{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4ID7VOP3E45AG67ET3FGQNQW6N","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":"67e8940e18af3d3437ddf828a759be334838a0e7ba4d542699ae59706d328f03","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T19:33:21Z","title_canon_sha256":"1ea77076e090c00a49764e61c74e917c241c2ee1ca90c9b207487187f53d100f"},"schema_version":"1.0","source":{"id":"2506.01133","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01133","created_at":"2026-07-05T11:13:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01133v1","created_at":"2026-07-05T11:13:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01133","created_at":"2026-07-05T11:13:47Z"},{"alias_kind":"pith_short_12","alias_value":"4ID7VOP3E45A","created_at":"2026-07-05T11:13:47Z"},{"alias_kind":"pith_short_16","alias_value":"4ID7VOP3E45AG67E","created_at":"2026-07-05T11:13:47Z"},{"alias_kind":"pith_short_8","alias_value":"4ID7VOP3","created_at":"2026-07-05T11:13:47Z"}],"graph_snapshots":[{"event_id":"sha256:330c3919539733b77641998a1c49d3000fd4f3fd13c8aa04c02701d415301b1f","target":"graph","created_at":"2026-07-05T11:13:47Z","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/2506.01133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"As{\\i}m Ersoy, Basel Mousi, Fahim Dalvi, Firoj Alam, Nadir Durrani, Shammur Chowdhury","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T19:33:21Z","title":"From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01133","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:d53576be022bb82b73e654a266a70d73c784b5926ce86e4a95568cafe1cfdfbf","target":"record","created_at":"2026-07-05T11:13:47Z","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":"67e8940e18af3d3437ddf828a759be334838a0e7ba4d542699ae59706d328f03","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T19:33:21Z","title_canon_sha256":"1ea77076e090c00a49764e61c74e917c241c2ee1ca90c9b207487187f53d100f"},"schema_version":"1.0","source":{"id":"2506.01133","kind":"arxiv","version":1}},"canonical_sha256":"e207fab9fb273a037be49eca683616f376796044d03d9577f7cd2c7d04a97e8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e207fab9fb273a037be49eca683616f376796044d03d9577f7cd2c7d04a97e8f","first_computed_at":"2026-07-05T11:13:47.125181Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:47.125181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GzqgDDs1YRsk/ArYhTnTDHjQ7fAm6Wlq4kVVKShlWXEMqhBvgFtYvU5twaF9x4jdOWDkU5e4MzFggyvBsUczCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:47.125755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01133","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d53576be022bb82b73e654a266a70d73c784b5926ce86e4a95568cafe1cfdfbf","sha256:330c3919539733b77641998a1c49d3000fd4f3fd13c8aa04c02701d415301b1f"],"state_sha256":"007b0c20698ffa5f4f13c5d2286bf4c1101fb8fd1f561eeb6c9c25e9e3ec51bf"}