{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Z3EMPY3WBJX6YS23BQG5SM2ZDT","short_pith_number":"pith:Z3EMPY3W","canonical_record":{"source":{"id":"2404.16375","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T07:29:17Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"632f3ffd14dcca90ff7f174fb5d633091addfa56e2ad7f4f22f0022ca07bd06c","abstract_canon_sha256":"cd163478c393e8ab8113c564e420b1da4b749749e24dd64aab66274f36377ff5"},"schema_version":"1.0"},"canonical_sha256":"cec8c7e3760a6fec4b5b0c0dd933591cccad8005783ffcf3b8c6f04cfb51a90b","source":{"kind":"arxiv","id":"2404.16375","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.16375","created_at":"2026-07-05T10:02:45Z"},{"alias_kind":"arxiv_version","alias_value":"2404.16375v2","created_at":"2026-07-05T10:02:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16375","created_at":"2026-07-05T10:02:45Z"},{"alias_kind":"pith_short_12","alias_value":"Z3EMPY3WBJX6","created_at":"2026-07-05T10:02:45Z"},{"alias_kind":"pith_short_16","alias_value":"Z3EMPY3WBJX6YS23","created_at":"2026-07-05T10:02:45Z"},{"alias_kind":"pith_short_8","alias_value":"Z3EMPY3W","created_at":"2026-07-05T10:02:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Z3EMPY3WBJX6YS23BQG5SM2ZDT","target":"record","payload":{"canonical_record":{"source":{"id":"2404.16375","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T07:29:17Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"632f3ffd14dcca90ff7f174fb5d633091addfa56e2ad7f4f22f0022ca07bd06c","abstract_canon_sha256":"cd163478c393e8ab8113c564e420b1da4b749749e24dd64aab66274f36377ff5"},"schema_version":"1.0"},"canonical_sha256":"cec8c7e3760a6fec4b5b0c0dd933591cccad8005783ffcf3b8c6f04cfb51a90b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:45.754672Z","signature_b64":"EFrRrmlHX35Tk3Tq9TulMk0QsMb5tCpviDQelfrB74Y/eW1gr0o/Xjov0FjvG/5q5YxRaj+J1SC/Ci5bZxS9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cec8c7e3760a6fec4b5b0c0dd933591cccad8005783ffcf3b8c6f04cfb51a90b","last_reissued_at":"2026-07-05T10:02:45.754206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:45.754206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.16375","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":"2026-07-05T10:02:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jDjiDJzar/P/xVTUdb798GYmNkdLmSc7VPQiOokoKjTY/2lWpMC7QV18SGRCYDLdXBTOw4Ga29KDzZqH0ZLDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:06:52.594869Z"},"content_sha256":"c638bad6709097e7791890fb714fd3d97a3394d810d99ac7edac714ac410024b","schema_version":"1.0","event_id":"sha256:c638bad6709097e7791890fb714fd3d97a3394d810d99ac7edac714ac410024b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Z3EMPY3WBJX6YS23BQG5SM2ZDT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"An Yan, Jianfeng Gao, Jianfeng Wang, Jianwei Yang, Julian McAuley, Junda Wu, Kevin Lin, Lijuan Wang, Linjie Li, Wanrong Zhu, Zhengyuan Yang","submitted_at":"2024-04-25T07:29:17Z","abstract_excerpt":"Set-of-Mark (SoM) Prompting unleashes the visual grounding capability of GPT-4V, by enabling the model to associate visual objects with tags inserted on the image. These tags, marked with alphanumerics, can be indexed via text tokens for easy reference. Despite the extraordinary performance from GPT-4V, we observe that other Multimodal Large Language Models (MLLMs) struggle to understand these visual tags. To promote the learning of SoM prompting for open-source models, we propose a new learning paradigm: \"list items one by one,\" which asks the model to enumerate and describe all visual tags p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16375","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/2404.16375/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":"2026-07-05T10:02:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"017+yEtyDvsJYoaOvwm3GC2I/hRYjLoogcljVdDTXONoQaE+hOmIgbEQku+F9BOD4ozWqMSWkMghaIaxd60jBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:06:52.595360Z"},"content_sha256":"c5242d6e3dc02fa47a3ea37ca5a35dc8d367f26307c95473782b89ff04885aa5","schema_version":"1.0","event_id":"sha256:c5242d6e3dc02fa47a3ea37ca5a35dc8d367f26307c95473782b89ff04885aa5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z3EMPY3WBJX6YS23BQG5SM2ZDT/bundle.json","state_url":"https://pith.science/pith/Z3EMPY3WBJX6YS23BQG5SM2ZDT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z3EMPY3WBJX6YS23BQG5SM2ZDT/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":"2026-08-06T10:06:52Z","links":{"resolver":"https://pith.science/pith/Z3EMPY3WBJX6YS23BQG5SM2ZDT","bundle":"https://pith.science/pith/Z3EMPY3WBJX6YS23BQG5SM2ZDT/bundle.json","state":"https://pith.science/pith/Z3EMPY3WBJX6YS23BQG5SM2ZDT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z3EMPY3WBJX6YS23BQG5SM2ZDT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z3EMPY3WBJX6YS23BQG5SM2ZDT","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":"cd163478c393e8ab8113c564e420b1da4b749749e24dd64aab66274f36377ff5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T07:29:17Z","title_canon_sha256":"632f3ffd14dcca90ff7f174fb5d633091addfa56e2ad7f4f22f0022ca07bd06c"},"schema_version":"1.0","source":{"id":"2404.16375","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.16375","created_at":"2026-07-05T10:02:45Z"},{"alias_kind":"arxiv_version","alias_value":"2404.16375v2","created_at":"2026-07-05T10:02:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16375","created_at":"2026-07-05T10:02:45Z"},{"alias_kind":"pith_short_12","alias_value":"Z3EMPY3WBJX6","created_at":"2026-07-05T10:02:45Z"},{"alias_kind":"pith_short_16","alias_value":"Z3EMPY3WBJX6YS23","created_at":"2026-07-05T10:02:45Z"},{"alias_kind":"pith_short_8","alias_value":"Z3EMPY3W","created_at":"2026-07-05T10:02:45Z"}],"graph_snapshots":[{"event_id":"sha256:c5242d6e3dc02fa47a3ea37ca5a35dc8d367f26307c95473782b89ff04885aa5","target":"graph","created_at":"2026-07-05T10:02:45Z","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/2404.16375/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Set-of-Mark (SoM) Prompting unleashes the visual grounding capability of GPT-4V, by enabling the model to associate visual objects with tags inserted on the image. These tags, marked with alphanumerics, can be indexed via text tokens for easy reference. Despite the extraordinary performance from GPT-4V, we observe that other Multimodal Large Language Models (MLLMs) struggle to understand these visual tags. To promote the learning of SoM prompting for open-source models, we propose a new learning paradigm: \"list items one by one,\" which asks the model to enumerate and describe all visual tags p","authors_text":"An Yan, Jianfeng Gao, Jianfeng Wang, Jianwei Yang, Julian McAuley, Junda Wu, Kevin Lin, Lijuan Wang, Linjie Li, Wanrong Zhu, Zhengyuan Yang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T07:29:17Z","title":"List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16375","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:c638bad6709097e7791890fb714fd3d97a3394d810d99ac7edac714ac410024b","target":"record","created_at":"2026-07-05T10:02:45Z","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":"cd163478c393e8ab8113c564e420b1da4b749749e24dd64aab66274f36377ff5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T07:29:17Z","title_canon_sha256":"632f3ffd14dcca90ff7f174fb5d633091addfa56e2ad7f4f22f0022ca07bd06c"},"schema_version":"1.0","source":{"id":"2404.16375","kind":"arxiv","version":2}},"canonical_sha256":"cec8c7e3760a6fec4b5b0c0dd933591cccad8005783ffcf3b8c6f04cfb51a90b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cec8c7e3760a6fec4b5b0c0dd933591cccad8005783ffcf3b8c6f04cfb51a90b","first_computed_at":"2026-07-05T10:02:45.754206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:45.754206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EFrRrmlHX35Tk3Tq9TulMk0QsMb5tCpviDQelfrB74Y/eW1gr0o/Xjov0FjvG/5q5YxRaj+J1SC/Ci5bZxS9Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:45.754672Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.16375","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c638bad6709097e7791890fb714fd3d97a3394d810d99ac7edac714ac410024b","sha256:c5242d6e3dc02fa47a3ea37ca5a35dc8d367f26307c95473782b89ff04885aa5"],"state_sha256":"8f6ae6c368d409462d675ebd4c85339db8023b5d4d1e440b7175e053e877b27f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5gbTyGghwi0NKnvPd5CaBRdueIoxje7/RHWTcmYPVA7lbdL7r2nma1HkmowBivafjw8hJ0SBlsOFaLSAGe4VAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T10:06:52.599974Z","bundle_sha256":"fbece2a7b6d2ae3bbe0dbc67cfff219fbb448a5b129b2b87301bd5d65ecc2e89"}}