{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BQKL5GIH6INWZL5NRWNHFLU6QD","short_pith_number":"pith:BQKL5GIH","canonical_record":{"source":{"id":"2503.19900","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T17:57:17Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"320557c3f368f46022ca1806c2bbd310ea5d0bc4199666cec8e65d1166fe7f13","abstract_canon_sha256":"9b459f0edf4b3cb10d7893939b79243126e068cd7314d2753326254500d3a95e"},"schema_version":"1.0"},"canonical_sha256":"0c14be9907f21b6cafad8d9a72ae9e80e55097a6de956ef2f1338a05f8d4ccb2","source":{"kind":"arxiv","id":"2503.19900","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19900","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19900v1","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19900","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"pith_short_12","alias_value":"BQKL5GIH6INW","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"pith_short_16","alias_value":"BQKL5GIH6INWZL5N","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"pith_short_8","alias_value":"BQKL5GIH","created_at":"2026-07-05T10:39:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BQKL5GIH6INWZL5NRWNHFLU6QD","target":"record","payload":{"canonical_record":{"source":{"id":"2503.19900","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T17:57:17Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"320557c3f368f46022ca1806c2bbd310ea5d0bc4199666cec8e65d1166fe7f13","abstract_canon_sha256":"9b459f0edf4b3cb10d7893939b79243126e068cd7314d2753326254500d3a95e"},"schema_version":"1.0"},"canonical_sha256":"0c14be9907f21b6cafad8d9a72ae9e80e55097a6de956ef2f1338a05f8d4ccb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:03.330293Z","signature_b64":"L1uqNG4mdeIyeWjhICI5r/y2LWZetlR+ifLYPKIzzqery8RFLmL6rz7+ojaBfV4m1PkerC/yb3crMExdDRnqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c14be9907f21b6cafad8d9a72ae9e80e55097a6de956ef2f1338a05f8d4ccb2","last_reissued_at":"2026-07-05T10:39:03.329811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:03.329811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.19900","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":"2026-07-05T10:39:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pgpe6sgAh4mN/OjpQBGIiz43hKSmoNts36uGT5fmDXYNlUsMfagkLlujjeHMdg6iM+uwCGIggpYpV6hPmYRwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:23:28.960959Z"},"content_sha256":"1e9d5124eb857f83980d3149b76d9e68ca0952440813f5484c5cfd2f44599ec8","schema_version":"1.0","event_id":"sha256:1e9d5124eb857f83980d3149b76d9e68ca0952440813f5484c5cfd2f44599ec8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BQKL5GIH6INWZL5NRWNHFLU6QD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Baosheng He, Hanchao Yu, Hao Yu, Jianyu Wang, Jiayi Liu, Lizhu Zhang, Lukasz Korycki, Shen Yan, Xiangjun Fan, Zhuokai Zhao","submitted_at":"2025-03-25T17:57:17Z","abstract_excerpt":"The rapid advancement of large vision-language models (LVLMs) has driven significant progress in multimodal tasks, enabling models to interpret, reason, and generate outputs across both visual and textual domains. While excelling in generative tasks, existing LVLMs often face limitations in tasks requiring high-fidelity representation learning, such as generating image or text embeddings for retrieval. Recent work has proposed finetuning LVLMs for representational learning, but the fine-tuned model often loses its generative capabilities due to the representational learning training paradigm. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19900","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/2503.19900/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":"2026-07-05T10:39:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v3GcSLgFG/hNFDqAq3aUmxv8LIxcisPFMckExPS8YF9zrzZv5wJZ18VhcazUyfbu064GR141yDIXWimSD4l6Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:23:28.962517Z"},"content_sha256":"87ab805625d1f4f00a7072039ad5b7feea9ef966614300ba66f0aed5a5d2ad04","schema_version":"1.0","event_id":"sha256:87ab805625d1f4f00a7072039ad5b7feea9ef966614300ba66f0aed5a5d2ad04"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BQKL5GIH6INWZL5NRWNHFLU6QD/bundle.json","state_url":"https://pith.science/pith/BQKL5GIH6INWZL5NRWNHFLU6QD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BQKL5GIH6INWZL5NRWNHFLU6QD/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":"2026-08-05T01:23:28Z","links":{"resolver":"https://pith.science/pith/BQKL5GIH6INWZL5NRWNHFLU6QD","bundle":"https://pith.science/pith/BQKL5GIH6INWZL5NRWNHFLU6QD/bundle.json","state":"https://pith.science/pith/BQKL5GIH6INWZL5NRWNHFLU6QD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BQKL5GIH6INWZL5NRWNHFLU6QD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BQKL5GIH6INWZL5NRWNHFLU6QD","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":"9b459f0edf4b3cb10d7893939b79243126e068cd7314d2753326254500d3a95e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T17:57:17Z","title_canon_sha256":"320557c3f368f46022ca1806c2bbd310ea5d0bc4199666cec8e65d1166fe7f13"},"schema_version":"1.0","source":{"id":"2503.19900","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19900","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19900v1","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19900","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"pith_short_12","alias_value":"BQKL5GIH6INW","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"pith_short_16","alias_value":"BQKL5GIH6INWZL5N","created_at":"2026-07-05T10:39:03Z"},{"alias_kind":"pith_short_8","alias_value":"BQKL5GIH","created_at":"2026-07-05T10:39:03Z"}],"graph_snapshots":[{"event_id":"sha256:87ab805625d1f4f00a7072039ad5b7feea9ef966614300ba66f0aed5a5d2ad04","target":"graph","created_at":"2026-07-05T10:39:03Z","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/2503.19900/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancement of large vision-language models (LVLMs) has driven significant progress in multimodal tasks, enabling models to interpret, reason, and generate outputs across both visual and textual domains. While excelling in generative tasks, existing LVLMs often face limitations in tasks requiring high-fidelity representation learning, such as generating image or text embeddings for retrieval. Recent work has proposed finetuning LVLMs for representational learning, but the fine-tuned model often loses its generative capabilities due to the representational learning training paradigm. ","authors_text":"Baosheng He, Hanchao Yu, Hao Yu, Jianyu Wang, Jiayi Liu, Lizhu Zhang, Lukasz Korycki, Shen Yan, Xiangjun Fan, Zhuokai Zhao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T17:57:17Z","title":"CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19900","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":"sha256:1e9d5124eb857f83980d3149b76d9e68ca0952440813f5484c5cfd2f44599ec8","target":"record","created_at":"2026-07-05T10:39:03Z","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":"9b459f0edf4b3cb10d7893939b79243126e068cd7314d2753326254500d3a95e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T17:57:17Z","title_canon_sha256":"320557c3f368f46022ca1806c2bbd310ea5d0bc4199666cec8e65d1166fe7f13"},"schema_version":"1.0","source":{"id":"2503.19900","kind":"arxiv","version":1}},"canonical_sha256":"0c14be9907f21b6cafad8d9a72ae9e80e55097a6de956ef2f1338a05f8d4ccb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c14be9907f21b6cafad8d9a72ae9e80e55097a6de956ef2f1338a05f8d4ccb2","first_computed_at":"2026-07-05T10:39:03.329811Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:03.329811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L1uqNG4mdeIyeWjhICI5r/y2LWZetlR+ifLYPKIzzqery8RFLmL6rz7+ojaBfV4m1PkerC/yb3crMExdDRnqDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:03.330293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.19900","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e9d5124eb857f83980d3149b76d9e68ca0952440813f5484c5cfd2f44599ec8","sha256:87ab805625d1f4f00a7072039ad5b7feea9ef966614300ba66f0aed5a5d2ad04"],"state_sha256":"ec43ce2783a393f68b8ea285af31ff34de01cade1807b222460e1740cb359014"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9J6TSmYqNI1V/FXyJcBySEHs+UBscsO2oJTPLVNb/W/xB0x+W7uz07aQa3nXfO83mpPw/io4lH9fMGbd5eQCCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:23:28.973813Z","bundle_sha256":"57e984e2500ab349492bd58080746ac4d404333b2d71370701a8f84807ea74fa"}}