{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KQA7DYW6Q33DSO7XNLAI3WK5WW","short_pith_number":"pith:KQA7DYW6","canonical_record":{"source":{"id":"2312.10665","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-17T09:44:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"12534fd8a702fd445eb56a183266aa9a2c828ea84200314b9564df4e3f059c09","abstract_canon_sha256":"114ec248dddbf3686820f868b3fa8dd86ac396b4be9bdda6bfe523bdbae3397c"},"schema_version":"1.0"},"canonical_sha256":"5401f1e2de86f6393bf76ac08dd95db5951b4e73f2e5971006e2967837513244","source":{"kind":"arxiv","id":"2312.10665","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10665","created_at":"2026-07-05T07:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10665v1","created_at":"2026-07-05T07:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10665","created_at":"2026-07-05T07:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"KQA7DYW6Q33D","created_at":"2026-07-05T07:25:10Z"},{"alias_kind":"pith_short_16","alias_value":"KQA7DYW6Q33DSO7X","created_at":"2026-07-05T07:25:10Z"},{"alias_kind":"pith_short_8","alias_value":"KQA7DYW6","created_at":"2026-07-05T07:25:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KQA7DYW6Q33DSO7XNLAI3WK5WW","target":"record","payload":{"canonical_record":{"source":{"id":"2312.10665","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-17T09:44:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"12534fd8a702fd445eb56a183266aa9a2c828ea84200314b9564df4e3f059c09","abstract_canon_sha256":"114ec248dddbf3686820f868b3fa8dd86ac396b4be9bdda6bfe523bdbae3397c"},"schema_version":"1.0"},"canonical_sha256":"5401f1e2de86f6393bf76ac08dd95db5951b4e73f2e5971006e2967837513244","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:10.406966Z","signature_b64":"WrfkF97xA6EAl/9GKhXTbSpVWXddcvKJ0zGGJ+RdNpDljTYSr8ycr8sUliQ2D0qY2ObKrGvD8V0mhisuBJL9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5401f1e2de86f6393bf76ac08dd95db5951b4e73f2e5971006e2967837513244","last_reissued_at":"2026-07-05T07:25:10.406496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:10.406496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.10665","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":"2026-07-05T07:25:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+oMxLIvNSCLwYMpIvOW3qgGatxvaw5h85B2xzButl90/TKjKL4/NetnGIUc3qTMkIGrfQ+b/ZCKVoN094B5bCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T01:50:16.734455Z"},"content_sha256":"ba58bd2925bda49b4d23b3883da3d5f9585316aafd28985a96d61b0dd7482a47","schema_version":"1.0","event_id":"sha256:ba58bd2925bda49b4d23b3883da3d5f9585316aafd28985a96d61b0dd7482a47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KQA7DYW6Q33DSO7XNLAI3WK5WW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Silkie: Preference Distillation for Large Visual Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Benyou Wang, Lei Li, Liang Chen, Lingpeng Kong, Mukai Li, Peiyi Wang, Shunian Chen, Yazheng Yang, Zhihui Xie","submitted_at":"2023-12-17T09:44:27Z","abstract_excerpt":"This paper explores preference distillation for large vision language models (LVLMs), improving their ability to generate helpful and faithful responses anchoring the visual context. We first build a vision-language feedback (VLFeedback) dataset utilizing AI annotation. Specifically, responses are generated by models sampled from 12 LVLMs, conditioned on multi-modal instructions sourced from various datasets. We adopt GPT-4V to assess the generated outputs regarding helpfulness, visual faithfulness, and ethical considerations. Furthermore, the preference supervision is distilled into Qwen-VL-C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10665","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/2312.10665/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":"2026-07-05T07:25:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H+bcTHuvamKubWsMNcFEy8kQnvsMPZD97udrK+H6TlgtsgR+yCkKrYnBgy7dp8nl5W25kdaeLdPAKTsZi1QQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T01:50:16.734969Z"},"content_sha256":"5233602068ae8bba7e7b320c8818322d9ac68ae5c6cffca64f2c296187a9d522","schema_version":"1.0","event_id":"sha256:5233602068ae8bba7e7b320c8818322d9ac68ae5c6cffca64f2c296187a9d522"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KQA7DYW6Q33DSO7XNLAI3WK5WW/bundle.json","state_url":"https://pith.science/pith/KQA7DYW6Q33DSO7XNLAI3WK5WW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KQA7DYW6Q33DSO7XNLAI3WK5WW/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":"2026-08-17T01:50:16Z","links":{"resolver":"https://pith.science/pith/KQA7DYW6Q33DSO7XNLAI3WK5WW","bundle":"https://pith.science/pith/KQA7DYW6Q33DSO7XNLAI3WK5WW/bundle.json","state":"https://pith.science/pith/KQA7DYW6Q33DSO7XNLAI3WK5WW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KQA7DYW6Q33DSO7XNLAI3WK5WW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KQA7DYW6Q33DSO7XNLAI3WK5WW","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":"114ec248dddbf3686820f868b3fa8dd86ac396b4be9bdda6bfe523bdbae3397c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-17T09:44:27Z","title_canon_sha256":"12534fd8a702fd445eb56a183266aa9a2c828ea84200314b9564df4e3f059c09"},"schema_version":"1.0","source":{"id":"2312.10665","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10665","created_at":"2026-07-05T07:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10665v1","created_at":"2026-07-05T07:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10665","created_at":"2026-07-05T07:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"KQA7DYW6Q33D","created_at":"2026-07-05T07:25:10Z"},{"alias_kind":"pith_short_16","alias_value":"KQA7DYW6Q33DSO7X","created_at":"2026-07-05T07:25:10Z"},{"alias_kind":"pith_short_8","alias_value":"KQA7DYW6","created_at":"2026-07-05T07:25:10Z"}],"graph_snapshots":[{"event_id":"sha256:5233602068ae8bba7e7b320c8818322d9ac68ae5c6cffca64f2c296187a9d522","target":"graph","created_at":"2026-07-05T07:25:10Z","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/2312.10665/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores preference distillation for large vision language models (LVLMs), improving their ability to generate helpful and faithful responses anchoring the visual context. We first build a vision-language feedback (VLFeedback) dataset utilizing AI annotation. Specifically, responses are generated by models sampled from 12 LVLMs, conditioned on multi-modal instructions sourced from various datasets. We adopt GPT-4V to assess the generated outputs regarding helpfulness, visual faithfulness, and ethical considerations. Furthermore, the preference supervision is distilled into Qwen-VL-C","authors_text":"Benyou Wang, Lei Li, Liang Chen, Lingpeng Kong, Mukai Li, Peiyi Wang, Shunian Chen, Yazheng Yang, Zhihui Xie","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-17T09:44:27Z","title":"Silkie: Preference Distillation for Large Visual Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10665","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:ba58bd2925bda49b4d23b3883da3d5f9585316aafd28985a96d61b0dd7482a47","target":"record","created_at":"2026-07-05T07:25:10Z","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":"114ec248dddbf3686820f868b3fa8dd86ac396b4be9bdda6bfe523bdbae3397c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-17T09:44:27Z","title_canon_sha256":"12534fd8a702fd445eb56a183266aa9a2c828ea84200314b9564df4e3f059c09"},"schema_version":"1.0","source":{"id":"2312.10665","kind":"arxiv","version":1}},"canonical_sha256":"5401f1e2de86f6393bf76ac08dd95db5951b4e73f2e5971006e2967837513244","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5401f1e2de86f6393bf76ac08dd95db5951b4e73f2e5971006e2967837513244","first_computed_at":"2026-07-05T07:25:10.406496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:25:10.406496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WrfkF97xA6EAl/9GKhXTbSpVWXddcvKJ0zGGJ+RdNpDljTYSr8ycr8sUliQ2D0qY2ObKrGvD8V0mhisuBJL9BA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:25:10.406966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.10665","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba58bd2925bda49b4d23b3883da3d5f9585316aafd28985a96d61b0dd7482a47","sha256:5233602068ae8bba7e7b320c8818322d9ac68ae5c6cffca64f2c296187a9d522"],"state_sha256":"4764bc2140c9ee18ca9c416a91aebcea3dac6404a2a8ff5c5e0ba57319195df7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gDJnS9igdU/mt5PO6HVfzHboTnk2XEiTtHZa94WT74rhN/x4th42jxLYnpst8yXZzfPr/Vro9RhASJLS1kixBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T01:50:16.739820Z","bundle_sha256":"4b583831181713443a0e81e3c6e2cade5c41727892419a5b624b352614fb4d75"}}