{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MHTQAS33N5FNE5TRMD4X444HB4","short_pith_number":"pith:MHTQAS33","schema_version":"1.0","canonical_sha256":"61e7004b7b6f4ad2767160f97e73870f3f1bcbbff6808612348783ad2d9af151","source":{"kind":"arxiv","id":"2607.04974","version":1},"attestation_state":"computed","paper":{"title":"A Comprehensive Study of Implementation Bugs in Multi-modal Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chang Yue, Fuman Xie, Guangdong Bai, Kai Chen, Lei Bu, Shangqing Liu, Suwan Li, Yile Wang","submitted_at":"2026-07-06T12:04:49Z","abstract_excerpt":"Multi-Modal Agents (M-agents), empowered by Large Language Models (LLMs), excel in various complex, open-world scenarios such as autonomous driving and robotics. However, their unique requirements to interact with dynamic and diverse multi-modal environments introduce novel implementation challenges beyond those faced by traditional agents. Outdated perception, untrustworthy planning and inapplicable execution could cause traffic accident and financial loss. Despite growing study on agent issues, there has not been a systematic study focusing on M-agent-specific implementation bugs. To address"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.04974","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-06T12:04:49Z","cross_cats_sorted":[],"title_canon_sha256":"9ad91fb6adf95df41cf8822f9540c0650f0b5e636cdf1c80702538ea59d370d5","abstract_canon_sha256":"1b148f92c0e64b6d874a887fdee1465d44e91a78b01e032c4eb049bfcc33ac81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:20:16.384772Z","signature_b64":"33RizuD8/I6ZW28z29rdaAdvKppJIREzfnJWA29kOu59b33iAdFv8VnzBGM6c5fMoecxLugnueSKWT4jMX0QBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61e7004b7b6f4ad2767160f97e73870f3f1bcbbff6808612348783ad2d9af151","last_reissued_at":"2026-07-07T02:20:16.384248Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:20:16.384248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comprehensive Study of Implementation Bugs in Multi-modal Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chang Yue, Fuman Xie, Guangdong Bai, Kai Chen, Lei Bu, Shangqing Liu, Suwan Li, Yile Wang","submitted_at":"2026-07-06T12:04:49Z","abstract_excerpt":"Multi-Modal Agents (M-agents), empowered by Large Language Models (LLMs), excel in various complex, open-world scenarios such as autonomous driving and robotics. However, their unique requirements to interact with dynamic and diverse multi-modal environments introduce novel implementation challenges beyond those faced by traditional agents. Outdated perception, untrustworthy planning and inapplicable execution could cause traffic accident and financial loss. Despite growing study on agent issues, there has not been a systematic study focusing on M-agent-specific implementation bugs. To address"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04974","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/2607.04974/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.04974","created_at":"2026-07-07T02:20:16.384342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04974v1","created_at":"2026-07-07T02:20:16.384342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04974","created_at":"2026-07-07T02:20:16.384342+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHTQAS33N5FN","created_at":"2026-07-07T02:20:16.384342+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHTQAS33N5FNE5TR","created_at":"2026-07-07T02:20:16.384342+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHTQAS33","created_at":"2026-07-07T02:20:16.384342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MHTQAS33N5FNE5TRMD4X444HB4","json":"https://pith.science/pith/MHTQAS33N5FNE5TRMD4X444HB4.json","graph_json":"https://pith.science/api/pith-number/MHTQAS33N5FNE5TRMD4X444HB4/graph.json","events_json":"https://pith.science/api/pith-number/MHTQAS33N5FNE5TRMD4X444HB4/events.json","paper":"https://pith.science/paper/MHTQAS33"},"agent_actions":{"view_html":"https://pith.science/pith/MHTQAS33N5FNE5TRMD4X444HB4","download_json":"https://pith.science/pith/MHTQAS33N5FNE5TRMD4X444HB4.json","view_paper":"https://pith.science/paper/MHTQAS33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04974&json=true","fetch_graph":"https://pith.science/api/pith-number/MHTQAS33N5FNE5TRMD4X444HB4/graph.json","fetch_events":"https://pith.science/api/pith-number/MHTQAS33N5FNE5TRMD4X444HB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHTQAS33N5FNE5TRMD4X444HB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHTQAS33N5FNE5TRMD4X444HB4/action/storage_attestation","attest_author":"https://pith.science/pith/MHTQAS33N5FNE5TRMD4X444HB4/action/author_attestation","sign_citation":"https://pith.science/pith/MHTQAS33N5FNE5TRMD4X444HB4/action/citation_signature","submit_replication":"https://pith.science/pith/MHTQAS33N5FNE5TRMD4X444HB4/action/replication_record"}},"created_at":"2026-07-07T02:20:16.384342+00:00","updated_at":"2026-07-07T02:20:16.384342+00:00"}