{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:APF7BJU727S3KL7SA5E27S5TAZ","short_pith_number":"pith:APF7BJU7","canonical_record":{"source":{"id":"2309.16058","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-27T22:50:51Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"783daa7fd0bf2182edb32b0212df4bdcfa3df34252f4e81de59ef283deb3cbb6","abstract_canon_sha256":"d5f1dd51d51f20b97807f5b2d242207739be6bad0534c694963fb5176f36c21e"},"schema_version":"1.0"},"canonical_sha256":"03cbf0a69fd7e5b52ff20749afcbb306684b36ed43a8e381efd80da3ec281949","source":{"kind":"arxiv","id":"2309.16058","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:APF7BJU727S3KL7SA5E27S5TAZ","target":"record","payload":{"canonical_record":{"source":{"id":"2309.16058","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-27T22:50:51Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"783daa7fd0bf2182edb32b0212df4bdcfa3df34252f4e81de59ef283deb3cbb6","abstract_canon_sha256":"d5f1dd51d51f20b97807f5b2d242207739be6bad0534c694963fb5176f36c21e"},"schema_version":"1.0"},"canonical_sha256":"03cbf0a69fd7e5b52ff20749afcbb306684b36ed43a8e381efd80da3ec281949","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:10.724809Z","signature_b64":"EFFNw2MB0ZYuwb8UfA0RAI0VmYfsXGFtkQZTD/zEdcuh1qd0fBoqkTELQX3aQ9CyOyR70B0mnW1WTaQ+1Xp9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03cbf0a69fd7e5b52ff20749afcbb306684b36ed43a8e381efd80da3ec281949","last_reissued_at":"2026-07-05T06:55:10.724405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:10.724405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.16058","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":"2026-07-05T06:55:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X4q/nSVk7XMitRwodpjZg6NQB6/jAlDoeSsxhcTaO1LA9U7tiB87ckmd8ROSqpBLpJEEAA2w/S4taYiyQtqoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:32:51.292187Z"},"content_sha256":"f5377e5498b71acaabb8892c44045cdcf56a6b5674ba78d32892eb04f40209aa","schema_version":"1.0","event_id":"sha256:f5377e5498b71acaabb8892c44045cdcf56a6b5674ba78d32892eb04f40209aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:APF7BJU727S3KL7SA5E27S5TAZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","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","submitted_at":"2023-09-27T22:50:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16058","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/2309.16058/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":"2026-07-05T06:55:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dmYl6DrRPqQOIsz2rfmkR665hVsI1JWKcog9WSl1Fi31p+csPgzMG8quX/c5i9XDdqzg8iYMg1/y7yrJ7Af6Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:32:51.292707Z"},"content_sha256":"f43a10f38bbd05a7997a06748fb20604b963cc9c3ea67dc6ff2186b4dce5bb3b","schema_version":"1.0","event_id":"sha256:f43a10f38bbd05a7997a06748fb20604b963cc9c3ea67dc6ff2186b4dce5bb3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/APF7BJU727S3KL7SA5E27S5TAZ/bundle.json","state_url":"https://pith.science/pith/APF7BJU727S3KL7SA5E27S5TAZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/APF7BJU727S3KL7SA5E27S5TAZ/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":"2026-08-10T05:32:51Z","links":{"resolver":"https://pith.science/pith/APF7BJU727S3KL7SA5E27S5TAZ","bundle":"https://pith.science/pith/APF7BJU727S3KL7SA5E27S5TAZ/bundle.json","state":"https://pith.science/pith/APF7BJU727S3KL7SA5E27S5TAZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/APF7BJU727S3KL7SA5E27S5TAZ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iQ3LcIAAL90qMdL4qqEunpcP5RpNzgcXVT2aclG7qLsGSN2FXyby9oqT5jXHePrY5hYAnefJAxW+bczaBHq3Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T05:32:51.296210Z","bundle_sha256":"35cb9a2fa5ae50f247220dd7c702524bd55bc5c84850aa65516773be68a9705a"}}