{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NCB2MPVKNDH2MVO62SRFFOI3MS","short_pith_number":"pith:NCB2MPVK","canonical_record":{"source":{"id":"2409.08206","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T16:46:41Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"ec9cba102407f8f7398512b778097f7c86701f66d5569b47cf53d55591637b16","abstract_canon_sha256":"ac7f33f4a462a88ec8ea2f53e85075117a8c0b3dc9e415c8a3a76f4135e7c748"},"schema_version":"1.0"},"canonical_sha256":"6883a63eaa68cfa655ded4a252b91b648203de1f2b9e3dbbd84921ed08b1bf7d","source":{"kind":"arxiv","id":"2409.08206","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08206","created_at":"2026-07-05T09:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08206v1","created_at":"2026-07-05T09:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08206","created_at":"2026-07-05T09:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"NCB2MPVKNDH2","created_at":"2026-07-05T09:06:21Z"},{"alias_kind":"pith_short_16","alias_value":"NCB2MPVKNDH2MVO6","created_at":"2026-07-05T09:06:21Z"},{"alias_kind":"pith_short_8","alias_value":"NCB2MPVK","created_at":"2026-07-05T09:06:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NCB2MPVKNDH2MVO62SRFFOI3MS","target":"record","payload":{"canonical_record":{"source":{"id":"2409.08206","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T16:46:41Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"ec9cba102407f8f7398512b778097f7c86701f66d5569b47cf53d55591637b16","abstract_canon_sha256":"ac7f33f4a462a88ec8ea2f53e85075117a8c0b3dc9e415c8a3a76f4135e7c748"},"schema_version":"1.0"},"canonical_sha256":"6883a63eaa68cfa655ded4a252b91b648203de1f2b9e3dbbd84921ed08b1bf7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:21.809671Z","signature_b64":"+AH5aK7XR5r3Cf390o74BGv4EhwlrC9eOQtsrMoBoG/HjdT8gV/QZCwLAm4aGobgCDZj1hEiBjN8WYMnXOtZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6883a63eaa68cfa655ded4a252b91b648203de1f2b9e3dbbd84921ed08b1bf7d","last_reissued_at":"2026-07-05T09:06:21.808961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:21.808961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.08206","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":"2026-07-05T09:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vbeRrh2hcsu1zOAEhOk6Qckc/lLI+3iq7uIHRuETas00wV/rlQNnIA0lBHzsiFpIW42/b1xAlaNei7MMhJHvCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T11:37:57.901598Z"},"content_sha256":"184b13940d6e0b1674ebfc5face5394bc7f661ce525a93b59144de917a480048","schema_version":"1.0","event_id":"sha256:184b13940d6e0b1674ebfc5face5394bc7f661ce525a93b59144de917a480048"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NCB2MPVKNDH2MVO62SRFFOI3MS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ComAlign: Compositional Alignment in Vision-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Ali Abdollah, Amirmohammad Izadi, Amirreza Mirzaei, Armin Saghafian, Mahdieh Soleymani Baghshah, Mohammadmahdi Samiei, Mohammad Mozafari, Reza Vahidimajd","submitted_at":"2024-09-12T16:46:41Z","abstract_excerpt":"Vision-language models (VLMs) like CLIP have showcased a remarkable ability to extract transferable features for downstream tasks. Nonetheless, the training process of these models is usually based on a coarse-grained contrastive loss between the global embedding of images and texts which may lose the compositional structure of these modalities. Many recent studies have shown VLMs lack compositional understandings like attribute binding and identifying object relationships. Although some recent methods have tried to achieve finer-level alignments, they either are not based on extracting meanin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08206","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/2409.08206/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":"2026-07-05T09:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A/EJJg0Y+y1os1vMsxSMUvxIvaOyNvTgQ4bPtcqoWWRKrHQxUL4ZMGcuJFlP4SrOSVGxla4Ga87S2O35L10jDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T11:37:57.901973Z"},"content_sha256":"55eb081ba91033480c02b835376eb499c7cc539dce09f66bb5258c243286746e","schema_version":"1.0","event_id":"sha256:55eb081ba91033480c02b835376eb499c7cc539dce09f66bb5258c243286746e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NCB2MPVKNDH2MVO62SRFFOI3MS/bundle.json","state_url":"https://pith.science/pith/NCB2MPVKNDH2MVO62SRFFOI3MS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NCB2MPVKNDH2MVO62SRFFOI3MS/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":"2026-07-20T11:37:57Z","links":{"resolver":"https://pith.science/pith/NCB2MPVKNDH2MVO62SRFFOI3MS","bundle":"https://pith.science/pith/NCB2MPVKNDH2MVO62SRFFOI3MS/bundle.json","state":"https://pith.science/pith/NCB2MPVKNDH2MVO62SRFFOI3MS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NCB2MPVKNDH2MVO62SRFFOI3MS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NCB2MPVKNDH2MVO62SRFFOI3MS","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":"ac7f33f4a462a88ec8ea2f53e85075117a8c0b3dc9e415c8a3a76f4135e7c748","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T16:46:41Z","title_canon_sha256":"ec9cba102407f8f7398512b778097f7c86701f66d5569b47cf53d55591637b16"},"schema_version":"1.0","source":{"id":"2409.08206","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08206","created_at":"2026-07-05T09:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08206v1","created_at":"2026-07-05T09:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08206","created_at":"2026-07-05T09:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"NCB2MPVKNDH2","created_at":"2026-07-05T09:06:21Z"},{"alias_kind":"pith_short_16","alias_value":"NCB2MPVKNDH2MVO6","created_at":"2026-07-05T09:06:21Z"},{"alias_kind":"pith_short_8","alias_value":"NCB2MPVK","created_at":"2026-07-05T09:06:21Z"}],"graph_snapshots":[{"event_id":"sha256:55eb081ba91033480c02b835376eb499c7cc539dce09f66bb5258c243286746e","target":"graph","created_at":"2026-07-05T09:06:21Z","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/2409.08206/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) like CLIP have showcased a remarkable ability to extract transferable features for downstream tasks. Nonetheless, the training process of these models is usually based on a coarse-grained contrastive loss between the global embedding of images and texts which may lose the compositional structure of these modalities. Many recent studies have shown VLMs lack compositional understandings like attribute binding and identifying object relationships. Although some recent methods have tried to achieve finer-level alignments, they either are not based on extracting meanin","authors_text":"Ali Abdollah, Amirmohammad Izadi, Amirreza Mirzaei, Armin Saghafian, Mahdieh Soleymani Baghshah, Mohammadmahdi Samiei, Mohammad Mozafari, Reza Vahidimajd","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T16:46:41Z","title":"ComAlign: Compositional Alignment in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08206","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":"sha256:184b13940d6e0b1674ebfc5face5394bc7f661ce525a93b59144de917a480048","target":"record","created_at":"2026-07-05T09:06:21Z","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":"ac7f33f4a462a88ec8ea2f53e85075117a8c0b3dc9e415c8a3a76f4135e7c748","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T16:46:41Z","title_canon_sha256":"ec9cba102407f8f7398512b778097f7c86701f66d5569b47cf53d55591637b16"},"schema_version":"1.0","source":{"id":"2409.08206","kind":"arxiv","version":1}},"canonical_sha256":"6883a63eaa68cfa655ded4a252b91b648203de1f2b9e3dbbd84921ed08b1bf7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6883a63eaa68cfa655ded4a252b91b648203de1f2b9e3dbbd84921ed08b1bf7d","first_computed_at":"2026-07-05T09:06:21.808961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:21.808961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+AH5aK7XR5r3Cf390o74BGv4EhwlrC9eOQtsrMoBoG/HjdT8gV/QZCwLAm4aGobgCDZj1hEiBjN8WYMnXOtZDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:21.809671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08206","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:184b13940d6e0b1674ebfc5face5394bc7f661ce525a93b59144de917a480048","sha256:55eb081ba91033480c02b835376eb499c7cc539dce09f66bb5258c243286746e"],"state_sha256":"ec29fae44257adbf5e80aecb002ad5cab49c0eb9c991efd3cef14483844613e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6PNi3+LrHofT1ZF2kkmVBanmrwFc+X3fo/LLO8yTgN9KdIguzWneWNZ1ebgmr52YPb7eUNnBLbjQe3ZH8BXLCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T11:37:57.904117Z","bundle_sha256":"79a34e18dc7ac7e3060f1719df931d3d699888777b7df8d31dd7cdf0211f0768"}}