{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:U2QIH26AHR63XJK5IHEXGWL5CV","short_pith_number":"pith:U2QIH26A","canonical_record":{"source":{"id":"2401.11337","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-20T22:04:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3dbff1f6a6453d5f5f42ccff193cb395d4e0697b724a7c9e9ef796cdaf19b3d1","abstract_canon_sha256":"1541cbcb340a88cfd0c23890696a6e8b5d4e7e87704ad6131391649637335ad2"},"schema_version":"1.0"},"canonical_sha256":"a6a083ebc03c7dbba55d41c973597d1569cafa620313240e5a88016bd0d16421","source":{"kind":"arxiv","id":"2401.11337","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11337","created_at":"2026-07-05T07:35:49Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11337v1","created_at":"2026-07-05T07:35:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11337","created_at":"2026-07-05T07:35:49Z"},{"alias_kind":"pith_short_12","alias_value":"U2QIH26AHR63","created_at":"2026-07-05T07:35:49Z"},{"alias_kind":"pith_short_16","alias_value":"U2QIH26AHR63XJK5","created_at":"2026-07-05T07:35:49Z"},{"alias_kind":"pith_short_8","alias_value":"U2QIH26A","created_at":"2026-07-05T07:35:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:U2QIH26AHR63XJK5IHEXGWL5CV","target":"record","payload":{"canonical_record":{"source":{"id":"2401.11337","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-20T22:04:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3dbff1f6a6453d5f5f42ccff193cb395d4e0697b724a7c9e9ef796cdaf19b3d1","abstract_canon_sha256":"1541cbcb340a88cfd0c23890696a6e8b5d4e7e87704ad6131391649637335ad2"},"schema_version":"1.0"},"canonical_sha256":"a6a083ebc03c7dbba55d41c973597d1569cafa620313240e5a88016bd0d16421","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:49.272920Z","signature_b64":"O6jCy7tRkd5l/s5mMyMAgygzMF9TQkEHDjDCjA0XbrpFhaodw4OXXmCYfHyboVNqF8sDrNQ9T4kLWZwmX8plDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6a083ebc03c7dbba55d41c973597d1569cafa620313240e5a88016bd0d16421","last_reissued_at":"2026-07-05T07:35:49.272495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:49.272495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.11337","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":"2026-07-05T07:35:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QWQ6fI+3DPwhVpAQr8FLu2bEuR6mFOaQ57yF0nmjUEYZPDgbbliAu9Yx5UR1xG1fD/hm+E/eh6LmFxN4juqeCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:54:12.428734Z"},"content_sha256":"8e2b5e33205c95cf61ef32a44a5e38f1273283c2f8d5d8d2fe9693901a09247c","schema_version":"1.0","event_id":"sha256:8e2b5e33205c95cf61ef32a44a5e38f1273283c2f8d5d8d2fe9693901a09247c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:U2QIH26AHR63XJK5IHEXGWL5CV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prompting Large Vision-Language Models for Compositional Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Junjie Hu, Ming Jiang, Timothy Ossowski","submitted_at":"2024-01-20T22:04:28Z","abstract_excerpt":"Vision-language models such as CLIP have shown impressive capabilities in encoding texts and images into aligned embeddings, enabling the retrieval of multimodal data in a shared embedding space. However, these embedding-based models still face challenges in effectively matching images and texts with similar visio-linguistic compositionality, as evidenced by their performance on the recent Winoground dataset. In this paper, we argue that this limitation stems from two factors: the use of single vector representations for complex multimodal data, and the absence of step-by-step reasoning in the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11337","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/2401.11337/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":"2026-07-05T07:35:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B++M0WkyyahWBa3yulB5ZzFI/FKSjmzjDl/a7WC/f235Nh61CTFdhoi7ErN/v8LCYhsxctHgW151Mk0WG9mzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:54:12.429027Z"},"content_sha256":"a9f9bfffecae2938fb2bdb3886cc0b62683eae8d1e7a3022bd028ec54e6a71f3","schema_version":"1.0","event_id":"sha256:a9f9bfffecae2938fb2bdb3886cc0b62683eae8d1e7a3022bd028ec54e6a71f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U2QIH26AHR63XJK5IHEXGWL5CV/bundle.json","state_url":"https://pith.science/pith/U2QIH26AHR63XJK5IHEXGWL5CV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U2QIH26AHR63XJK5IHEXGWL5CV/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":"2026-08-17T12:54:12Z","links":{"resolver":"https://pith.science/pith/U2QIH26AHR63XJK5IHEXGWL5CV","bundle":"https://pith.science/pith/U2QIH26AHR63XJK5IHEXGWL5CV/bundle.json","state":"https://pith.science/pith/U2QIH26AHR63XJK5IHEXGWL5CV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U2QIH26AHR63XJK5IHEXGWL5CV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U2QIH26AHR63XJK5IHEXGWL5CV","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":"1541cbcb340a88cfd0c23890696a6e8b5d4e7e87704ad6131391649637335ad2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-20T22:04:28Z","title_canon_sha256":"3dbff1f6a6453d5f5f42ccff193cb395d4e0697b724a7c9e9ef796cdaf19b3d1"},"schema_version":"1.0","source":{"id":"2401.11337","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11337","created_at":"2026-07-05T07:35:49Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11337v1","created_at":"2026-07-05T07:35:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11337","created_at":"2026-07-05T07:35:49Z"},{"alias_kind":"pith_short_12","alias_value":"U2QIH26AHR63","created_at":"2026-07-05T07:35:49Z"},{"alias_kind":"pith_short_16","alias_value":"U2QIH26AHR63XJK5","created_at":"2026-07-05T07:35:49Z"},{"alias_kind":"pith_short_8","alias_value":"U2QIH26A","created_at":"2026-07-05T07:35:49Z"}],"graph_snapshots":[{"event_id":"sha256:a9f9bfffecae2938fb2bdb3886cc0b62683eae8d1e7a3022bd028ec54e6a71f3","target":"graph","created_at":"2026-07-05T07:35:49Z","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/2401.11337/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models such as CLIP have shown impressive capabilities in encoding texts and images into aligned embeddings, enabling the retrieval of multimodal data in a shared embedding space. However, these embedding-based models still face challenges in effectively matching images and texts with similar visio-linguistic compositionality, as evidenced by their performance on the recent Winoground dataset. In this paper, we argue that this limitation stems from two factors: the use of single vector representations for complex multimodal data, and the absence of step-by-step reasoning in the","authors_text":"Junjie Hu, Ming Jiang, Timothy Ossowski","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-20T22:04:28Z","title":"Prompting Large Vision-Language Models for Compositional Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11337","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":"sha256:8e2b5e33205c95cf61ef32a44a5e38f1273283c2f8d5d8d2fe9693901a09247c","target":"record","created_at":"2026-07-05T07:35:49Z","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":"1541cbcb340a88cfd0c23890696a6e8b5d4e7e87704ad6131391649637335ad2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-20T22:04:28Z","title_canon_sha256":"3dbff1f6a6453d5f5f42ccff193cb395d4e0697b724a7c9e9ef796cdaf19b3d1"},"schema_version":"1.0","source":{"id":"2401.11337","kind":"arxiv","version":1}},"canonical_sha256":"a6a083ebc03c7dbba55d41c973597d1569cafa620313240e5a88016bd0d16421","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6a083ebc03c7dbba55d41c973597d1569cafa620313240e5a88016bd0d16421","first_computed_at":"2026-07-05T07:35:49.272495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:35:49.272495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O6jCy7tRkd5l/s5mMyMAgygzMF9TQkEHDjDCjA0XbrpFhaodw4OXXmCYfHyboVNqF8sDrNQ9T4kLWZwmX8plDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:35:49.272920Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.11337","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e2b5e33205c95cf61ef32a44a5e38f1273283c2f8d5d8d2fe9693901a09247c","sha256:a9f9bfffecae2938fb2bdb3886cc0b62683eae8d1e7a3022bd028ec54e6a71f3"],"state_sha256":"5f3eb207b57bfa126d622966fd25dfc02c86deba52c54b2e43e5dbd873c1c9ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hrGtIQ17N7Xxq2MhWXON0po66nGdF+trfz8v0UxHI01SPupxFbREXeYc1lmRpPxD/ycdKngDpvmfrY+dDU9wBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T12:54:12.431224Z","bundle_sha256":"401168bebd62f586d947811695f9c867058d226934bfd1ce1f8c1b61099ae746"}}