{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TRDYRXUQMLQYLETZSQKOGYTX24","short_pith_number":"pith:TRDYRXUQ","canonical_record":{"source":{"id":"2505.04623","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T17:59:49Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f56607595f4f18c047898dfe176d43d76c11c8f6915652fdeea4f0c032b61436","abstract_canon_sha256":"ff8f037bcb4a441fc2e2d451c269e1b4214b53984df7c55952df89c236df61f0"},"schema_version":"1.0"},"canonical_sha256":"9c4788de9062e18592799414e36277d70bf44e13c437c500b145ca593f2a29ad","source":{"kind":"arxiv","id":"2505.04623","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04623","created_at":"2026-07-05T11:23:48Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04623v1","created_at":"2026-07-05T11:23:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04623","created_at":"2026-07-05T11:23:48Z"},{"alias_kind":"pith_short_12","alias_value":"TRDYRXUQMLQY","created_at":"2026-07-05T11:23:48Z"},{"alias_kind":"pith_short_16","alias_value":"TRDYRXUQMLQYLETZ","created_at":"2026-07-05T11:23:48Z"},{"alias_kind":"pith_short_8","alias_value":"TRDYRXUQ","created_at":"2026-07-05T11:23:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TRDYRXUQMLQYLETZSQKOGYTX24","target":"record","payload":{"canonical_record":{"source":{"id":"2505.04623","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T17:59:49Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f56607595f4f18c047898dfe176d43d76c11c8f6915652fdeea4f0c032b61436","abstract_canon_sha256":"ff8f037bcb4a441fc2e2d451c269e1b4214b53984df7c55952df89c236df61f0"},"schema_version":"1.0"},"canonical_sha256":"9c4788de9062e18592799414e36277d70bf44e13c437c500b145ca593f2a29ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:48.584682Z","signature_b64":"eOB87bJfYLeLXNfJPGVqSfgoTizW3WdijkRXbQjTiOnIpQio1tgkkU1NBF5vSrIzd21++WHar5dGJP9SoczlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c4788de9062e18592799414e36277d70bf44e13c437c500b145ca593f2a29ad","last_reissued_at":"2026-07-05T11:23:48.584186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:48.584186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.04623","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":"2026-07-05T11:23:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"52lIhj9Awmm9Hs43FznE7iNf9MQt06b4L7ToPILhPRQlsOf0iEdYyz9iNpnXQLR6zrg9tQh6/ql+uh4Qpo06Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:07:15.296252Z"},"content_sha256":"6e10ea425a69446c188111a820ac8e2fae747e8f77df62291605fdd671165571","schema_version":"1.0","event_id":"sha256:6e10ea425a69446c188111a820ac8e2fae747e8f77df62291605fdd671165571"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TRDYRXUQMLQYLETZSQKOGYTX24","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CV","authors_text":"Chi-Wing Fu, Jifeng Dai, Pheng-Ann Heng, Wenhai Wang, Xiaowei Hu, Zhenghao Xing","submitted_at":"2025-05-07T17:59:49Z","abstract_excerpt":"Multimodal large language models (MLLMs) have advanced perception across text, vision, and audio, yet they often struggle with structured cross-modal reasoning, particularly when integrating audio and visual signals. We introduce EchoInk-R1, a reinforcement learning framework that enhances such reasoning in MLLMs. Built upon the Qwen2.5-Omni-7B foundation and optimized with Group Relative Policy Optimization (GRPO), EchoInk-R1 tackles multiple-choice question answering over synchronized audio-image pairs. To enable this, we curate AVQA-R1-6K, a dataset pairing such audio-image inputs with mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04623","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/2505.04623/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":"2026-07-05T11:23:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hiP0GNaH5jS/4diqsjdEJ6hXgNMTrjJ1o3YwgNNvxj1UwYDmrBTQZygUmvLzh9AnTJjVXhptho8Mi5zTyoYuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:07:15.296765Z"},"content_sha256":"d2b8f32b08f6f62c9b8d9ace7a7a2e45c6c0d612e9c5cbb1ce04b45c2421ebca","schema_version":"1.0","event_id":"sha256:d2b8f32b08f6f62c9b8d9ace7a7a2e45c6c0d612e9c5cbb1ce04b45c2421ebca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TRDYRXUQMLQYLETZSQKOGYTX24/bundle.json","state_url":"https://pith.science/pith/TRDYRXUQMLQYLETZSQKOGYTX24/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TRDYRXUQMLQYLETZSQKOGYTX24/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":"2026-08-07T18:07:15Z","links":{"resolver":"https://pith.science/pith/TRDYRXUQMLQYLETZSQKOGYTX24","bundle":"https://pith.science/pith/TRDYRXUQMLQYLETZSQKOGYTX24/bundle.json","state":"https://pith.science/pith/TRDYRXUQMLQYLETZSQKOGYTX24/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TRDYRXUQMLQYLETZSQKOGYTX24/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TRDYRXUQMLQYLETZSQKOGYTX24","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":"ff8f037bcb4a441fc2e2d451c269e1b4214b53984df7c55952df89c236df61f0","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T17:59:49Z","title_canon_sha256":"f56607595f4f18c047898dfe176d43d76c11c8f6915652fdeea4f0c032b61436"},"schema_version":"1.0","source":{"id":"2505.04623","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04623","created_at":"2026-07-05T11:23:48Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04623v1","created_at":"2026-07-05T11:23:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04623","created_at":"2026-07-05T11:23:48Z"},{"alias_kind":"pith_short_12","alias_value":"TRDYRXUQMLQY","created_at":"2026-07-05T11:23:48Z"},{"alias_kind":"pith_short_16","alias_value":"TRDYRXUQMLQYLETZ","created_at":"2026-07-05T11:23:48Z"},{"alias_kind":"pith_short_8","alias_value":"TRDYRXUQ","created_at":"2026-07-05T11:23:48Z"}],"graph_snapshots":[{"event_id":"sha256:d2b8f32b08f6f62c9b8d9ace7a7a2e45c6c0d612e9c5cbb1ce04b45c2421ebca","target":"graph","created_at":"2026-07-05T11:23:48Z","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/2505.04623/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have advanced perception across text, vision, and audio, yet they often struggle with structured cross-modal reasoning, particularly when integrating audio and visual signals. We introduce EchoInk-R1, a reinforcement learning framework that enhances such reasoning in MLLMs. Built upon the Qwen2.5-Omni-7B foundation and optimized with Group Relative Policy Optimization (GRPO), EchoInk-R1 tackles multiple-choice question answering over synchronized audio-image pairs. To enable this, we curate AVQA-R1-6K, a dataset pairing such audio-image inputs with mult","authors_text":"Chi-Wing Fu, Jifeng Dai, Pheng-Ann Heng, Wenhai Wang, Xiaowei Hu, Zhenghao Xing","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T17:59:49Z","title":"EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04623","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":"sha256:6e10ea425a69446c188111a820ac8e2fae747e8f77df62291605fdd671165571","target":"record","created_at":"2026-07-05T11:23:48Z","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":"ff8f037bcb4a441fc2e2d451c269e1b4214b53984df7c55952df89c236df61f0","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T17:59:49Z","title_canon_sha256":"f56607595f4f18c047898dfe176d43d76c11c8f6915652fdeea4f0c032b61436"},"schema_version":"1.0","source":{"id":"2505.04623","kind":"arxiv","version":1}},"canonical_sha256":"9c4788de9062e18592799414e36277d70bf44e13c437c500b145ca593f2a29ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c4788de9062e18592799414e36277d70bf44e13c437c500b145ca593f2a29ad","first_computed_at":"2026-07-05T11:23:48.584186Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:48.584186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eOB87bJfYLeLXNfJPGVqSfgoTizW3WdijkRXbQjTiOnIpQio1tgkkU1NBF5vSrIzd21++WHar5dGJP9SoczlBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:48.584682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.04623","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e10ea425a69446c188111a820ac8e2fae747e8f77df62291605fdd671165571","sha256:d2b8f32b08f6f62c9b8d9ace7a7a2e45c6c0d612e9c5cbb1ce04b45c2421ebca"],"state_sha256":"0e6e20908c1857843e11029d3f4f22bbfc94cf832904a5fc97559513efddd00e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3ATtx72KPdm3V1GzdrqMh6bmYE1iHo8i+m4IuEwjPrQs0nux4o4Ox7n+PPiqbbbrBH0hW7pCXCABfiZa1jCnAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:07:15.300831Z","bundle_sha256":"a8dffb3475e7a51f590711615fa0fcd00acac5fbf13279c53964cc3003961687"}}