{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YZRHIQYI55HTFA7OYSTYDXBH3Y","short_pith_number":"pith:YZRHIQYI","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"},"canonical_sha256":"c662744308ef4f3283eec4a781dc27de113820444bbceb2b470de39087b6eb7e","source":{"kind":"arxiv","id":"2506.01872","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01872","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01872v1","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01872","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"pith_short_12","alias_value":"YZRHIQYI55HT","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"pith_short_16","alias_value":"YZRHIQYI55HTFA7O","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"pith_short_8","alias_value":"YZRHIQYI","created_at":"2026-07-05T11:14:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YZRHIQYI55HTFA7OYSTYDXBH3Y","target":"record","payload":{"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"},"canonical_sha256":"c662744308ef4f3283eec4a781dc27de113820444bbceb2b470de39087b6eb7e","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"},"source_kind":"arxiv","source_id":"2506.01872","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":"2026-07-05T11:14:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7qYmhcyk3zh+LfeRFsiS8ncE/ap6wJc434LgARRs/NFpFPzZcsVcfIZYLtWWRsn6bu6oExpv2vyFhpN0LcgkCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:57:13.017823Z"},"content_sha256":"deedddd4b0fa67668beb68eae0ad17bc1b11c3e39003df6a1574885a24fedfa0","schema_version":"1.0","event_id":"sha256:deedddd4b0fa67668beb68eae0ad17bc1b11c3e39003df6a1574885a24fedfa0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YZRHIQYI55HTFA7OYSTYDXBH3Y","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oUUimZuURlACoTf07LhoEwiauWRIzPcLrcbpVFGKeZRkfT4iaVepo19WcAGmuPaKRD4q6hBOCttFXSKlPcLsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:57:13.018330Z"},"content_sha256":"b82bf8eaefb4d7dc201ad389ba2ea7ffa941479b79b557c4d0601437989d9682","schema_version":"1.0","event_id":"sha256:b82bf8eaefb4d7dc201ad389ba2ea7ffa941479b79b557c4d0601437989d9682"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YZRHIQYI55HTFA7OYSTYDXBH3Y/bundle.json","state_url":"https://pith.science/pith/YZRHIQYI55HTFA7OYSTYDXBH3Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YZRHIQYI55HTFA7OYSTYDXBH3Y/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":"2026-08-08T20:57:13Z","links":{"resolver":"https://pith.science/pith/YZRHIQYI55HTFA7OYSTYDXBH3Y","bundle":"https://pith.science/pith/YZRHIQYI55HTFA7OYSTYDXBH3Y/bundle.json","state":"https://pith.science/pith/YZRHIQYI55HTFA7OYSTYDXBH3Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YZRHIQYI55HTFA7OYSTYDXBH3Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YZRHIQYI55HTFA7OYSTYDXBH3Y","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":"2a27a1ade5aa901013a0bd837d1bb0cb43cf11cd0baf842c983fd902b7a1fd69","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T17:01:40Z","title_canon_sha256":"f7b493c1b1e0100bc5ee012a61e9b070d5f52db3ed32a8502375da8a05ea8659"},"schema_version":"1.0","source":{"id":"2506.01872","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01872","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01872v1","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01872","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"pith_short_12","alias_value":"YZRHIQYI55HT","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"pith_short_16","alias_value":"YZRHIQYI55HTFA7O","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"pith_short_8","alias_value":"YZRHIQYI","created_at":"2026-07-05T11:14:20Z"}],"graph_snapshots":[{"event_id":"sha256:b82bf8eaefb4d7dc201ad389ba2ea7ffa941479b79b557c4d0601437989d9682","target":"graph","created_at":"2026-07-05T11:14:20Z","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/2506.01872/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kai Zhang, Muhao Chen, Tinghui Zhu, Yu Su","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T17:01:40Z","title":"Is Extending Modality The Right Path Towards Omni-Modality?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01872","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:deedddd4b0fa67668beb68eae0ad17bc1b11c3e39003df6a1574885a24fedfa0","target":"record","created_at":"2026-07-05T11:14:20Z","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":"2a27a1ade5aa901013a0bd837d1bb0cb43cf11cd0baf842c983fd902b7a1fd69","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T17:01:40Z","title_canon_sha256":"f7b493c1b1e0100bc5ee012a61e9b070d5f52db3ed32a8502375da8a05ea8659"},"schema_version":"1.0","source":{"id":"2506.01872","kind":"arxiv","version":1}},"canonical_sha256":"c662744308ef4f3283eec4a781dc27de113820444bbceb2b470de39087b6eb7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c662744308ef4f3283eec4a781dc27de113820444bbceb2b470de39087b6eb7e","first_computed_at":"2026-07-05T11:14:20.723750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:20.723750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X6vAWB35wXj4n2NSgXvVfj+NoUDrVIyxbnDOqdvewwYNtgP/UgwtgR1Ss3NWVzQ69mpBRlMceBEaCXLwcLcIBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:20.724207Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01872","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:deedddd4b0fa67668beb68eae0ad17bc1b11c3e39003df6a1574885a24fedfa0","sha256:b82bf8eaefb4d7dc201ad389ba2ea7ffa941479b79b557c4d0601437989d9682"],"state_sha256":"48c00e1a95e393b3116f2496f533960b896bca2f787c7c4d8929cdb364200307"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wAxPIOek8EJLZO/I6dJdokPPoBPwXPsb7eMH9eVfdZuar03P8pvXD5Kuq4drfRqamKMoMz+7uJ3gm6D8kotSAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:57:13.022996Z","bundle_sha256":"fe42075544176e4a3226b63b287f8fa9ec0630eaf7a9687b3cd05b35ae6c8d6c"}}