef8"},"schema_version":"1.0","source":{"id":"2503.15338","kind":"arxiv","version":1}},"canonical_sha256":"4f58fc4cc9080ca78e98b4881f57c0a8b3874a2b0191e8993d7cc1b1ac0ace91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f58fc4cc9080ca78e98b4881f57c0a8b3874a2b0191e8993d7cc1b1ac0ace91","first_computed_at":"2026-07-05T10:35:24.312183Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:24.312183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sQDrl/BA1mUJ4+GqjtBMfJZMClkqiFGWpZHclaSB5DMj+ugkKsKfFPqdg8allHWgyZ9ZBo5zn2YbSJsgSkTzDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:24.313339Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.15338","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ad26744ffbc298ec755971cc3df9f29576fda102869f954fe6b900a777b6eab","sha256:1d1e33577c33e92e3e516577f00a697cab955dab3e95598e46c7a7e7aa300843"],"state_sha256":"a2c35e7aaa1bd00e28820dccc91add26a4f9bdd55abb06ca9e59f82639251d07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O6lEtPttIvxozstAlzqQSVekPt5Z6X7Z5KKGy/IQSacLp0mVdgHqcK6Dy11vxX4wxNAI7/cnk8M75h1e0EPzCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T11:17:24.842858Z","bundle_sha256":"6fafd983db784699c0d6f83d0b6d525c8e54f6c02ba21ce6e62088e083fee810"}}