{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q557VXYIN6IHNZYPMAX6JMMVVZ","short_pith_number":"pith:Q557VXYI","canonical_record":{"source":{"id":"2406.09406","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"dc9aa658026ee547c372dc143ffe8d730fcfd7497623a6b17f56900be0462e7f","abstract_canon_sha256":"d0904cfa0c3d0412a78ee6a0910a7fb2b90f39017ef83dfbad29f06d70f581b3"},"schema_version":"1.0"},"canonical_sha256":"877bfadf086f9076e70f602fe4b195ae7dd7b8b1c761383306b244a7b016efa7","source":{"kind":"arxiv","id":"2406.09406","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09406","created_at":"2026-07-05T08:31:53Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09406v2","created_at":"2026-07-05T08:31:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09406","created_at":"2026-07-05T08:31:53Z"},{"alias_kind":"pith_short_12","alias_value":"Q557VXYIN6IH","created_at":"2026-07-05T08:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"Q557VXYIN6IHNZYP","created_at":"2026-07-05T08:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"Q557VXYI","created_at":"2026-07-05T08:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q557VXYIN6IHNZYPMAX6JMMVVZ","target":"record","payload":{"canonical_record":{"source":{"id":"2406.09406","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"dc9aa658026ee547c372dc143ffe8d730fcfd7497623a6b17f56900be0462e7f","abstract_canon_sha256":"d0904cfa0c3d0412a78ee6a0910a7fb2b90f39017ef83dfbad29f06d70f581b3"},"schema_version":"1.0"},"canonical_sha256":"877bfadf086f9076e70f602fe4b195ae7dd7b8b1c761383306b244a7b016efa7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:53.675248Z","signature_b64":"ejZ2/eWLN4+kmGMVIIY7GJOVoidk/HER3LGNbDFKB3joDVHel5HeupYG/mA5wyil958lgPi/3OledO9iD6ulBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"877bfadf086f9076e70f602fe4b195ae7dd7b8b1c761383306b244a7b016efa7","last_reissued_at":"2026-07-05T08:31:53.674751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:53.674751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.09406","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:31:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UdLYPE1IWcLbBx5sjJlDXv+SKjOfSJoSRRMMoS7Zo7b3kv3uG7NrfZTC+V7L+8W2IdHC/lPfXCscfw/G5gz4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:55:41.152756Z"},"content_sha256":"ae5a7b9b67498e8937d559bf7cd26578cef45a4b8d5a69706391313207e0db7d","schema_version":"1.0","event_id":"sha256:ae5a7b9b67498e8937d559bf7cd26578cef45a4b8d5a69706391313207e0db7d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q557VXYIN6IHNZYPMAX6JMMVVZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Afshin Dehghan, Ali Garjani, Amir Zamir, David Griffiths, David Mizrahi, Jiaming Hu, Mingfei Gao, O\\u{g}uzhan Fatih Kar, Roman Bachmann","submitted_at":"2024-06-13T17:59:42Z","abstract_excerpt":"Current multimodal and multitask foundation models like 4M or UnifiedIO show promising results, but in practice their out-of-the-box abilities to accept diverse inputs and perform diverse tasks are limited by the (usually rather small) number of modalities and tasks they are trained on. In this paper, we expand upon the capabilities of them by training a single model on tens of highly diverse modalities and by performing co-training on large-scale multimodal datasets and text corpora. This includes training on several semantic and geometric modalities, feature maps from recent state of the art"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09406","kind":"arxiv","version":2},"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/2406.09406/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":"2026-07-05T08:31:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iFyudBQqOo3/k5HJUeCww1Hnz6rungKjcg46szcvy1E10QBsO/hyLPXMUcLs83W5hUxMkc7lM5x86pdYxXNvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:55:41.153134Z"},"content_sha256":"e68f57e0e54a40238ffb20a145ef6d021d8c99079bb1afdf43905475363121f0","schema_version":"1.0","event_id":"sha256:e68f57e0e54a40238ffb20a145ef6d021d8c99079bb1afdf43905475363121f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q557VXYIN6IHNZYPMAX6JMMVVZ/bundle.json","state_url":"https://pith.science/pith/Q557VXYIN6IHNZYPMAX6JMMVVZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q557VXYIN6IHNZYPMAX6JMMVVZ/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":"2026-07-07T11:55:41Z","links":{"resolver":"https://pith.science/pith/Q557VXYIN6IHNZYPMAX6JMMVVZ","bundle":"https://pith.science/pith/Q557VXYIN6IHNZYPMAX6JMMVVZ/bundle.json","state":"https://pith.science/pith/Q557VXYIN6IHNZYPMAX6JMMVVZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q557VXYIN6IHNZYPMAX6JMMVVZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q557VXYIN6IHNZYPMAX6JMMVVZ","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":"d0904cfa0c3d0412a78ee6a0910a7fb2b90f39017ef83dfbad29f06d70f581b3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:42Z","title_canon_sha256":"dc9aa658026ee547c372dc143ffe8d730fcfd7497623a6b17f56900be0462e7f"},"schema_version":"1.0","source":{"id":"2406.09406","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09406","created_at":"2026-07-05T08:31:53Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09406v2","created_at":"2026-07-05T08:31:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09406","created_at":"2026-07-05T08:31:53Z"},{"alias_kind":"pith_short_12","alias_value":"Q557VXYIN6IH","created_at":"2026-07-05T08:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"Q557VXYIN6IHNZYP","created_at":"2026-07-05T08:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"Q557VXYI","created_at":"2026-07-05T08:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:e68f57e0e54a40238ffb20a145ef6d021d8c99079bb1afdf43905475363121f0","target":"graph","created_at":"2026-07-05T08:31:53Z","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/2406.09406/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current multimodal and multitask foundation models like 4M or UnifiedIO show promising results, but in practice their out-of-the-box abilities to accept diverse inputs and perform diverse tasks are limited by the (usually rather small) number of modalities and tasks they are trained on. In this paper, we expand upon the capabilities of them by training a single model on tens of highly diverse modalities and by performing co-training on large-scale multimodal datasets and text corpora. This includes training on several semantic and geometric modalities, feature maps from recent state of the art","authors_text":"Afshin Dehghan, Ali Garjani, Amir Zamir, David Griffiths, David Mizrahi, Jiaming Hu, Mingfei Gao, O\\u{g}uzhan Fatih Kar, Roman Bachmann","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:42Z","title":"4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09406","kind":"arxiv","version":2},"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:ae5a7b9b67498e8937d559bf7cd26578cef45a4b8d5a69706391313207e0db7d","target":"record","created_at":"2026-07-05T08:31:53Z","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":"d0904cfa0c3d0412a78ee6a0910a7fb2b90f39017ef83dfbad29f06d70f581b3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:42Z","title_canon_sha256":"dc9aa658026ee547c372dc143ffe8d730fcfd7497623a6b17f56900be0462e7f"},"schema_version":"1.0","source":{"id":"2406.09406","kind":"arxiv","version":2}},"canonical_sha256":"877bfadf086f9076e70f602fe4b195ae7dd7b8b1c761383306b244a7b016efa7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"877bfadf086f9076e70f602fe4b195ae7dd7b8b1c761383306b244a7b016efa7","first_computed_at":"2026-07-05T08:31:53.674751Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:53.674751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ejZ2/eWLN4+kmGMVIIY7GJOVoidk/HER3LGNbDFKB3joDVHel5HeupYG/mA5wyil958lgPi/3OledO9iD6ulBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:53.675248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09406","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae5a7b9b67498e8937d559bf7cd26578cef45a4b8d5a69706391313207e0db7d","sha256:e68f57e0e54a40238ffb20a145ef6d021d8c99079bb1afdf43905475363121f0"],"state_sha256":"da83dfcee27f0ed028945a9e0c8b78e4707c549aeb321c7779454d777803df88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MPawE5l2jqshOWT3nWj4Q+4bUxB6DCK/FGKfooL0UQz5ku9+khAqIhuO2Lau0VlznV4SakzqASWeWeS9/swOCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:55:41.155120Z","bundle_sha256":"a56cded350e09661db6b21dc001aa1c89e9d5945767904ffe4dcd21b875d9579"}}