{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RMMMR63Q2EZS3STSXK7B6VJ6SO","short_pith_number":"pith:RMMMR63Q","canonical_record":{"source":{"id":"2505.23271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T09:19:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1b5a087c2d7429f5d67b37f580d9ed18037be1ac0ad186371c2cbb1253d52adf","abstract_canon_sha256":"e47d626561d7d0ed44b5d7baa00f3566acb6813525f0b3f6bd7d15121e23e73d"},"schema_version":"1.0"},"canonical_sha256":"8b18c8fb70d1332dca72babe1f553e93b583a7374183530b0bf870c78c5c1e8c","source":{"kind":"arxiv","id":"2505.23271","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23271","created_at":"2026-07-05T11:11:58Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23271v1","created_at":"2026-07-05T11:11:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23271","created_at":"2026-07-05T11:11:58Z"},{"alias_kind":"pith_short_12","alias_value":"RMMMR63Q2EZS","created_at":"2026-07-05T11:11:58Z"},{"alias_kind":"pith_short_16","alias_value":"RMMMR63Q2EZS3STS","created_at":"2026-07-05T11:11:58Z"},{"alias_kind":"pith_short_8","alias_value":"RMMMR63Q","created_at":"2026-07-05T11:11:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RMMMR63Q2EZS3STSXK7B6VJ6SO","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T09:19:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1b5a087c2d7429f5d67b37f580d9ed18037be1ac0ad186371c2cbb1253d52adf","abstract_canon_sha256":"e47d626561d7d0ed44b5d7baa00f3566acb6813525f0b3f6bd7d15121e23e73d"},"schema_version":"1.0"},"canonical_sha256":"8b18c8fb70d1332dca72babe1f553e93b583a7374183530b0bf870c78c5c1e8c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:58.668531Z","signature_b64":"ET7V1NaPiIL3aOSFyV/ZpvbuiQRJCqr+1pwjSH3ZxDoOpKvJNjtGyc2d/O0QTfTZj6K3Oou3OlFF5gyEEAxpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b18c8fb70d1332dca72babe1f553e93b583a7374183530b0bf870c78c5c1e8c","last_reissued_at":"2026-07-05T11:11:58.668037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:58.668037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23271","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":"2026-07-05T11:11:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nS6wZOpV2g0xkVGFzp43kFiGgdLo9wCsL9BjKMxlIXj+oD3fh6PspbA9lVyRkcqpzpLWCI6UuWZkbBE726d6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:41:52.880964Z"},"content_sha256":"9b219638e6f2473c77e20322e98132dc2b3ec78726dc0790db59b6af96212eda","schema_version":"1.0","event_id":"sha256:9b219638e6f2473c77e20322e98132dc2b3ec78726dc0790db59b6af96212eda"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RMMMR63Q2EZS3STSXK7B6VJ6SO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LADA: Scalable Label-Specific CLIP Adapter for Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Mao-Lin Luo, Min-Ling Zhang, Tong Wei, Zi-Hao Zhou","submitted_at":"2025-05-29T09:19:51Z","abstract_excerpt":"Continual learning with vision-language models like CLIP offers a pathway toward scalable machine learning systems by leveraging its transferable representations. Existing CLIP-based methods adapt the pre-trained image encoder by adding multiple sets of learnable parameters, with each task using a partial set of parameters. This requires selecting the expected parameters for input images during inference, which is prone to error that degrades performance. To address this problem, we introduce LADA (Label-specific ADApter). Instead of partitioning parameters across tasks, LADA appends lightweig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23271","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/2505.23271/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":"2026-07-05T11:11:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N9y3Qsyv4l1rMbIfd7TkyhZOdSoatHkoWL34ZWDdKjU2eqAD+m8Mfz+aolx/hYHV1fElUk9Hejtw/HTCw9VuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:41:52.881353Z"},"content_sha256":"9775dfd7ef844bf514f3f28a67625b059962c25c6e579058a05c5e0197d777db","schema_version":"1.0","event_id":"sha256:9775dfd7ef844bf514f3f28a67625b059962c25c6e579058a05c5e0197d777db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RMMMR63Q2EZS3STSXK7B6VJ6SO/bundle.json","state_url":"https://pith.science/pith/RMMMR63Q2EZS3STSXK7B6VJ6SO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RMMMR63Q2EZS3STSXK7B6VJ6SO/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":"2026-07-05T14:41:52Z","links":{"resolver":"https://pith.science/pith/RMMMR63Q2EZS3STSXK7B6VJ6SO","bundle":"https://pith.science/pith/RMMMR63Q2EZS3STSXK7B6VJ6SO/bundle.json","state":"https://pith.science/pith/RMMMR63Q2EZS3STSXK7B6VJ6SO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RMMMR63Q2EZS3STSXK7B6VJ6SO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RMMMR63Q2EZS3STSXK7B6VJ6SO","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":"e47d626561d7d0ed44b5d7baa00f3566acb6813525f0b3f6bd7d15121e23e73d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T09:19:51Z","title_canon_sha256":"1b5a087c2d7429f5d67b37f580d9ed18037be1ac0ad186371c2cbb1253d52adf"},"schema_version":"1.0","source":{"id":"2505.23271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23271","created_at":"2026-07-05T11:11:58Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23271v1","created_at":"2026-07-05T11:11:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23271","created_at":"2026-07-05T11:11:58Z"},{"alias_kind":"pith_short_12","alias_value":"RMMMR63Q2EZS","created_at":"2026-07-05T11:11:58Z"},{"alias_kind":"pith_short_16","alias_value":"RMMMR63Q2EZS3STS","created_at":"2026-07-05T11:11:58Z"},{"alias_kind":"pith_short_8","alias_value":"RMMMR63Q","created_at":"2026-07-05T11:11:58Z"}],"graph_snapshots":[{"event_id":"sha256:9775dfd7ef844bf514f3f28a67625b059962c25c6e579058a05c5e0197d777db","target":"graph","created_at":"2026-07-05T11:11:58Z","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/2505.23271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continual learning with vision-language models like CLIP offers a pathway toward scalable machine learning systems by leveraging its transferable representations. Existing CLIP-based methods adapt the pre-trained image encoder by adding multiple sets of learnable parameters, with each task using a partial set of parameters. This requires selecting the expected parameters for input images during inference, which is prone to error that degrades performance. To address this problem, we introduce LADA (Label-specific ADApter). Instead of partitioning parameters across tasks, LADA appends lightweig","authors_text":"Mao-Lin Luo, Min-Ling Zhang, Tong Wei, Zi-Hao Zhou","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T09:19:51Z","title":"LADA: Scalable Label-Specific CLIP Adapter for Continual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23271","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":"sha256:9b219638e6f2473c77e20322e98132dc2b3ec78726dc0790db59b6af96212eda","target":"record","created_at":"2026-07-05T11:11:58Z","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":"e47d626561d7d0ed44b5d7baa00f3566acb6813525f0b3f6bd7d15121e23e73d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T09:19:51Z","title_canon_sha256":"1b5a087c2d7429f5d67b37f580d9ed18037be1ac0ad186371c2cbb1253d52adf"},"schema_version":"1.0","source":{"id":"2505.23271","kind":"arxiv","version":1}},"canonical_sha256":"8b18c8fb70d1332dca72babe1f553e93b583a7374183530b0bf870c78c5c1e8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b18c8fb70d1332dca72babe1f553e93b583a7374183530b0bf870c78c5c1e8c","first_computed_at":"2026-07-05T11:11:58.668037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:58.668037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ET7V1NaPiIL3aOSFyV/ZpvbuiQRJCqr+1pwjSH3ZxDoOpKvJNjtGyc2d/O0QTfTZj6K3Oou3OlFF5gyEEAxpAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:58.668531Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b219638e6f2473c77e20322e98132dc2b3ec78726dc0790db59b6af96212eda","sha256:9775dfd7ef844bf514f3f28a67625b059962c25c6e579058a05c5e0197d777db"],"state_sha256":"1d9be47721f47e433e6e9f0dfe3de4a814d174fc9d1ecbe93817e118d2d60aa2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vNSS1zzNfJcgZ2LvfxORQyy7aGAzZOPRmau8kF95pFcIB0Ve1UEgvqU7pL3JIRWWFUWTr1vDUdT37oKfj9+sCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T14:41:52.883325Z","bundle_sha256":"e889c5e4833c5ff5eb283713c8f9b2d5c180ac7715710bf4774b5a534a70d6b5"}}