{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:APF7BJU727S3KL7SA5E27S5TAZ","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":"d5f1dd51d51f20b97807f5b2d242207739be6bad0534c694963fb5176f36c21e","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-27T22:50:51Z","title_canon_sha256":"783daa7fd0bf2182edb32b0212df4bdcfa3df34252f4e81de59ef283deb3cbb6"},"schema_version":"1.0","source":{"id":"2309.16058","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16058","created_at":"2026-07-05T06:55:10Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16058v1","created_at":"2026-07-05T06:55:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16058","created_at":"2026-07-05T06:55:10Z"},{"alias_kind":"pith_short_12","alias_value":"APF7BJU727S3","created_at":"2026-07-05T06:55:10Z"},{"alias_kind":"pith_short_16","alias_value":"APF7BJU727S3KL7S","created_at":"2026-07-05T06:55:10Z"},{"alias_kind":"pith_short_8","alias_value":"APF7BJU7","created_at":"2026-07-05T06:55:10Z"}],"graph_snapshots":[{"event_id":"sha256:f43a10f38bbd05a7997a06748fb20604b963cc9c3ea67dc6ff2186b4dce5bb3b","target":"graph","created_at":"2026-07-05T06:55:10Z","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/2309.16058/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Any-Modality Augmented Language Model (AnyMAL), a unified model that reasons over diverse input modality signals (i.e. text, image, video, audio, IMU motion sensor), and generates textual responses. AnyMAL inherits the powerful text-based reasoning abilities of the state-of-the-art LLMs including LLaMA-2 (70B), and converts modality-specific signals to the joint textual space through a pre-trained aligner module. To further strengthen the multimodal LLM's capabilities, we fine-tune the model with a multimodal instruction set manually collected to cover diverse topics and tasks beyon","authors_text":"Andrea Madotto, Anuj Kumar, Babak Damavandi, Chun-Fu Yeh, Kavya Srinet, Matt Smith, Peyman Heidari, Prakash Murugesan, Seungwhan Moon, Shashank Jain, Tushar Nagarajan, Yue Liu, Zhaojiang Lin","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-27T22:50:51Z","title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16058","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:f5377e5498b71acaabb8892c44045cdcf56a6b5674ba78d32892eb04f40209aa","target":"record","created_at":"2026-07-05T06:55:10Z","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":"d5f1dd51d51f20b97807f5b2d242207739be6bad0534c694963fb5176f36c21e","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-27T22:50:51Z","title_canon_sha256":"783daa7fd0bf2182edb32b0212df4bdcfa3df34252f4e81de59ef283deb3cbb6"},"schema_version":"1.0","source":{"id":"2309.16058","kind":"arxiv","version":1}},"canonical_sha256":"03cbf0a69fd7e5b52ff20749afcbb306684b36ed43a8e381efd80da3ec281949","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03cbf0a69fd7e5b52ff20749afcbb306684b36ed43a8e381efd80da3ec281949","first_computed_at":"2026-07-05T06:55:10.724405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:55:10.724405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EFFNw2MB0ZYuwb8UfA0RAI0VmYfsXGFtkQZTD/zEdcuh1qd0fBoqkTELQX3aQ9CyOyR70B0mnW1WTaQ+1Xp9DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:55:10.724809Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.16058","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5377e5498b71acaabb8892c44045cdcf56a6b5674ba78d32892eb04f40209aa","sha256:f43a10f38bbd05a7997a06748fb20604b963cc9c3ea67dc6ff2186b4dce5bb3b"],"state_sha256":"b78c68f7dc6449f184e0e2935863b35068d2e7a4eb4ef87b146f3597ed6199ab"}