{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:K2NANV2HXTIEARXC4ODT3H2KRL","short_pith_number":"pith:K2NANV2H","canonical_record":{"source":{"id":"2407.11784","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-16T14:40:07Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"7367e6f6b366e10ab9963635c1bbfe2905488f38ca47935e64767370535efaea","abstract_canon_sha256":"dd65647622027900591a77528cd5cdbfc6e46e68684b6094a61a1424f896011e"},"schema_version":"1.0"},"canonical_sha256":"569a06d747bcd04046e2e3873d9f4a8aeff1349e63c43418cbe99ef80842db87","source":{"kind":"arxiv","id":"2407.11784","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11784","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11784v3","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11784","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_12","alias_value":"K2NANV2HXTIE","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_16","alias_value":"K2NANV2HXTIEARXC","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_8","alias_value":"K2NANV2H","created_at":"2026-07-05T11:15:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:K2NANV2HXTIEARXC4ODT3H2KRL","target":"record","payload":{"canonical_record":{"source":{"id":"2407.11784","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-16T14:40:07Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"7367e6f6b366e10ab9963635c1bbfe2905488f38ca47935e64767370535efaea","abstract_canon_sha256":"dd65647622027900591a77528cd5cdbfc6e46e68684b6094a61a1424f896011e"},"schema_version":"1.0"},"canonical_sha256":"569a06d747bcd04046e2e3873d9f4a8aeff1349e63c43418cbe99ef80842db87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:38.698332Z","signature_b64":"96TbBvi6c0bPLBPWnwwWMk35qPw5Rq+suJhB3muD7Fztu9Xc0u9b/SztZ1YirhdYz75iN1OGGhbAr3am2cKWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"569a06d747bcd04046e2e3873d9f4a8aeff1349e63c43418cbe99ef80842db87","last_reissued_at":"2026-07-05T11:15:38.697808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:38.697808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.11784","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uzTjpS1epQ0h/g/p4xS2CkuOJBZoz2kn9G4lDB6G7506t6+JRgDiWGeUOdWvxTyUlBoXoBugyzfeIUF4eVmpBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:18:54.934311Z"},"content_sha256":"d6f809ecabceee224e978887a503224adc1d2562a8e1bd91a9c24559b4f5ddbb","schema_version":"1.0","event_id":"sha256:d6f809ecabceee224e978887a503224adc1d2562a8e1bd91a9c24559b4f5ddbb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:K2NANV2HXTIEARXC4ODT3H2KRL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Bolin Ding, Ce Ge, Daoyuan Chen, Haibin Wang, Jingren Zhou, Yaliang Li, Yilun Huang","submitted_at":"2024-07-16T14:40:07Z","abstract_excerpt":"The emergence of multimodal large models has advanced artificial intelligence, introducing unprecedented levels of performance and functionality. However, optimizing these models remains challenging due to historically isolated paths of model-centric and data-centric developments, leading to suboptimal outcomes and inefficient resource utilization. In response, we present a new sandbox suite tailored for integrated data-model co-development. This sandbox provides a feedback-driven experimental platform, enabling cost-effective iteration and guided refinement of both data and models. Our propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11784","kind":"arxiv","version":3},"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/2407.11784/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":"2026-07-05T11:15:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aIiiTQXt8VdNH1PifMXEjXzQBIBcrE/7O0piqbmgmSoqEFyrzr35NtihCh67E5/mvyck3mBa/yWeZc1C+Z7pBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:18:54.934872Z"},"content_sha256":"ce08930f3cc0725b8d69655233b7f5890fc3a83e0d119ad845d4052ca7f27dec","schema_version":"1.0","event_id":"sha256:ce08930f3cc0725b8d69655233b7f5890fc3a83e0d119ad845d4052ca7f27dec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K2NANV2HXTIEARXC4ODT3H2KRL/bundle.json","state_url":"https://pith.science/pith/K2NANV2HXTIEARXC4ODT3H2KRL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K2NANV2HXTIEARXC4ODT3H2KRL/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":"2026-08-10T13:18:54Z","links":{"resolver":"https://pith.science/pith/K2NANV2HXTIEARXC4ODT3H2KRL","bundle":"https://pith.science/pith/K2NANV2HXTIEARXC4ODT3H2KRL/bundle.json","state":"https://pith.science/pith/K2NANV2HXTIEARXC4ODT3H2KRL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K2NANV2HXTIEARXC4ODT3H2KRL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K2NANV2HXTIEARXC4ODT3H2KRL","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":"dd65647622027900591a77528cd5cdbfc6e46e68684b6094a61a1424f896011e","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-16T14:40:07Z","title_canon_sha256":"7367e6f6b366e10ab9963635c1bbfe2905488f38ca47935e64767370535efaea"},"schema_version":"1.0","source":{"id":"2407.11784","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11784","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11784v3","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11784","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_12","alias_value":"K2NANV2HXTIE","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_16","alias_value":"K2NANV2HXTIEARXC","created_at":"2026-07-05T11:15:38Z"},{"alias_kind":"pith_short_8","alias_value":"K2NANV2H","created_at":"2026-07-05T11:15:38Z"}],"graph_snapshots":[{"event_id":"sha256:ce08930f3cc0725b8d69655233b7f5890fc3a83e0d119ad845d4052ca7f27dec","target":"graph","created_at":"2026-07-05T11:15:38Z","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/2407.11784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emergence of multimodal large models has advanced artificial intelligence, introducing unprecedented levels of performance and functionality. However, optimizing these models remains challenging due to historically isolated paths of model-centric and data-centric developments, leading to suboptimal outcomes and inefficient resource utilization. In response, we present a new sandbox suite tailored for integrated data-model co-development. This sandbox provides a feedback-driven experimental platform, enabling cost-effective iteration and guided refinement of both data and models. Our propos","authors_text":"Bolin Ding, Ce Ge, Daoyuan Chen, Haibin Wang, Jingren Zhou, Yaliang Li, Yilun Huang","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-16T14:40:07Z","title":"Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11784","kind":"arxiv","version":3},"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:d6f809ecabceee224e978887a503224adc1d2562a8e1bd91a9c24559b4f5ddbb","target":"record","created_at":"2026-07-05T11:15:38Z","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":"dd65647622027900591a77528cd5cdbfc6e46e68684b6094a61a1424f896011e","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-16T14:40:07Z","title_canon_sha256":"7367e6f6b366e10ab9963635c1bbfe2905488f38ca47935e64767370535efaea"},"schema_version":"1.0","source":{"id":"2407.11784","kind":"arxiv","version":3}},"canonical_sha256":"569a06d747bcd04046e2e3873d9f4a8aeff1349e63c43418cbe99ef80842db87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"569a06d747bcd04046e2e3873d9f4a8aeff1349e63c43418cbe99ef80842db87","first_computed_at":"2026-07-05T11:15:38.697808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:38.697808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"96TbBvi6c0bPLBPWnwwWMk35qPw5Rq+suJhB3muD7Fztu9Xc0u9b/SztZ1YirhdYz75iN1OGGhbAr3am2cKWDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:38.698332Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.11784","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6f809ecabceee224e978887a503224adc1d2562a8e1bd91a9c24559b4f5ddbb","sha256:ce08930f3cc0725b8d69655233b7f5890fc3a83e0d119ad845d4052ca7f27dec"],"state_sha256":"04ebc46a125a2b8a59be5fbd298aac3f59074e7c77f00eff55065cb785381558"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YOUddqQZDgsekpug2n3iuf7LzKkUaHOFFcq/4p+LJ2wByskCy4On3kz04miPfq1dmD4eurJfzUoF04GPgqkXCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T13:18:54.940923Z","bundle_sha256":"1324cb96bd0477c43d98706e7b9582367a204684b0edfb1fd473bf893aab466b"}}