{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4ID7VOP3E45AG67ET3FGQNQW6N","short_pith_number":"pith:4ID7VOP3","schema_version":"1.0","canonical_sha256":"e207fab9fb273a037be49eca683616f376796044d03d9577f7cd2c7d04a97e8f","source":{"kind":"arxiv","id":"2506.01133","version":1},"attestation_state":"computed","paper":{"title":"From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"As{\\i}m Ersoy, Basel Mousi, Fahim Dalvi, Firoj Alam, Nadir Durrani, Shammur Chowdhury","submitted_at":"2025-06-01T19:33:21Z","abstract_excerpt":"The emergence of large language models (LLMs) has demonstrated that systems trained solely on text can acquire extensive world knowledge, develop reasoning capabilities, and internalize abstract semantic concepts--showcasing properties that can be associated with general intelligence. This raises an intriguing question: Do such concepts emerge in models trained on other modalities, such as speech? Furthermore, when models are trained jointly on multiple modalities: Do they develop a richer, more structured semantic understanding? To explore this, we analyze the conceptual structures learned by"},"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":"2506.01133","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T19:33:21Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"1ea77076e090c00a49764e61c74e917c241c2ee1ca90c9b207487187f53d100f","abstract_canon_sha256":"67e8940e18af3d3437ddf828a759be334838a0e7ba4d542699ae59706d328f03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:47.125755Z","signature_b64":"GzqgDDs1YRsk/ArYhTnTDHjQ7fAm6Wlq4kVVKShlWXEMqhBvgFtYvU5twaF9x4jdOWDkU5e4MzFggyvBsUczCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e207fab9fb273a037be49eca683616f376796044d03d9577f7cd2c7d04a97e8f","last_reissued_at":"2026-07-05T11:13:47.125181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:47.125181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"As{\\i}m Ersoy, Basel Mousi, Fahim Dalvi, Firoj Alam, Nadir Durrani, Shammur Chowdhury","submitted_at":"2025-06-01T19:33:21Z","abstract_excerpt":"The emergence of large language models (LLMs) has demonstrated that systems trained solely on text can acquire extensive world knowledge, develop reasoning capabilities, and internalize abstract semantic concepts--showcasing properties that can be associated with general intelligence. This raises an intriguing question: Do such concepts emerge in models trained on other modalities, such as speech? Furthermore, when models are trained jointly on multiple modalities: Do they develop a richer, more structured semantic understanding? To explore this, we analyze the conceptual structures learned by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01133","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/2506.01133/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":"2506.01133","created_at":"2026-07-05T11:13:47.125261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01133v1","created_at":"2026-07-05T11:13:47.125261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01133","created_at":"2026-07-05T11:13:47.125261+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ID7VOP3E45A","created_at":"2026-07-05T11:13:47.125261+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ID7VOP3E45AG67E","created_at":"2026-07-05T11:13:47.125261+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ID7VOP3","created_at":"2026-07-05T11:13:47.125261+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01133","citing_title":"From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ID7VOP3E45AG67ET3FGQNQW6N","json":"https://pith.science/pith/4ID7VOP3E45AG67ET3FGQNQW6N.json","graph_json":"https://pith.science/api/pith-number/4ID7VOP3E45AG67ET3FGQNQW6N/graph.json","events_json":"https://pith.science/api/pith-number/4ID7VOP3E45AG67ET3FGQNQW6N/events.json","paper":"https://pith.science/paper/4ID7VOP3"},"agent_actions":{"view_html":"https://pith.science/pith/4ID7VOP3E45AG67ET3FGQNQW6N","download_json":"https://pith.science/pith/4ID7VOP3E45AG67ET3FGQNQW6N.json","view_paper":"https://pith.science/paper/4ID7VOP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01133&json=true","fetch_graph":"https://pith.science/api/pith-number/4ID7VOP3E45AG67ET3FGQNQW6N/graph.json","fetch_events":"https://pith.science/api/pith-number/4ID7VOP3E45AG67ET3FGQNQW6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ID7VOP3E45AG67ET3FGQNQW6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ID7VOP3E45AG67ET3FGQNQW6N/action/storage_attestation","attest_author":"https://pith.science/pith/4ID7VOP3E45AG67ET3FGQNQW6N/action/author_attestation","sign_citation":"https://pith.science/pith/4ID7VOP3E45AG67ET3FGQNQW6N/action/citation_signature","submit_replication":"https://pith.science/pith/4ID7VOP3E45AG67ET3FGQNQW6N/action/replication_record"}},"created_at":"2026-07-05T11:13:47.125261+00:00","updated_at":"2026-07-05T11:13:47.125261+00:00"}