{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QSP6PRUVKLRXG7FPQNTSTTRER3","short_pith_number":"pith:QSP6PRUV","canonical_record":{"source":{"id":"2306.09093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T12:45:25Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"5b8e807f4c12b9a98570a38e22bf457556114fff4590051fcedceab2d0d4bd05","abstract_canon_sha256":"2a5296d6910aad2f98d0051243068622e5f1f5d1da09aa772f79f2cef3ad5207"},"schema_version":"1.0"},"canonical_sha256":"849fe7c69552e3737caf836729ce248ec621ab4246d8ac2eda156535d14000ac","source":{"kind":"arxiv","id":"2306.09093","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09093","created_at":"2026-07-05T06:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09093v1","created_at":"2026-07-05T06:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09093","created_at":"2026-07-05T06:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"QSP6PRUVKLRX","created_at":"2026-07-05T06:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"QSP6PRUVKLRXG7FP","created_at":"2026-07-05T06:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"QSP6PRUV","created_at":"2026-07-05T06:21:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QSP6PRUVKLRXG7FPQNTSTTRER3","target":"record","payload":{"canonical_record":{"source":{"id":"2306.09093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T12:45:25Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"5b8e807f4c12b9a98570a38e22bf457556114fff4590051fcedceab2d0d4bd05","abstract_canon_sha256":"2a5296d6910aad2f98d0051243068622e5f1f5d1da09aa772f79f2cef3ad5207"},"schema_version":"1.0"},"canonical_sha256":"849fe7c69552e3737caf836729ce248ec621ab4246d8ac2eda156535d14000ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:08.527751Z","signature_b64":"I8n3ntGRbKx7LnLwR9BoI4EN8V/J5ayFy8OIQ+7tT5MfdEa7/a2hfX7kfjn2tG+p3Aqltr4J9tLILsNHVbObCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"849fe7c69552e3737caf836729ce248ec621ab4246d8ac2eda156535d14000ac","last_reissued_at":"2026-07-05T06:21:08.527101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:08.527101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.09093","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":"2026-07-05T06:21:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R5K6wqsNL78vg0lNx0qU8xAkZk60eMFid2mQGNIJlNGHLJrFmTeiGZ2G4nPR43iFYTike6yu95Tde4v9z0TfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:54:52.604320Z"},"content_sha256":"fcdda6aec60e2acce024ddb97ae055cb0741fdebff29a78653fa4e9120354e4e","schema_version":"1.0","event_id":"sha256:fcdda6aec60e2acce024ddb97ae055cb0741fdebff29a78653fa4e9120354e4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QSP6PRUVKLRXG7FPQNTSTTRER3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Bingshuai Liu, Chenyang Lyu, Longyue Wang, Minghao Wu, Shuming Shi, Xinting Huang, Zefeng Du, Zhaopeng Tu","submitted_at":"2023-06-15T12:45:25Z","abstract_excerpt":"Although instruction-tuned large language models (LLMs) have exhibited remarkable capabilities across various NLP tasks, their effectiveness on other data modalities beyond text has not been fully studied. In this work, we propose Macaw-LLM, a novel multi-modal LLM that seamlessly integrates visual, audio, and textual information. Macaw-LLM consists of three main components: a modality module for encoding multi-modal data, a cognitive module for harnessing pretrained LLMs, and an alignment module for harmonizing diverse representations. Our novel alignment module seamlessly bridges multi-modal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09093","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/2306.09093/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":"2026-07-05T06:21:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fBK5UTaa5v8uW1aX8wWkmm+Y4IYTCARawKPXm3sOlSFf3Rq9o17IpCbdcA36gzL6+LSW7nfqkfxVIPs34XUrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:54:52.605155Z"},"content_sha256":"6b9760119285ce29c161fb0aaa7a7ebb91b3ef11d01d131603731c25503d0484","schema_version":"1.0","event_id":"sha256:6b9760119285ce29c161fb0aaa7a7ebb91b3ef11d01d131603731c25503d0484"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QSP6PRUVKLRXG7FPQNTSTTRER3/bundle.json","state_url":"https://pith.science/pith/QSP6PRUVKLRXG7FPQNTSTTRER3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QSP6PRUVKLRXG7FPQNTSTTRER3/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":"2026-08-04T12:54:52Z","links":{"resolver":"https://pith.science/pith/QSP6PRUVKLRXG7FPQNTSTTRER3","bundle":"https://pith.science/pith/QSP6PRUVKLRXG7FPQNTSTTRER3/bundle.json","state":"https://pith.science/pith/QSP6PRUVKLRXG7FPQNTSTTRER3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QSP6PRUVKLRXG7FPQNTSTTRER3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QSP6PRUVKLRXG7FPQNTSTTRER3","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":"2a5296d6910aad2f98d0051243068622e5f1f5d1da09aa772f79f2cef3ad5207","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T12:45:25Z","title_canon_sha256":"5b8e807f4c12b9a98570a38e22bf457556114fff4590051fcedceab2d0d4bd05"},"schema_version":"1.0","source":{"id":"2306.09093","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09093","created_at":"2026-07-05T06:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09093v1","created_at":"2026-07-05T06:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09093","created_at":"2026-07-05T06:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"QSP6PRUVKLRX","created_at":"2026-07-05T06:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"QSP6PRUVKLRXG7FP","created_at":"2026-07-05T06:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"QSP6PRUV","created_at":"2026-07-05T06:21:08Z"}],"graph_snapshots":[{"event_id":"sha256:6b9760119285ce29c161fb0aaa7a7ebb91b3ef11d01d131603731c25503d0484","target":"graph","created_at":"2026-07-05T06:21:08Z","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/2306.09093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although instruction-tuned large language models (LLMs) have exhibited remarkable capabilities across various NLP tasks, their effectiveness on other data modalities beyond text has not been fully studied. In this work, we propose Macaw-LLM, a novel multi-modal LLM that seamlessly integrates visual, audio, and textual information. Macaw-LLM consists of three main components: a modality module for encoding multi-modal data, a cognitive module for harnessing pretrained LLMs, and an alignment module for harmonizing diverse representations. Our novel alignment module seamlessly bridges multi-modal","authors_text":"Bingshuai Liu, Chenyang Lyu, Longyue Wang, Minghao Wu, Shuming Shi, Xinting Huang, Zefeng Du, Zhaopeng Tu","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T12:45:25Z","title":"Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09093","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:fcdda6aec60e2acce024ddb97ae055cb0741fdebff29a78653fa4e9120354e4e","target":"record","created_at":"2026-07-05T06:21:08Z","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":"2a5296d6910aad2f98d0051243068622e5f1f5d1da09aa772f79f2cef3ad5207","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T12:45:25Z","title_canon_sha256":"5b8e807f4c12b9a98570a38e22bf457556114fff4590051fcedceab2d0d4bd05"},"schema_version":"1.0","source":{"id":"2306.09093","kind":"arxiv","version":1}},"canonical_sha256":"849fe7c69552e3737caf836729ce248ec621ab4246d8ac2eda156535d14000ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"849fe7c69552e3737caf836729ce248ec621ab4246d8ac2eda156535d14000ac","first_computed_at":"2026-07-05T06:21:08.527101Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:21:08.527101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I8n3ntGRbKx7LnLwR9BoI4EN8V/J5ayFy8OIQ+7tT5MfdEa7/a2hfX7kfjn2tG+p3Aqltr4J9tLILsNHVbObCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:21:08.527751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09093","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcdda6aec60e2acce024ddb97ae055cb0741fdebff29a78653fa4e9120354e4e","sha256:6b9760119285ce29c161fb0aaa7a7ebb91b3ef11d01d131603731c25503d0484"],"state_sha256":"5b438aa0f14fe6ca4dabbc0bac34cc04c77fa20992c97f80c3318ba06c2b25d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lKPvoBF68eNzuQzYuyFxRNtD54wHi/aNGnRBoKeUdJcqtg16SYW98Cw7OGPbpf/OKHSi1FJrZgayTX2TzOevCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:54:52.611063Z","bundle_sha256":"abd2b04b4d707e02bddc8703e76774db7fe08d2363e318b4036a901497e35a13"}}