{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4K7ADCNJY6IWYSXY2DCZT2DLMB","short_pith_number":"pith:4K7ADCNJ","canonical_record":{"source":{"id":"2603.16100","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-17T03:49:55Z","cross_cats_sorted":[],"title_canon_sha256":"64fd9831cd69b607ed6abd1efc511b52f12ba8de5da4890d0b5510bedcc47c78","abstract_canon_sha256":"e783dd305a84d578eada4f93062ff4bae4c51dd9749e484960ca8d951b8e7c3e"},"schema_version":"1.0"},"canonical_sha256":"e2be0189a9c7916c4af8d0c599e86b606eedee136fc4d0be45c9c5b7a6f6eac1","source":{"kind":"arxiv","id":"2603.16100","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.16100","created_at":"2026-05-26T02:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"2603.16100v2","created_at":"2026-05-26T02:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.16100","created_at":"2026-05-26T02:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"4K7ADCNJY6IW","created_at":"2026-05-26T02:04:08Z"},{"alias_kind":"pith_short_16","alias_value":"4K7ADCNJY6IWYSXY","created_at":"2026-05-26T02:04:08Z"},{"alias_kind":"pith_short_8","alias_value":"4K7ADCNJ","created_at":"2026-05-26T02:04:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4K7ADCNJY6IWYSXY2DCZT2DLMB","target":"record","payload":{"canonical_record":{"source":{"id":"2603.16100","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-17T03:49:55Z","cross_cats_sorted":[],"title_canon_sha256":"64fd9831cd69b607ed6abd1efc511b52f12ba8de5da4890d0b5510bedcc47c78","abstract_canon_sha256":"e783dd305a84d578eada4f93062ff4bae4c51dd9749e484960ca8d951b8e7c3e"},"schema_version":"1.0"},"canonical_sha256":"e2be0189a9c7916c4af8d0c599e86b606eedee136fc4d0be45c9c5b7a6f6eac1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:08.856207Z","signature_b64":"0AUHc9ZnRcxcj/QwGHClid7U3CnpR2uwwpZs9EYQVYkywNJQGJJq7w/pHu/n27jEY6ck21FOCDBtfDyThMacAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2be0189a9c7916c4af8d0c599e86b606eedee136fc4d0be45c9c5b7a6f6eac1","last_reissued_at":"2026-05-26T02:04:08.855330Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:08.855330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.16100","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":"2026-05-26T02:04:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PPvYXFcaa8Tk5+iG8aTlGuYi5DW5fWaSL7/m1sfMCv3MwzD7OY6mqVaZ+FKKNCOpwK5Ow36RLNcg3n/spKRcDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T19:13:02.082163Z"},"content_sha256":"7f70d4a8d35f11e30be214e9c94198b4377821b1ac3b4b2a10c0feec504e9b67","schema_version":"1.0","event_id":"sha256:7f70d4a8d35f11e30be214e9c94198b4377821b1ac3b4b2a10c0feec504e9b67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4K7ADCNJY6IWYSXY2DCZT2DLMB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reevaluating the Intra-Modal Misalignment Hypothesis in CLIP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jonas Herzog, Yue Wang","submitted_at":"2026-03-17T03:49:55Z","abstract_excerpt":"Recent research suggested that the embeddings produced by CLIP-like contrastive language-image training are suboptimal for image-only tasks. The main theory is that the inter-modal (language-image) alignment loss ignores intra-modal (image-image) alignment, leading to poorly calibrated distances between images. In this study, we question this intra-modal misalignment hypothesis. We reexamine its foundational theoretical argument, the indicators used to support it, and the performance metrics affected. For the theoretical argument, we demonstrate that there are no such supposed degrees of freed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.16100","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/2603.16100/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":"2026-05-26T02:04:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UdMqfu2OBh3HIRYjhGqQAW2xDQfJeCulh7vx5YnLz7/jX2zKgnlRzMB88FjH3maeWAB3d3l33MjuVlkRqUGQDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T19:13:02.082546Z"},"content_sha256":"ff027071db5937aa10cbecab8be30e3ce2e48bad4dad2986efab7e1897710627","schema_version":"1.0","event_id":"sha256:ff027071db5937aa10cbecab8be30e3ce2e48bad4dad2986efab7e1897710627"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4K7ADCNJY6IWYSXY2DCZT2DLMB/bundle.json","state_url":"https://pith.science/pith/4K7ADCNJY6IWYSXY2DCZT2DLMB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4K7ADCNJY6IWYSXY2DCZT2DLMB/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":"2026-07-15T19:13:02Z","links":{"resolver":"https://pith.science/pith/4K7ADCNJY6IWYSXY2DCZT2DLMB","bundle":"https://pith.science/pith/4K7ADCNJY6IWYSXY2DCZT2DLMB/bundle.json","state":"https://pith.science/pith/4K7ADCNJY6IWYSXY2DCZT2DLMB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4K7ADCNJY6IWYSXY2DCZT2DLMB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4K7ADCNJY6IWYSXY2DCZT2DLMB","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":"e783dd305a84d578eada4f93062ff4bae4c51dd9749e484960ca8d951b8e7c3e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-17T03:49:55Z","title_canon_sha256":"64fd9831cd69b607ed6abd1efc511b52f12ba8de5da4890d0b5510bedcc47c78"},"schema_version":"1.0","source":{"id":"2603.16100","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.16100","created_at":"2026-05-26T02:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"2603.16100v2","created_at":"2026-05-26T02:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.16100","created_at":"2026-05-26T02:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"4K7ADCNJY6IW","created_at":"2026-05-26T02:04:08Z"},{"alias_kind":"pith_short_16","alias_value":"4K7ADCNJY6IWYSXY","created_at":"2026-05-26T02:04:08Z"},{"alias_kind":"pith_short_8","alias_value":"4K7ADCNJ","created_at":"2026-05-26T02:04:08Z"}],"graph_snapshots":[{"event_id":"sha256:ff027071db5937aa10cbecab8be30e3ce2e48bad4dad2986efab7e1897710627","target":"graph","created_at":"2026-05-26T02:04:08Z","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/2603.16100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research suggested that the embeddings produced by CLIP-like contrastive language-image training are suboptimal for image-only tasks. The main theory is that the inter-modal (language-image) alignment loss ignores intra-modal (image-image) alignment, leading to poorly calibrated distances between images. In this study, we question this intra-modal misalignment hypothesis. We reexamine its foundational theoretical argument, the indicators used to support it, and the performance metrics affected. For the theoretical argument, we demonstrate that there are no such supposed degrees of freed","authors_text":"Jonas Herzog, Yue Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-17T03:49:55Z","title":"Reevaluating the Intra-Modal Misalignment Hypothesis in CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.16100","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":"sha256:7f70d4a8d35f11e30be214e9c94198b4377821b1ac3b4b2a10c0feec504e9b67","target":"record","created_at":"2026-05-26T02:04:08Z","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":"e783dd305a84d578eada4f93062ff4bae4c51dd9749e484960ca8d951b8e7c3e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-17T03:49:55Z","title_canon_sha256":"64fd9831cd69b607ed6abd1efc511b52f12ba8de5da4890d0b5510bedcc47c78"},"schema_version":"1.0","source":{"id":"2603.16100","kind":"arxiv","version":2}},"canonical_sha256":"e2be0189a9c7916c4af8d0c599e86b606eedee136fc4d0be45c9c5b7a6f6eac1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2be0189a9c7916c4af8d0c599e86b606eedee136fc4d0be45c9c5b7a6f6eac1","first_computed_at":"2026-05-26T02:04:08.855330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:08.855330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0AUHc9ZnRcxcj/QwGHClid7U3CnpR2uwwpZs9EYQVYkywNJQGJJq7w/pHu/n27jEY6ck21FOCDBtfDyThMacAA==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:08.856207Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.16100","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f70d4a8d35f11e30be214e9c94198b4377821b1ac3b4b2a10c0feec504e9b67","sha256:ff027071db5937aa10cbecab8be30e3ce2e48bad4dad2986efab7e1897710627"],"state_sha256":"2d15feafe97bec5436855c5d0150a9c6c33ff3181e3d2f9db1d60ae282ab2090"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X591Uk1bK/pGrnmDIRHO0kP3xVyQHV+7g28SEecZxWktma+O7gPbLA5by8O7LpNBv+boYKOKrLeSvjBoCBKDAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-15T19:13:02.084754Z","bundle_sha256":"82cfa115d936d0b7f3add008a48c048dbac40d63e4753a170edce752a86b816e"}}