{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HWKGJ7SMZBKI4RSN64HTJWAFE2","short_pith_number":"pith:HWKGJ7SM","canonical_record":{"source":{"id":"2505.08971","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-13T21:27:52Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b224f882801ce7020111049adadfd80e49372b2c8635a66989ef13a77a27e25f","abstract_canon_sha256":"bf6d20e31cea3518a011a66927b53177e2e4613277cb749dce9bac898259e129"},"schema_version":"1.0"},"canonical_sha256":"3d9464fe4cc8548e464df70f34d80526a0ae630b90a2a55883131b676d750d00","source":{"kind":"arxiv","id":"2505.08971","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08971","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08971v1","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08971","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"pith_short_12","alias_value":"HWKGJ7SMZBKI","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"pith_short_16","alias_value":"HWKGJ7SMZBKI4RSN","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"pith_short_8","alias_value":"HWKGJ7SM","created_at":"2026-07-05T11:02:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HWKGJ7SMZBKI4RSN64HTJWAFE2","target":"record","payload":{"canonical_record":{"source":{"id":"2505.08971","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-13T21:27:52Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b224f882801ce7020111049adadfd80e49372b2c8635a66989ef13a77a27e25f","abstract_canon_sha256":"bf6d20e31cea3518a011a66927b53177e2e4613277cb749dce9bac898259e129"},"schema_version":"1.0"},"canonical_sha256":"3d9464fe4cc8548e464df70f34d80526a0ae630b90a2a55883131b676d750d00","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:48.130242Z","signature_b64":"kbnOW6pf2MUW/zNekW6hUFktnm0rdLCaRnijJoG0OQEEG62JuNc5ZlkIm9hSZ9vpa/Q95QeOF3wkGfMUxK0tBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d9464fe4cc8548e464df70f34d80526a0ae630b90a2a55883131b676d750d00","last_reissued_at":"2026-07-05T11:02:48.129802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:48.129802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.08971","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":"2026-07-05T11:02:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6olLMa+cqFwXmo5nPXrgXxIJVmiOXCMyLSaIEK35zj+JptidhgjCHZTKcyQ20TlK5dRbF409bq33mclWw5C4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:42:33.693466Z"},"content_sha256":"b041e906c5ca5ea2b154a1f28c14ad6fc4abaadb91b48faf99a4cc1619738b08","schema_version":"1.0","event_id":"sha256:b041e906c5ca5ea2b154a1f28c14ad6fc4abaadb91b48faf99a4cc1619738b08"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HWKGJ7SMZBKI4RSN64HTJWAFE2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prioritizing Image-Related Tokens Enhances Vision-Language Pre-Training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Peng, Heng Ji, Tong Zhang, Yangyi Chen","submitted_at":"2025-05-13T21:27:52Z","abstract_excerpt":"In standard large vision-language models (LVLMs) pre-training, the model typically maximizes the joint probability of the caption conditioned on the image via next-token prediction (NTP); however, since only a small subset of caption tokens directly relates to the visual content, this naive NTP unintentionally fits the model to noise and increases the risk of hallucination. We present PRIOR, a simple vision-language pre-training approach that addresses this issue by prioritizing image-related tokens through differential weighting in the NTP loss, drawing from the importance sampling framework."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08971","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/2505.08971/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":"2026-07-05T11:02:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m9t5lQE03SfyeVHA2Oe366SmPHq5wn7f9zb/yTN0tYO+hMEA9LMg46ipTAHYMZUqF0n8VUf6X4PEXtIHN0RpBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:42:33.693957Z"},"content_sha256":"1e8b8a8f630263b53a89ce6a9eb35104186fe95f555cb8d871faba69e96aa0e1","schema_version":"1.0","event_id":"sha256:1e8b8a8f630263b53a89ce6a9eb35104186fe95f555cb8d871faba69e96aa0e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HWKGJ7SMZBKI4RSN64HTJWAFE2/bundle.json","state_url":"https://pith.science/pith/HWKGJ7SMZBKI4RSN64HTJWAFE2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HWKGJ7SMZBKI4RSN64HTJWAFE2/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":"2026-08-16T22:42:33Z","links":{"resolver":"https://pith.science/pith/HWKGJ7SMZBKI4RSN64HTJWAFE2","bundle":"https://pith.science/pith/HWKGJ7SMZBKI4RSN64HTJWAFE2/bundle.json","state":"https://pith.science/pith/HWKGJ7SMZBKI4RSN64HTJWAFE2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HWKGJ7SMZBKI4RSN64HTJWAFE2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HWKGJ7SMZBKI4RSN64HTJWAFE2","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":"bf6d20e31cea3518a011a66927b53177e2e4613277cb749dce9bac898259e129","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-13T21:27:52Z","title_canon_sha256":"b224f882801ce7020111049adadfd80e49372b2c8635a66989ef13a77a27e25f"},"schema_version":"1.0","source":{"id":"2505.08971","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08971","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08971v1","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08971","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"pith_short_12","alias_value":"HWKGJ7SMZBKI","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"pith_short_16","alias_value":"HWKGJ7SMZBKI4RSN","created_at":"2026-07-05T11:02:48Z"},{"alias_kind":"pith_short_8","alias_value":"HWKGJ7SM","created_at":"2026-07-05T11:02:48Z"}],"graph_snapshots":[{"event_id":"sha256:1e8b8a8f630263b53a89ce6a9eb35104186fe95f555cb8d871faba69e96aa0e1","target":"graph","created_at":"2026-07-05T11:02:48Z","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/2505.08971/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In standard large vision-language models (LVLMs) pre-training, the model typically maximizes the joint probability of the caption conditioned on the image via next-token prediction (NTP); however, since only a small subset of caption tokens directly relates to the visual content, this naive NTP unintentionally fits the model to noise and increases the risk of hallucination. We present PRIOR, a simple vision-language pre-training approach that addresses this issue by prioritizing image-related tokens through differential weighting in the NTP loss, drawing from the importance sampling framework.","authors_text":"Hao Peng, Heng Ji, Tong Zhang, Yangyi Chen","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-13T21:27:52Z","title":"Prioritizing Image-Related Tokens Enhances Vision-Language Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08971","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:b041e906c5ca5ea2b154a1f28c14ad6fc4abaadb91b48faf99a4cc1619738b08","target":"record","created_at":"2026-07-05T11:02:48Z","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":"bf6d20e31cea3518a011a66927b53177e2e4613277cb749dce9bac898259e129","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-13T21:27:52Z","title_canon_sha256":"b224f882801ce7020111049adadfd80e49372b2c8635a66989ef13a77a27e25f"},"schema_version":"1.0","source":{"id":"2505.08971","kind":"arxiv","version":1}},"canonical_sha256":"3d9464fe4cc8548e464df70f34d80526a0ae630b90a2a55883131b676d750d00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d9464fe4cc8548e464df70f34d80526a0ae630b90a2a55883131b676d750d00","first_computed_at":"2026-07-05T11:02:48.129802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:48.129802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kbnOW6pf2MUW/zNekW6hUFktnm0rdLCaRnijJoG0OQEEG62JuNc5ZlkIm9hSZ9vpa/Q95QeOF3wkGfMUxK0tBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:48.130242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.08971","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b041e906c5ca5ea2b154a1f28c14ad6fc4abaadb91b48faf99a4cc1619738b08","sha256:1e8b8a8f630263b53a89ce6a9eb35104186fe95f555cb8d871faba69e96aa0e1"],"state_sha256":"b312b4b07c2a59f9378396279e01cc21f4e24c0c7312f6d760a894f0db653b9e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JODp0FNRjtOOvgtExTblvh57FmMOd6SZHDynTjnbL51b+Fl9TWXP91cLN14VSymheaO6/PYVbeqaWb5CxzFhDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T22:42:33.697322Z","bundle_sha256":"0706c8d1c77c623066d06b765bfa8d40313dd4198420b2ecb2c391a24dfda57a"}}