{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:O7QSKCDIU5GUEY56KPQJORHLF3","short_pith_number":"pith:O7QSKCDI","canonical_record":{"source":{"id":"2405.19716","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T05:53:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"889e9183b3720f237ff9205feafbe9c1e3b50c1720e129015e7254b861f7bfaa","abstract_canon_sha256":"3ee3435cfd812f082277ca2fbcad206419ed50b281f10276fdfc4486efc848f5"},"schema_version":"1.0"},"canonical_sha256":"77e1250868a74d4263be53e09744eb2ed25f5e8aa0e1f9709216c6d96eee9ba9","source":{"kind":"arxiv","id":"2405.19716","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19716","created_at":"2026-07-05T09:39:23Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19716v2","created_at":"2026-07-05T09:39:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19716","created_at":"2026-07-05T09:39:23Z"},{"alias_kind":"pith_short_12","alias_value":"O7QSKCDIU5GU","created_at":"2026-07-05T09:39:23Z"},{"alias_kind":"pith_short_16","alias_value":"O7QSKCDIU5GUEY56","created_at":"2026-07-05T09:39:23Z"},{"alias_kind":"pith_short_8","alias_value":"O7QSKCDI","created_at":"2026-07-05T09:39:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:O7QSKCDIU5GUEY56KPQJORHLF3","target":"record","payload":{"canonical_record":{"source":{"id":"2405.19716","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T05:53:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"889e9183b3720f237ff9205feafbe9c1e3b50c1720e129015e7254b861f7bfaa","abstract_canon_sha256":"3ee3435cfd812f082277ca2fbcad206419ed50b281f10276fdfc4486efc848f5"},"schema_version":"1.0"},"canonical_sha256":"77e1250868a74d4263be53e09744eb2ed25f5e8aa0e1f9709216c6d96eee9ba9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:23.598810Z","signature_b64":"qdAkZ5TiqlV5H3Zhs19CT7jgxYeTniXhQmGwwdftlc8NrLIqTaHmewC2DqROVWJwbGYBLjSU6ymcZQ4dCUMgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77e1250868a74d4263be53e09744eb2ed25f5e8aa0e1f9709216c6d96eee9ba9","last_reissued_at":"2026-07-05T09:39:23.598308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:23.598308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.19716","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:39:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"306G6evLd4qzvCt5NpBB4Ck9M5LpCxhqahxn5sZAGFcmr0ahfVh3yrO8m8XI0kGFZBsOzEFrYRMVwYtlsvDKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:38:32.460233Z"},"content_sha256":"e174de904829205668283754ff26be57793d46be08021d7f86af1634f6bf9dc9","schema_version":"1.0","event_id":"sha256:e174de904829205668283754ff26be57793d46be08021d7f86af1634f6bf9dc9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:O7QSKCDIU5GUEY56KPQJORHLF3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Large Vision Language Models with Self-Training on Image Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fan Yin, James Zou, Kai-Wei Chang, Pan Lu, Quanquan Gu, Sheng Shen, Wei Wang, Yihe Deng, Ziniu Hu","submitted_at":"2024-05-30T05:53:49Z","abstract_excerpt":"Large vision language models (LVLMs) integrate large language models (LLMs) with pre-trained vision encoders, thereby activating the perception capability of the model to understand image inputs for different queries and conduct subsequent reasoning. Improving this capability requires high-quality vision-language data, which is costly and labor-intensive to acquire. Self-training approaches have been effective in single-modal settings to alleviate the need for labeled data by leveraging model's own generation. However, effective self-training remains a challenge regarding the unique visual per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19716","kind":"arxiv","version":2},"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/2405.19716/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":"2026-07-05T09:39:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SccidRINYDcYa+TRnLlox9kGDgTNACoTA5p6IEh5KESr7KHs03uIJ0n82OzoCQEnHwUb6SV6Ijyc1Siu6MFXCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:38:32.461197Z"},"content_sha256":"131b2c4a46644c02208ee8dc16a12e0cd9eb8065e33d1d6feb36084a199778ac","schema_version":"1.0","event_id":"sha256:131b2c4a46644c02208ee8dc16a12e0cd9eb8065e33d1d6feb36084a199778ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O7QSKCDIU5GUEY56KPQJORHLF3/bundle.json","state_url":"https://pith.science/pith/O7QSKCDIU5GUEY56KPQJORHLF3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O7QSKCDIU5GUEY56KPQJORHLF3/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":"2026-08-07T10:38:32Z","links":{"resolver":"https://pith.science/pith/O7QSKCDIU5GUEY56KPQJORHLF3","bundle":"https://pith.science/pith/O7QSKCDIU5GUEY56KPQJORHLF3/bundle.json","state":"https://pith.science/pith/O7QSKCDIU5GUEY56KPQJORHLF3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O7QSKCDIU5GUEY56KPQJORHLF3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O7QSKCDIU5GUEY56KPQJORHLF3","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":"3ee3435cfd812f082277ca2fbcad206419ed50b281f10276fdfc4486efc848f5","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T05:53:49Z","title_canon_sha256":"889e9183b3720f237ff9205feafbe9c1e3b50c1720e129015e7254b861f7bfaa"},"schema_version":"1.0","source":{"id":"2405.19716","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19716","created_at":"2026-07-05T09:39:23Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19716v2","created_at":"2026-07-05T09:39:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19716","created_at":"2026-07-05T09:39:23Z"},{"alias_kind":"pith_short_12","alias_value":"O7QSKCDIU5GU","created_at":"2026-07-05T09:39:23Z"},{"alias_kind":"pith_short_16","alias_value":"O7QSKCDIU5GUEY56","created_at":"2026-07-05T09:39:23Z"},{"alias_kind":"pith_short_8","alias_value":"O7QSKCDI","created_at":"2026-07-05T09:39:23Z"}],"graph_snapshots":[{"event_id":"sha256:131b2c4a46644c02208ee8dc16a12e0cd9eb8065e33d1d6feb36084a199778ac","target":"graph","created_at":"2026-07-05T09:39:23Z","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/2405.19716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large vision language models (LVLMs) integrate large language models (LLMs) with pre-trained vision encoders, thereby activating the perception capability of the model to understand image inputs for different queries and conduct subsequent reasoning. Improving this capability requires high-quality vision-language data, which is costly and labor-intensive to acquire. Self-training approaches have been effective in single-modal settings to alleviate the need for labeled data by leveraging model's own generation. However, effective self-training remains a challenge regarding the unique visual per","authors_text":"Fan Yin, James Zou, Kai-Wei Chang, Pan Lu, Quanquan Gu, Sheng Shen, Wei Wang, Yihe Deng, Ziniu Hu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T05:53:49Z","title":"Enhancing Large Vision Language Models with Self-Training on Image Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19716","kind":"arxiv","version":2},"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:e174de904829205668283754ff26be57793d46be08021d7f86af1634f6bf9dc9","target":"record","created_at":"2026-07-05T09:39:23Z","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":"3ee3435cfd812f082277ca2fbcad206419ed50b281f10276fdfc4486efc848f5","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T05:53:49Z","title_canon_sha256":"889e9183b3720f237ff9205feafbe9c1e3b50c1720e129015e7254b861f7bfaa"},"schema_version":"1.0","source":{"id":"2405.19716","kind":"arxiv","version":2}},"canonical_sha256":"77e1250868a74d4263be53e09744eb2ed25f5e8aa0e1f9709216c6d96eee9ba9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77e1250868a74d4263be53e09744eb2ed25f5e8aa0e1f9709216c6d96eee9ba9","first_computed_at":"2026-07-05T09:39:23.598308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:23.598308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qdAkZ5TiqlV5H3Zhs19CT7jgxYeTniXhQmGwwdftlc8NrLIqTaHmewC2DqROVWJwbGYBLjSU6ymcZQ4dCUMgCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:23.598810Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19716","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e174de904829205668283754ff26be57793d46be08021d7f86af1634f6bf9dc9","sha256:131b2c4a46644c02208ee8dc16a12e0cd9eb8065e33d1d6feb36084a199778ac"],"state_sha256":"281912667be1bac490b2762e01649e9b84a85d6e51c16f4cebd29f15cf70c946"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iRxDyWGOrzLpCJ462XiG1PgmvkqXsIBnnAAfmfXXSfN52QBO01ra9yfZLlhB1xm/Iy24ouPxtP+sqw2Vxc6XAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:38:32.468057Z","bundle_sha256":"036e7118ff764e9dfad1533a02f12227ee846137aac9304e6d46f62e53114245"}}