{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZPOTY52VLSYET3D4EL72A6Z4RI","short_pith_number":"pith:ZPOTY52V","canonical_record":{"source":{"id":"2412.04616","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T21:04:58Z","cross_cats_sorted":[],"title_canon_sha256":"8962fe8e46ebc112110a82ffd68a6e8f97698feb3f4b3f46f74199f81260aa14","abstract_canon_sha256":"df07fc5b0ba514ac1d8f4fa992c79154a9b3a9ac7bcddb354e85073dc7b9a090"},"schema_version":"1.0"},"canonical_sha256":"cbdd3c77555cb049ec7c22ffa07b3c8a3e361b5691ca29b9c9797a458a0c603c","source":{"kind":"arxiv","id":"2412.04616","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04616","created_at":"2026-07-05T10:51:29Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04616v2","created_at":"2026-07-05T10:51:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04616","created_at":"2026-07-05T10:51:29Z"},{"alias_kind":"pith_short_12","alias_value":"ZPOTY52VLSYE","created_at":"2026-07-05T10:51:29Z"},{"alias_kind":"pith_short_16","alias_value":"ZPOTY52VLSYET3D4","created_at":"2026-07-05T10:51:29Z"},{"alias_kind":"pith_short_8","alias_value":"ZPOTY52V","created_at":"2026-07-05T10:51:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZPOTY52VLSYET3D4EL72A6Z4RI","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04616","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T21:04:58Z","cross_cats_sorted":[],"title_canon_sha256":"8962fe8e46ebc112110a82ffd68a6e8f97698feb3f4b3f46f74199f81260aa14","abstract_canon_sha256":"df07fc5b0ba514ac1d8f4fa992c79154a9b3a9ac7bcddb354e85073dc7b9a090"},"schema_version":"1.0"},"canonical_sha256":"cbdd3c77555cb049ec7c22ffa07b3c8a3e361b5691ca29b9c9797a458a0c603c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:29.513105Z","signature_b64":"9PUI/Oo7I26SwHS/pcAzU3XJr38Nm/l+0Asd29EW22ezPNOKYwU7ULWbi2OBKkFnV3kL562nGXiOYuMb/gypAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbdd3c77555cb049ec7c22ffa07b3c8a3e361b5691ca29b9c9797a458a0c603c","last_reissued_at":"2026-07-05T10:51:29.512542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:29.512542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04616","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":"2026-07-05T10:51:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4kgor/PSh+jv6mZNvIFC7WriYJBHAt+2PoggcWhHIr1d2urFFvNhebOR6gjCa9YxjbCGRvQ/vltPsW8ea+NLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:20:38.846439Z"},"content_sha256":"2248761a832baa15178aa316928973c54d27c1579797a20a3ba338e268806b81","schema_version":"1.0","event_id":"sha256:2248761a832baa15178aa316928973c54d27c1579797a20a3ba338e268806b81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZPOTY52VLSYET3D4EL72A6Z4RI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Assessing and Learning Alignment of Unimodal Vision and Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aishwarya Agrawal, Le Zhang, Qian Yang","submitted_at":"2024-12-05T21:04:58Z","abstract_excerpt":"How well are unimodal vision and language models aligned? Although prior work have approached answering this question, their assessment methods do not directly translate to how these models are used in practical vision-language tasks. In this paper, we propose a direct assessment method, inspired by linear probing, to assess vision-language alignment. We identify that the degree of alignment of the SSL vision models depends on their SSL training objective, and we find that the clustering quality of SSL representations has a stronger impact on alignment performance than their linear separabilit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04616","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/2412.04616/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":"2026-07-05T10:51:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tHvqZGVVxRHBQZkKjz0p6+Ropm8PfEGHM2jasHK5TInHExwfERdpJ7xy/FJa5rKXniCMRFTIbURJlo81lchHBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:20:38.847349Z"},"content_sha256":"ab9da9d9330753917ecbbaf2aa96e058c8dcf5f589700d32288e84e210b7bc48","schema_version":"1.0","event_id":"sha256:ab9da9d9330753917ecbbaf2aa96e058c8dcf5f589700d32288e84e210b7bc48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZPOTY52VLSYET3D4EL72A6Z4RI/bundle.json","state_url":"https://pith.science/pith/ZPOTY52VLSYET3D4EL72A6Z4RI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZPOTY52VLSYET3D4EL72A6Z4RI/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":"2026-08-09T07:20:38Z","links":{"resolver":"https://pith.science/pith/ZPOTY52VLSYET3D4EL72A6Z4RI","bundle":"https://pith.science/pith/ZPOTY52VLSYET3D4EL72A6Z4RI/bundle.json","state":"https://pith.science/pith/ZPOTY52VLSYET3D4EL72A6Z4RI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZPOTY52VLSYET3D4EL72A6Z4RI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZPOTY52VLSYET3D4EL72A6Z4RI","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":"df07fc5b0ba514ac1d8f4fa992c79154a9b3a9ac7bcddb354e85073dc7b9a090","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T21:04:58Z","title_canon_sha256":"8962fe8e46ebc112110a82ffd68a6e8f97698feb3f4b3f46f74199f81260aa14"},"schema_version":"1.0","source":{"id":"2412.04616","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04616","created_at":"2026-07-05T10:51:29Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04616v2","created_at":"2026-07-05T10:51:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04616","created_at":"2026-07-05T10:51:29Z"},{"alias_kind":"pith_short_12","alias_value":"ZPOTY52VLSYE","created_at":"2026-07-05T10:51:29Z"},{"alias_kind":"pith_short_16","alias_value":"ZPOTY52VLSYET3D4","created_at":"2026-07-05T10:51:29Z"},{"alias_kind":"pith_short_8","alias_value":"ZPOTY52V","created_at":"2026-07-05T10:51:29Z"}],"graph_snapshots":[{"event_id":"sha256:ab9da9d9330753917ecbbaf2aa96e058c8dcf5f589700d32288e84e210b7bc48","target":"graph","created_at":"2026-07-05T10:51:29Z","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/2412.04616/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How well are unimodal vision and language models aligned? Although prior work have approached answering this question, their assessment methods do not directly translate to how these models are used in practical vision-language tasks. In this paper, we propose a direct assessment method, inspired by linear probing, to assess vision-language alignment. We identify that the degree of alignment of the SSL vision models depends on their SSL training objective, and we find that the clustering quality of SSL representations has a stronger impact on alignment performance than their linear separabilit","authors_text":"Aishwarya Agrawal, Le Zhang, Qian Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T21:04:58Z","title":"Assessing and Learning Alignment of Unimodal Vision and Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04616","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":"sha256:2248761a832baa15178aa316928973c54d27c1579797a20a3ba338e268806b81","target":"record","created_at":"2026-07-05T10:51:29Z","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":"df07fc5b0ba514ac1d8f4fa992c79154a9b3a9ac7bcddb354e85073dc7b9a090","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T21:04:58Z","title_canon_sha256":"8962fe8e46ebc112110a82ffd68a6e8f97698feb3f4b3f46f74199f81260aa14"},"schema_version":"1.0","source":{"id":"2412.04616","kind":"arxiv","version":2}},"canonical_sha256":"cbdd3c77555cb049ec7c22ffa07b3c8a3e361b5691ca29b9c9797a458a0c603c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbdd3c77555cb049ec7c22ffa07b3c8a3e361b5691ca29b9c9797a458a0c603c","first_computed_at":"2026-07-05T10:51:29.512542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:29.512542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9PUI/Oo7I26SwHS/pcAzU3XJr38Nm/l+0Asd29EW22ezPNOKYwU7ULWbi2OBKkFnV3kL562nGXiOYuMb/gypAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:29.513105Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04616","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2248761a832baa15178aa316928973c54d27c1579797a20a3ba338e268806b81","sha256:ab9da9d9330753917ecbbaf2aa96e058c8dcf5f589700d32288e84e210b7bc48"],"state_sha256":"24dedf5e206b745c5949386c546cd53561be916985a7ff6aeac1c4c4d4183f18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D9beFCcx7fen0JXHAJDMYe7CWVlCNKUqQq7m4PS6hv66GQpLaHvpPgz5h68py7dbk/tWPpJB4kRk/+nZ3VXTAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:20:38.851749Z","bundle_sha256":"686151be4895808041e934c7c9ea97a56390fd0702d5ac025a260d199d08af52"}}