{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YZRHIQYI55HTFA7OYSTYDXBH3Y","short_pith_number":"pith:YZRHIQYI","schema_version":"1.0","canonical_sha256":"c662744308ef4f3283eec4a781dc27de113820444bbceb2b470de39087b6eb7e","source":{"kind":"arxiv","id":"2506.01872","version":1},"attestation_state":"computed","paper":{"title":"Is Extending Modality The Right Path Towards Omni-Modality?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Kai Zhang, Muhao Chen, Tinghui Zhu, Yu Su","submitted_at":"2025-06-02T17:01:40Z","abstract_excerpt":"Omni-modal language models (OLMs) aim to integrate and reason over diverse input modalities--such as text, images, video, and audio--while maintaining strong language capabilities. Despite recent advancements, existing models, especially open-source ones, remain far from true omni-modality, struggling to generalize beyond the specific modality pairs they are trained on or to achieve strong performance when processing multi-modal inputs. We study the effect of extending modality, the dominant technique for training multimodal models, where an off-the-shelf language model is fine-tuned on target"},"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":"2506.01872","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T17:01:40Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f7b493c1b1e0100bc5ee012a61e9b070d5f52db3ed32a8502375da8a05ea8659","abstract_canon_sha256":"2a27a1ade5aa901013a0bd837d1bb0cb43cf11cd0baf842c983fd902b7a1fd69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:20.724207Z","signature_b64":"X6vAWB35wXj4n2NSgXvVfj+NoUDrVIyxbnDOqdvewwYNtgP/UgwtgR1Ss3NWVzQ69mpBRlMceBEaCXLwcLcIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c662744308ef4f3283eec4a781dc27de113820444bbceb2b470de39087b6eb7e","last_reissued_at":"2026-07-05T11:14:20.723750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:20.723750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Extending Modality The Right Path Towards Omni-Modality?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Kai Zhang, Muhao Chen, Tinghui Zhu, Yu Su","submitted_at":"2025-06-02T17:01:40Z","abstract_excerpt":"Omni-modal language models (OLMs) aim to integrate and reason over diverse input modalities--such as text, images, video, and audio--while maintaining strong language capabilities. Despite recent advancements, existing models, especially open-source ones, remain far from true omni-modality, struggling to generalize beyond the specific modality pairs they are trained on or to achieve strong performance when processing multi-modal inputs. We study the effect of extending modality, the dominant technique for training multimodal models, where an off-the-shelf language model is fine-tuned on target"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01872","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/2506.01872/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":"2506.01872","created_at":"2026-07-05T11:14:20.723803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01872v1","created_at":"2026-07-05T11:14:20.723803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01872","created_at":"2026-07-05T11:14:20.723803+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZRHIQYI55HT","created_at":"2026-07-05T11:14:20.723803+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZRHIQYI55HTFA7O","created_at":"2026-07-05T11:14:20.723803+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZRHIQYI","created_at":"2026-07-05T11:14:20.723803+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.09789","citing_title":"Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YZRHIQYI55HTFA7OYSTYDXBH3Y","json":"https://pith.science/pith/YZRHIQYI55HTFA7OYSTYDXBH3Y.json","graph_json":"https://pith.science/api/pith-number/YZRHIQYI55HTFA7OYSTYDXBH3Y/graph.json","events_json":"https://pith.science/api/pith-number/YZRHIQYI55HTFA7OYSTYDXBH3Y/events.json","paper":"https://pith.science/paper/YZRHIQYI"},"agent_actions":{"view_html":"https://pith.science/pith/YZRHIQYI55HTFA7OYSTYDXBH3Y","download_json":"https://pith.science/pith/YZRHIQYI55HTFA7OYSTYDXBH3Y.json","view_paper":"https://pith.science/paper/YZRHIQYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01872&json=true","fetch_graph":"https://pith.science/api/pith-number/YZRHIQYI55HTFA7OYSTYDXBH3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/YZRHIQYI55HTFA7OYSTYDXBH3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZRHIQYI55HTFA7OYSTYDXBH3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZRHIQYI55HTFA7OYSTYDXBH3Y/action/storage_attestation","attest_author":"https://pith.science/pith/YZRHIQYI55HTFA7OYSTYDXBH3Y/action/author_attestation","sign_citation":"https://pith.science/pith/YZRHIQYI55HTFA7OYSTYDXBH3Y/action/citation_signature","submit_replication":"https://pith.science/pith/YZRHIQYI55HTFA7OYSTYDXBH3Y/action/replication_record"}},"created_at":"2026-07-05T11:14:20.723803+00:00","updated_at":"2026-07-05T11:14:20.723803+00:00"}