{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EEK5DJ5IQMWUHRC54DBVTODT3L","short_pith_number":"pith:EEK5DJ5I","canonical_record":{"source":{"id":"2405.19335","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T17:59:58Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"1a0115b8b84440618db0aacbedeafed8cbfc0ad5cc7e03caf4b9dba0773f5c01","abstract_canon_sha256":"f22539a41af7dc582f61cdb27bdd40ba3e1edd199c83117c6fbcf7da16e62926"},"schema_version":"1.0"},"canonical_sha256":"2115d1a7a8832d43c45de0c359b873dadfd96050cbc83f3cef0a7d1a0c5676bb","source":{"kind":"arxiv","id":"2405.19335","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19335","created_at":"2026-07-05T08:24:51Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19335v1","created_at":"2026-07-05T08:24:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19335","created_at":"2026-07-05T08:24:51Z"},{"alias_kind":"pith_short_12","alias_value":"EEK5DJ5IQMWU","created_at":"2026-07-05T08:24:51Z"},{"alias_kind":"pith_short_16","alias_value":"EEK5DJ5IQMWUHRC5","created_at":"2026-07-05T08:24:51Z"},{"alias_kind":"pith_short_8","alias_value":"EEK5DJ5I","created_at":"2026-07-05T08:24:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EEK5DJ5IQMWUHRC54DBVTODT3L","target":"record","payload":{"canonical_record":{"source":{"id":"2405.19335","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T17:59:58Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"1a0115b8b84440618db0aacbedeafed8cbfc0ad5cc7e03caf4b9dba0773f5c01","abstract_canon_sha256":"f22539a41af7dc582f61cdb27bdd40ba3e1edd199c83117c6fbcf7da16e62926"},"schema_version":"1.0"},"canonical_sha256":"2115d1a7a8832d43c45de0c359b873dadfd96050cbc83f3cef0a7d1a0c5676bb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:51.259720Z","signature_b64":"aUzJKNmq+kWC3qmKxkisLzNHsCvfErte3QQltJpoS+r0N+YslyAyR89LZcG8V8Wo0MsITJQ06SEw/Ar4qQoICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2115d1a7a8832d43c45de0c359b873dadfd96050cbc83f3cef0a7d1a0c5676bb","last_reissued_at":"2026-07-05T08:24:51.259204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:51.259204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.19335","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":"2026-07-05T08:24:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1MDQUCvfEtyTG8Rs7XPQbq4yYwv8RY3JDQKZiD9rc0gqAPsy7BXHwvCY4E7L4cgrDyvXaKXmKyRHw7GpZvFNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:09:11.099342Z"},"content_sha256":"57d837fbbcabef475569ef52254cfb796568d682b6823b7551211dd3bbb52591","schema_version":"1.0","event_id":"sha256:57d837fbbcabef475569ef52254cfb796568d682b6823b7551211dd3bbb52591"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EEK5DJ5IQMWUHRC54DBVTODT3L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"X-VILA: Cross-Modality Alignment for Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Tao, Dan Xu, De-An Huang, Hanrong Ye, Hongxu Yin, Jan Kautz, Pavlo Molchanov, Song Han, Wei Ping, Yao Lu, Zhiding Yu","submitted_at":"2024-05-29T17:59:58Z","abstract_excerpt":"We introduce X-VILA, an omni-modality model designed to extend the capabilities of large language models (LLMs) by incorporating image, video, and audio modalities. By aligning modality-specific encoders with LLM inputs and diffusion decoders with LLM outputs, X-VILA achieves cross-modality understanding, reasoning, and generation. To facilitate this cross-modality alignment, we curate an effective interleaved any-to-any modality instruction-following dataset. Furthermore, we identify a significant problem with the current cross-modality alignment method, which results in visual information lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19335","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/2405.19335/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":"2026-07-05T08:24:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0TxJA6DXNT/zbqXV4nCySqdxaINr6MEopCRbU/m6RdNYXRCfM0LCe897TCHic3hA6UvASSPba9XPA3oI2leKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:09:11.099971Z"},"content_sha256":"c980ddba758dcd49581a7cbc0e2023809fc489698a918632747106e588ed493a","schema_version":"1.0","event_id":"sha256:c980ddba758dcd49581a7cbc0e2023809fc489698a918632747106e588ed493a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EEK5DJ5IQMWUHRC54DBVTODT3L/bundle.json","state_url":"https://pith.science/pith/EEK5DJ5IQMWUHRC54DBVTODT3L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EEK5DJ5IQMWUHRC54DBVTODT3L/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":"2026-08-04T09:09:11Z","links":{"resolver":"https://pith.science/pith/EEK5DJ5IQMWUHRC54DBVTODT3L","bundle":"https://pith.science/pith/EEK5DJ5IQMWUHRC54DBVTODT3L/bundle.json","state":"https://pith.science/pith/EEK5DJ5IQMWUHRC54DBVTODT3L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EEK5DJ5IQMWUHRC54DBVTODT3L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EEK5DJ5IQMWUHRC54DBVTODT3L","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":"f22539a41af7dc582f61cdb27bdd40ba3e1edd199c83117c6fbcf7da16e62926","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T17:59:58Z","title_canon_sha256":"1a0115b8b84440618db0aacbedeafed8cbfc0ad5cc7e03caf4b9dba0773f5c01"},"schema_version":"1.0","source":{"id":"2405.19335","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19335","created_at":"2026-07-05T08:24:51Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19335v1","created_at":"2026-07-05T08:24:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19335","created_at":"2026-07-05T08:24:51Z"},{"alias_kind":"pith_short_12","alias_value":"EEK5DJ5IQMWU","created_at":"2026-07-05T08:24:51Z"},{"alias_kind":"pith_short_16","alias_value":"EEK5DJ5IQMWUHRC5","created_at":"2026-07-05T08:24:51Z"},{"alias_kind":"pith_short_8","alias_value":"EEK5DJ5I","created_at":"2026-07-05T08:24:51Z"}],"graph_snapshots":[{"event_id":"sha256:c980ddba758dcd49581a7cbc0e2023809fc489698a918632747106e588ed493a","target":"graph","created_at":"2026-07-05T08:24:51Z","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/2405.19335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce X-VILA, an omni-modality model designed to extend the capabilities of large language models (LLMs) by incorporating image, video, and audio modalities. By aligning modality-specific encoders with LLM inputs and diffusion decoders with LLM outputs, X-VILA achieves cross-modality understanding, reasoning, and generation. To facilitate this cross-modality alignment, we curate an effective interleaved any-to-any modality instruction-following dataset. Furthermore, we identify a significant problem with the current cross-modality alignment method, which results in visual information lo","authors_text":"Andrew Tao, Dan Xu, De-An Huang, Hanrong Ye, Hongxu Yin, Jan Kautz, Pavlo Molchanov, Song Han, Wei Ping, Yao Lu, Zhiding Yu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T17:59:58Z","title":"X-VILA: Cross-Modality Alignment for Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19335","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":"sha256:57d837fbbcabef475569ef52254cfb796568d682b6823b7551211dd3bbb52591","target":"record","created_at":"2026-07-05T08:24:51Z","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":"f22539a41af7dc582f61cdb27bdd40ba3e1edd199c83117c6fbcf7da16e62926","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T17:59:58Z","title_canon_sha256":"1a0115b8b84440618db0aacbedeafed8cbfc0ad5cc7e03caf4b9dba0773f5c01"},"schema_version":"1.0","source":{"id":"2405.19335","kind":"arxiv","version":1}},"canonical_sha256":"2115d1a7a8832d43c45de0c359b873dadfd96050cbc83f3cef0a7d1a0c5676bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2115d1a7a8832d43c45de0c359b873dadfd96050cbc83f3cef0a7d1a0c5676bb","first_computed_at":"2026-07-05T08:24:51.259204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:51.259204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aUzJKNmq+kWC3qmKxkisLzNHsCvfErte3QQltJpoS+r0N+YslyAyR89LZcG8V8Wo0MsITJQ06SEw/Ar4qQoICw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:51.259720Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19335","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57d837fbbcabef475569ef52254cfb796568d682b6823b7551211dd3bbb52591","sha256:c980ddba758dcd49581a7cbc0e2023809fc489698a918632747106e588ed493a"],"state_sha256":"2395ace51f223644499148657442c3e64150501e51df94295dd40c73236676c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gIZHZ47Z0ZhtWCfSIwgucy5/87XylshcOZSFZ4H/8+9+A3E2Ew87XMukojh2shnm85vb7OSNbYDZyp/7QHBKAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:09:11.105358Z","bundle_sha256":"faf12d60ceabb7a1a64eeb2519d51bd003b5a293d9315d99e4dc1fd8f4e84324"}}