{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JOW3CFTNXIFMQCXMBTYEQ5JRFO","short_pith_number":"pith:JOW3CFTN","canonical_record":{"source":{"id":"2606.00579","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-30T07:04:27Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5be662cec7385b4569a93a7daadc8fb49f7b43f52a0142b48f2bc489ddc74cc8","abstract_canon_sha256":"3788a4cd6135db6dfbb3845ffc2caa2a9687c23eeca29903508fe795cde1bc32"},"schema_version":"1.0"},"canonical_sha256":"4badb1166dba0ac80aec0cf04875312b8de5154bedcd1e1a8598fea68537a98d","source":{"kind":"arxiv","id":"2606.00579","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00579","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00579v1","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00579","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"JOW3CFTNXIFM","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"JOW3CFTNXIFMQCXM","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"JOW3CFTN","created_at":"2026-06-02T01:03:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JOW3CFTNXIFMQCXMBTYEQ5JRFO","target":"record","payload":{"canonical_record":{"source":{"id":"2606.00579","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-30T07:04:27Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5be662cec7385b4569a93a7daadc8fb49f7b43f52a0142b48f2bc489ddc74cc8","abstract_canon_sha256":"3788a4cd6135db6dfbb3845ffc2caa2a9687c23eeca29903508fe795cde1bc32"},"schema_version":"1.0"},"canonical_sha256":"4badb1166dba0ac80aec0cf04875312b8de5154bedcd1e1a8598fea68537a98d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:58.814131Z","signature_b64":"M/ahHFsIUX6JZq4gQLRnjOBTjZXDj9ipB6FZuPsd70tvTXioQ+T+Czdnyebp+OODoTF57ONisaKDCQmQXRZjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4badb1166dba0ac80aec0cf04875312b8de5154bedcd1e1a8598fea68537a98d","last_reissued_at":"2026-06-02T01:03:58.813730Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:58.813730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.00579","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":"2026-06-02T01:03:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VtKshoLjf0yAoYVAAW4k+tFWn6Gv/TKb2Xg1Peks42Z3Vn1ccRbBN1nbpw0Tw2wmSX14+UgNWaj49/lx5IqzBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T02:25:49.003259Z"},"content_sha256":"94dd2a72b2b6bca1495307b1410b45181c465cdd9c74d08a84e604d8f73192cb","schema_version":"1.0","event_id":"sha256:94dd2a72b2b6bca1495307b1410b45181c465cdd9c74d08a84e604d8f73192cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JOW3CFTNXIFMQCXMBTYEQ5JRFO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sandboxed Coding Agents are Competitive Omni-modal Task Solvers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Dianqi Li, Dongping Chen, Qingyuan Shi, Tianyi Zhou, Xuanao Huang, Zhihan Hu","submitted_at":"2026-05-30T07:04:27Z","abstract_excerpt":"As multimodal LLMs increasingly target video and audio, it is often assumed that such tasks require native omnimodal models. We show that this is not always the case: coding agents with only text+image access and a sandboxed tool-use interface can match, and in several settings outperform, SOTA native omnimodal models and predefined multimodal agent scaffolds across multiple audio-video benchmarks. Our trajectory analysis suggests that their strength comes from writing code and orchestrating tools to extract relevant evidence from transcripts, frames, and other modality signals, thereby conver"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00579","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/2606.00579/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":"2026-06-02T01:03:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QWmTjhAweMBvIV1sHyLjk4bf26M+TD9lorNrrEkHuuGfBVUyA6kD2OaDsAvFaN8RhqWgMuklPqxfWfdaPf2YDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T02:25:49.003659Z"},"content_sha256":"aa28c98884a0b9b159c144816a2ffd6f71cbef4644392cd39674de1aafa083c2","schema_version":"1.0","event_id":"sha256:aa28c98884a0b9b159c144816a2ffd6f71cbef4644392cd39674de1aafa083c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JOW3CFTNXIFMQCXMBTYEQ5JRFO/bundle.json","state_url":"https://pith.science/pith/JOW3CFTNXIFMQCXMBTYEQ5JRFO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JOW3CFTNXIFMQCXMBTYEQ5JRFO/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":"2026-06-05T02:25:49Z","links":{"resolver":"https://pith.science/pith/JOW3CFTNXIFMQCXMBTYEQ5JRFO","bundle":"https://pith.science/pith/JOW3CFTNXIFMQCXMBTYEQ5JRFO/bundle.json","state":"https://pith.science/pith/JOW3CFTNXIFMQCXMBTYEQ5JRFO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JOW3CFTNXIFMQCXMBTYEQ5JRFO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JOW3CFTNXIFMQCXMBTYEQ5JRFO","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":"3788a4cd6135db6dfbb3845ffc2caa2a9687c23eeca29903508fe795cde1bc32","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-30T07:04:27Z","title_canon_sha256":"5be662cec7385b4569a93a7daadc8fb49f7b43f52a0142b48f2bc489ddc74cc8"},"schema_version":"1.0","source":{"id":"2606.00579","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00579","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00579v1","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00579","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"JOW3CFTNXIFM","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"JOW3CFTNXIFMQCXM","created_at":"2026-06-02T01:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"JOW3CFTN","created_at":"2026-06-02T01:03:58Z"}],"graph_snapshots":[{"event_id":"sha256:aa28c98884a0b9b159c144816a2ffd6f71cbef4644392cd39674de1aafa083c2","target":"graph","created_at":"2026-06-02T01:03:58Z","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/2606.00579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As multimodal LLMs increasingly target video and audio, it is often assumed that such tasks require native omnimodal models. We show that this is not always the case: coding agents with only text+image access and a sandboxed tool-use interface can match, and in several settings outperform, SOTA native omnimodal models and predefined multimodal agent scaffolds across multiple audio-video benchmarks. Our trajectory analysis suggests that their strength comes from writing code and orchestrating tools to extract relevant evidence from transcripts, frames, and other modality signals, thereby conver","authors_text":"Dianqi Li, Dongping Chen, Qingyuan Shi, Tianyi Zhou, Xuanao Huang, Zhihan Hu","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-30T07:04:27Z","title":"Sandboxed Coding Agents are Competitive Omni-modal Task Solvers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00579","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":"sha256:94dd2a72b2b6bca1495307b1410b45181c465cdd9c74d08a84e604d8f73192cb","target":"record","created_at":"2026-06-02T01:03:58Z","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":"3788a4cd6135db6dfbb3845ffc2caa2a9687c23eeca29903508fe795cde1bc32","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-30T07:04:27Z","title_canon_sha256":"5be662cec7385b4569a93a7daadc8fb49f7b43f52a0142b48f2bc489ddc74cc8"},"schema_version":"1.0","source":{"id":"2606.00579","kind":"arxiv","version":1}},"canonical_sha256":"4badb1166dba0ac80aec0cf04875312b8de5154bedcd1e1a8598fea68537a98d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4badb1166dba0ac80aec0cf04875312b8de5154bedcd1e1a8598fea68537a98d","first_computed_at":"2026-06-02T01:03:58.813730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:58.813730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M/ahHFsIUX6JZq4gQLRnjOBTjZXDj9ipB6FZuPsd70tvTXioQ+T+Czdnyebp+OODoTF57ONisaKDCQmQXRZjDg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:58.814131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00579","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94dd2a72b2b6bca1495307b1410b45181c465cdd9c74d08a84e604d8f73192cb","sha256:aa28c98884a0b9b159c144816a2ffd6f71cbef4644392cd39674de1aafa083c2"],"state_sha256":"e263c8d73c74dae0c3387ba7451b5c8c35f4f4d82db3cde16ab48993b84b2079"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4fXkmd4iKwCi76G+CPZj5cSyXwGSchwkRuKIYoC6adnlrfCsRVoaqLbQ33UNXae/PZc/GaTL1v5HVPj6M3jyBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T02:25:49.005779Z","bundle_sha256":"8beaa1801570ee8775b31dfa23052273caaa2111ca818d36efd2d7365cd5da37"}}