{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LJYDFZ3S3KGL4OR6HWVBK4LCEV","short_pith_number":"pith:LJYDFZ3S","canonical_record":{"source":{"id":"2504.12717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-17T07:46:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"022088fddf1c3864ecb1f84d03f92941b69cecf0b2eb6e5c5e0a90456a9bd628","abstract_canon_sha256":"b999bcf741c10a6b22e44ee2f1d86c18e04bef726a247a0ad9ce656ab3f3ef37"},"schema_version":"1.0"},"canonical_sha256":"5a7032e772da8cbe3a3e3daa15716225783c90480b3725ecd437ef23f62b7a7b","source":{"kind":"arxiv","id":"2504.12717","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12717","created_at":"2026-07-05T10:50:21Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12717v1","created_at":"2026-07-05T10:50:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12717","created_at":"2026-07-05T10:50:21Z"},{"alias_kind":"pith_short_12","alias_value":"LJYDFZ3S3KGL","created_at":"2026-07-05T10:50:21Z"},{"alias_kind":"pith_short_16","alias_value":"LJYDFZ3S3KGL4OR6","created_at":"2026-07-05T10:50:21Z"},{"alias_kind":"pith_short_8","alias_value":"LJYDFZ3S","created_at":"2026-07-05T10:50:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LJYDFZ3S3KGL4OR6HWVBK4LCEV","target":"record","payload":{"canonical_record":{"source":{"id":"2504.12717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-17T07:46:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"022088fddf1c3864ecb1f84d03f92941b69cecf0b2eb6e5c5e0a90456a9bd628","abstract_canon_sha256":"b999bcf741c10a6b22e44ee2f1d86c18e04bef726a247a0ad9ce656ab3f3ef37"},"schema_version":"1.0"},"canonical_sha256":"5a7032e772da8cbe3a3e3daa15716225783c90480b3725ecd437ef23f62b7a7b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:21.189242Z","signature_b64":"oF0pEkK4tnmpQRZa/gk9gPkcC90y4avNYJWgu7Zwd31cVDWywLmrbFYRjtO9LBn/PKy9AxVsV0qkguHG7gWeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a7032e772da8cbe3a3e3daa15716225783c90480b3725ecd437ef23f62b7a7b","last_reissued_at":"2026-07-05T10:50:21.188829Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:21.188829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.12717","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":"2026-07-05T10:50:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xbGnt9hXfdof+FqxkVgX9VkUR4QNFO+nO6PPVq9H5Ix0Znlh1ddfMiPHDazYQa+YOcoZFMlKyXrAlHGGVhDUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T13:13:00.183254Z"},"content_sha256":"0f4624740b23573e33ac64b261913a81bcd03cc320171f3c324a7382be7d4b5e","schema_version":"1.0","event_id":"sha256:0f4624740b23573e33ac64b261913a81bcd03cc320171f3c324a7382be7d4b5e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LJYDFZ3S3KGL4OR6HWVBK4LCEV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Post-pre-training for Modality Alignment in Vision-Language Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Daiki Chijiwa, Dewei Feng, Kazuki Adachi, Sekitoshi Kanai, Shin'ya Yamaguchi","submitted_at":"2025-04-17T07:46:19Z","abstract_excerpt":"Contrastive language image pre-training (CLIP) is an essential component of building modern vision-language foundation models. While CLIP demonstrates remarkable zero-shot performance on downstream tasks, the multi-modal feature spaces still suffer from a modality gap, which is a gap between image and text feature clusters and limits downstream task performance. Although existing works attempt to address the modality gap by modifying pre-training or fine-tuning, they struggle with heavy training costs with large datasets or degradations of zero-shot performance. This paper presents CLIP-Refine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12717","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/2504.12717/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":"2026-07-05T10:50:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WaNc0ugSKLC7Or9HbbeSdUw4uV32oTPr9t6HEe7jdUDuf50LBmDykEH71uj6EylgwmONLBSU9vRdZdIWERuyCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T13:13:00.183787Z"},"content_sha256":"76985115a654a18051c48d14dac8707e67716c22bb8742d70aee846d75774818","schema_version":"1.0","event_id":"sha256:76985115a654a18051c48d14dac8707e67716c22bb8742d70aee846d75774818"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LJYDFZ3S3KGL4OR6HWVBK4LCEV/bundle.json","state_url":"https://pith.science/pith/LJYDFZ3S3KGL4OR6HWVBK4LCEV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LJYDFZ3S3KGL4OR6HWVBK4LCEV/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":"2026-08-02T13:13:00Z","links":{"resolver":"https://pith.science/pith/LJYDFZ3S3KGL4OR6HWVBK4LCEV","bundle":"https://pith.science/pith/LJYDFZ3S3KGL4OR6HWVBK4LCEV/bundle.json","state":"https://pith.science/pith/LJYDFZ3S3KGL4OR6HWVBK4LCEV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LJYDFZ3S3KGL4OR6HWVBK4LCEV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LJYDFZ3S3KGL4OR6HWVBK4LCEV","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":"b999bcf741c10a6b22e44ee2f1d86c18e04bef726a247a0ad9ce656ab3f3ef37","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-17T07:46:19Z","title_canon_sha256":"022088fddf1c3864ecb1f84d03f92941b69cecf0b2eb6e5c5e0a90456a9bd628"},"schema_version":"1.0","source":{"id":"2504.12717","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12717","created_at":"2026-07-05T10:50:21Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12717v1","created_at":"2026-07-05T10:50:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12717","created_at":"2026-07-05T10:50:21Z"},{"alias_kind":"pith_short_12","alias_value":"LJYDFZ3S3KGL","created_at":"2026-07-05T10:50:21Z"},{"alias_kind":"pith_short_16","alias_value":"LJYDFZ3S3KGL4OR6","created_at":"2026-07-05T10:50:21Z"},{"alias_kind":"pith_short_8","alias_value":"LJYDFZ3S","created_at":"2026-07-05T10:50:21Z"}],"graph_snapshots":[{"event_id":"sha256:76985115a654a18051c48d14dac8707e67716c22bb8742d70aee846d75774818","target":"graph","created_at":"2026-07-05T10:50:21Z","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/2504.12717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive language image pre-training (CLIP) is an essential component of building modern vision-language foundation models. While CLIP demonstrates remarkable zero-shot performance on downstream tasks, the multi-modal feature spaces still suffer from a modality gap, which is a gap between image and text feature clusters and limits downstream task performance. Although existing works attempt to address the modality gap by modifying pre-training or fine-tuning, they struggle with heavy training costs with large datasets or degradations of zero-shot performance. This paper presents CLIP-Refine","authors_text":"Daiki Chijiwa, Dewei Feng, Kazuki Adachi, Sekitoshi Kanai, Shin'ya Yamaguchi","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-17T07:46:19Z","title":"Post-pre-training for Modality Alignment in Vision-Language Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12717","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":"sha256:0f4624740b23573e33ac64b261913a81bcd03cc320171f3c324a7382be7d4b5e","target":"record","created_at":"2026-07-05T10:50:21Z","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":"b999bcf741c10a6b22e44ee2f1d86c18e04bef726a247a0ad9ce656ab3f3ef37","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-17T07:46:19Z","title_canon_sha256":"022088fddf1c3864ecb1f84d03f92941b69cecf0b2eb6e5c5e0a90456a9bd628"},"schema_version":"1.0","source":{"id":"2504.12717","kind":"arxiv","version":1}},"canonical_sha256":"5a7032e772da8cbe3a3e3daa15716225783c90480b3725ecd437ef23f62b7a7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a7032e772da8cbe3a3e3daa15716225783c90480b3725ecd437ef23f62b7a7b","first_computed_at":"2026-07-05T10:50:21.188829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:21.188829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oF0pEkK4tnmpQRZa/gk9gPkcC90y4avNYJWgu7Zwd31cVDWywLmrbFYRjtO9LBn/PKy9AxVsV0qkguHG7gWeAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:21.189242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12717","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f4624740b23573e33ac64b261913a81bcd03cc320171f3c324a7382be7d4b5e","sha256:76985115a654a18051c48d14dac8707e67716c22bb8742d70aee846d75774818"],"state_sha256":"8252c946e04ae277567784f44df73289d936cd7288a392fa35cef6ebb80a393f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pc9c7nk9JWybk6B/bn9upuHGelzTIfhd4spBQswulpYfk4nzoEGvmJ1T1pCBO9hOC47+TbKXkgY8L0krtNMIDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T13:13:00.188476Z","bundle_sha256":"01d35df97212222723f6311adf7b159e3ce18a6f814e4752e55826159a11f0dc"}}