{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2TO4FBZ7OBDQX45STNLXQLGFLK","short_pith_number":"pith:2TO4FBZ7","canonical_record":{"source":{"id":"2506.07484","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T07:04:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"127b2411aedcc2aa07f861bf3e89b0cc40e31fe0289ee069905e84466608130e","abstract_canon_sha256":"0a9b01cd59f5ca9326e61558dcaf289f8dc9bdf15b02134632e733063ac1ad86"},"schema_version":"1.0"},"canonical_sha256":"d4ddc2873f70470bf3b29b57782cc55aa664d83d2f13688442eec5d66843914a","source":{"kind":"arxiv","id":"2506.07484","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07484","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07484v1","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07484","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"2TO4FBZ7OBDQ","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_16","alias_value":"2TO4FBZ7OBDQX45S","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_8","alias_value":"2TO4FBZ7","created_at":"2026-07-05T11:18:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2TO4FBZ7OBDQX45STNLXQLGFLK","target":"record","payload":{"canonical_record":{"source":{"id":"2506.07484","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T07:04:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"127b2411aedcc2aa07f861bf3e89b0cc40e31fe0289ee069905e84466608130e","abstract_canon_sha256":"0a9b01cd59f5ca9326e61558dcaf289f8dc9bdf15b02134632e733063ac1ad86"},"schema_version":"1.0"},"canonical_sha256":"d4ddc2873f70470bf3b29b57782cc55aa664d83d2f13688442eec5d66843914a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:28.051123Z","signature_b64":"5dDdBr3Zfi+uGgMELNUDmPpVLUnaxMn1kXpK5/Ex+sHzlZowTGiKo3QgBt/Pm1PoVELr9VujoK8a2lKzO2plAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4ddc2873f70470bf3b29b57782cc55aa664d83d2f13688442eec5d66843914a","last_reissued_at":"2026-07-05T11:18:28.050595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:28.050595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.07484","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":"2026-07-05T11:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Knw8ccJKewHP0z2RTd+VARYBKkZU3kJfZfj/FY/BfgbkCLoasodmYZcSbZLuaPEwWGwmbIp+UNa9Z/LzAOMZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:51:58.021080Z"},"content_sha256":"e3a0ed9cea48b8b0b6f0941cd2f2b523ab706e118886e012a058fdbaf897f12e","schema_version":"1.0","event_id":"sha256:e3a0ed9cea48b8b0b6f0941cd2f2b523ab706e118886e012a058fdbaf897f12e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2TO4FBZ7OBDQX45STNLXQLGFLK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoCoA-Mix: Confusion-and-Confidence-Aware Mixture Model for Context Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dasol Hong, Hyun Myung, Wooju Lee","submitted_at":"2025-06-09T07:04:47Z","abstract_excerpt":"Prompt tuning, which adapts vision-language models by freezing model parameters and optimizing only the prompt, has proven effective for task-specific adaptations. The core challenge in prompt tuning is improving specialization for a specific task and generalization for unseen domains. However, frozen encoders often produce misaligned features, leading to confusion between classes and limiting specialization. To overcome this issue, we propose a confusion-aware loss (CoA-loss) that improves specialization by refining the decision boundaries between confusing classes. Additionally, we mathemati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07484","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/2506.07484/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":"2026-07-05T11:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nm0s1a1thxuOMZEubuTlIZ+uxvIPn+jqGUShz595V2al78OOBS/c7Bo7lhUjyGDfMf3KvQD9JC7MD21jeqsWAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:51:58.021626Z"},"content_sha256":"d22921eaca5d3151627ce534507f563e6b0089827daba3576f39ed3b5e253d71","schema_version":"1.0","event_id":"sha256:d22921eaca5d3151627ce534507f563e6b0089827daba3576f39ed3b5e253d71"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2TO4FBZ7OBDQX45STNLXQLGFLK/bundle.json","state_url":"https://pith.science/pith/2TO4FBZ7OBDQX45STNLXQLGFLK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2TO4FBZ7OBDQX45STNLXQLGFLK/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":"2026-08-07T23:51:58Z","links":{"resolver":"https://pith.science/pith/2TO4FBZ7OBDQX45STNLXQLGFLK","bundle":"https://pith.science/pith/2TO4FBZ7OBDQX45STNLXQLGFLK/bundle.json","state":"https://pith.science/pith/2TO4FBZ7OBDQX45STNLXQLGFLK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2TO4FBZ7OBDQX45STNLXQLGFLK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2TO4FBZ7OBDQX45STNLXQLGFLK","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":"0a9b01cd59f5ca9326e61558dcaf289f8dc9bdf15b02134632e733063ac1ad86","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T07:04:47Z","title_canon_sha256":"127b2411aedcc2aa07f861bf3e89b0cc40e31fe0289ee069905e84466608130e"},"schema_version":"1.0","source":{"id":"2506.07484","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07484","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07484v1","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07484","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"2TO4FBZ7OBDQ","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_16","alias_value":"2TO4FBZ7OBDQX45S","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_8","alias_value":"2TO4FBZ7","created_at":"2026-07-05T11:18:28Z"}],"graph_snapshots":[{"event_id":"sha256:d22921eaca5d3151627ce534507f563e6b0089827daba3576f39ed3b5e253d71","target":"graph","created_at":"2026-07-05T11:18:28Z","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/2506.07484/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompt tuning, which adapts vision-language models by freezing model parameters and optimizing only the prompt, has proven effective for task-specific adaptations. The core challenge in prompt tuning is improving specialization for a specific task and generalization for unseen domains. However, frozen encoders often produce misaligned features, leading to confusion between classes and limiting specialization. To overcome this issue, we propose a confusion-aware loss (CoA-loss) that improves specialization by refining the decision boundaries between confusing classes. Additionally, we mathemati","authors_text":"Dasol Hong, Hyun Myung, Wooju Lee","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T07:04:47Z","title":"CoCoA-Mix: Confusion-and-Confidence-Aware Mixture Model for Context Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07484","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:e3a0ed9cea48b8b0b6f0941cd2f2b523ab706e118886e012a058fdbaf897f12e","target":"record","created_at":"2026-07-05T11:18:28Z","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":"0a9b01cd59f5ca9326e61558dcaf289f8dc9bdf15b02134632e733063ac1ad86","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T07:04:47Z","title_canon_sha256":"127b2411aedcc2aa07f861bf3e89b0cc40e31fe0289ee069905e84466608130e"},"schema_version":"1.0","source":{"id":"2506.07484","kind":"arxiv","version":1}},"canonical_sha256":"d4ddc2873f70470bf3b29b57782cc55aa664d83d2f13688442eec5d66843914a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4ddc2873f70470bf3b29b57782cc55aa664d83d2f13688442eec5d66843914a","first_computed_at":"2026-07-05T11:18:28.050595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:28.050595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5dDdBr3Zfi+uGgMELNUDmPpVLUnaxMn1kXpK5/Ex+sHzlZowTGiKo3QgBt/Pm1PoVELr9VujoK8a2lKzO2plAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:28.051123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07484","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3a0ed9cea48b8b0b6f0941cd2f2b523ab706e118886e012a058fdbaf897f12e","sha256:d22921eaca5d3151627ce534507f563e6b0089827daba3576f39ed3b5e253d71"],"state_sha256":"1ff4e53038df906ca341ca790e0a379324879c9bee4fa35de35bbe043fc1a923"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oNIgPkruR6Bykmdkh9UNvO19Xxw9fVNTjwFlDsp7Mf5dv36U+gabgKtpyUJId82SL/jUjV6iA3QrrovxVJNzCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:51:58.025673Z","bundle_sha256":"d5f38287e5e18ec30c9e3928d0eb462aae6846a379bb6f87948988adfca03e4d"}}