{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6ZP3TVDWRQV4QZXEYWJWOAAIPZ","short_pith_number":"pith:6ZP3TVDW","canonical_record":{"source":{"id":"2606.23763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T14:14:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b667652aa4ef71bdfefdce86333e6e01a22b131856050c565c1bc7a1f5d685ba","abstract_canon_sha256":"55b2da0b6d362227d1099dc751937631889658ddf6d1999d52e25b30625dc830"},"schema_version":"1.0"},"canonical_sha256":"f65fb9d4768c2bc866e4c5936700087e5ed0777d18d61ef261d877e1339f86d0","source":{"kind":"arxiv","id":"2606.23763","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23763","created_at":"2026-06-24T00:14:25Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23763v1","created_at":"2026-06-24T00:14:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23763","created_at":"2026-06-24T00:14:25Z"},{"alias_kind":"pith_short_12","alias_value":"6ZP3TVDWRQV4","created_at":"2026-06-24T00:14:25Z"},{"alias_kind":"pith_short_16","alias_value":"6ZP3TVDWRQV4QZXE","created_at":"2026-06-24T00:14:25Z"},{"alias_kind":"pith_short_8","alias_value":"6ZP3TVDW","created_at":"2026-06-24T00:14:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6ZP3TVDWRQV4QZXEYWJWOAAIPZ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.23763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T14:14:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b667652aa4ef71bdfefdce86333e6e01a22b131856050c565c1bc7a1f5d685ba","abstract_canon_sha256":"55b2da0b6d362227d1099dc751937631889658ddf6d1999d52e25b30625dc830"},"schema_version":"1.0"},"canonical_sha256":"f65fb9d4768c2bc866e4c5936700087e5ed0777d18d61ef261d877e1339f86d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T00:14:25.345651Z","signature_b64":"3YIRfBMTxvBvC/OhKOy0nVcFa5Yn/3lIUbSRxTyTEnOYcDpW0pHBUVOht6ZrK2BrojCklfVDqqWHS79G/5ofCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f65fb9d4768c2bc866e4c5936700087e5ed0777d18d61ef261d877e1339f86d0","last_reissued_at":"2026-06-24T00:14:25.345216Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T00:14:25.345216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.23763","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":"2026-06-24T00:14:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z31QlidUwTdYmnMTBanUnycEH9N5rTFE1k7bn0mOfRKzA6wfS251isPFJ8A6+odxpZKBMuFnfX5mDqroWhucCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T11:07:11.072972Z"},"content_sha256":"5628ee261f5a9c21bd1d77b5c936575766340d693820d4c49d6334e138b68425","schema_version":"1.0","event_id":"sha256:5628ee261f5a9c21bd1d77b5c936575766340d693820d4c49d6334e138b68425"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6ZP3TVDWRQV4QZXEYWJWOAAIPZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Listening makes Vision Clear for VLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Binrui Shen, Yixin Tan, Yiyang Chen","submitted_at":"2026-06-22T14:14:46Z","abstract_excerpt":"Recent work typically assesses vision--language consistency using attention distributions of answer-side tokens. However, we observe that highest attention regions are not always consistent with the intended semantic token. This probably stems from decoding drift, where language priors from previously generated answer tokens accumulate and mismatch with visual attention. Besides the priors from previous answer tokens, we find that structural tokens, e.g., modality boundary markers, may encompass the entire context and generate high attention to areas unrelated to the target. To avoid these dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23763","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/2606.23763/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":"2026-06-24T00:14:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cyEyGktuC3BAhK5ykiREQMkC6/+1n0IaQRLsYxuxxivKR3lOHcQcRyLVfkIegKByeo22kHjr4nxQ6+ymFlctDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T11:07:11.073341Z"},"content_sha256":"806421047dd95d4e80a3292f5bc30ae0236b67de9ddc8bed6d9fadc28f59e848","schema_version":"1.0","event_id":"sha256:806421047dd95d4e80a3292f5bc30ae0236b67de9ddc8bed6d9fadc28f59e848"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6ZP3TVDWRQV4QZXEYWJWOAAIPZ/bundle.json","state_url":"https://pith.science/pith/6ZP3TVDWRQV4QZXEYWJWOAAIPZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6ZP3TVDWRQV4QZXEYWJWOAAIPZ/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":"2026-06-27T11:07:11Z","links":{"resolver":"https://pith.science/pith/6ZP3TVDWRQV4QZXEYWJWOAAIPZ","bundle":"https://pith.science/pith/6ZP3TVDWRQV4QZXEYWJWOAAIPZ/bundle.json","state":"https://pith.science/pith/6ZP3TVDWRQV4QZXEYWJWOAAIPZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6ZP3TVDWRQV4QZXEYWJWOAAIPZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6ZP3TVDWRQV4QZXEYWJWOAAIPZ","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":"55b2da0b6d362227d1099dc751937631889658ddf6d1999d52e25b30625dc830","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T14:14:46Z","title_canon_sha256":"b667652aa4ef71bdfefdce86333e6e01a22b131856050c565c1bc7a1f5d685ba"},"schema_version":"1.0","source":{"id":"2606.23763","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23763","created_at":"2026-06-24T00:14:25Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23763v1","created_at":"2026-06-24T00:14:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23763","created_at":"2026-06-24T00:14:25Z"},{"alias_kind":"pith_short_12","alias_value":"6ZP3TVDWRQV4","created_at":"2026-06-24T00:14:25Z"},{"alias_kind":"pith_short_16","alias_value":"6ZP3TVDWRQV4QZXE","created_at":"2026-06-24T00:14:25Z"},{"alias_kind":"pith_short_8","alias_value":"6ZP3TVDW","created_at":"2026-06-24T00:14:25Z"}],"graph_snapshots":[{"event_id":"sha256:806421047dd95d4e80a3292f5bc30ae0236b67de9ddc8bed6d9fadc28f59e848","target":"graph","created_at":"2026-06-24T00:14:25Z","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/2606.23763/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work typically assesses vision--language consistency using attention distributions of answer-side tokens. However, we observe that highest attention regions are not always consistent with the intended semantic token. This probably stems from decoding drift, where language priors from previously generated answer tokens accumulate and mismatch with visual attention. Besides the priors from previous answer tokens, we find that structural tokens, e.g., modality boundary markers, may encompass the entire context and generate high attention to areas unrelated to the target. To avoid these dis","authors_text":"Binrui Shen, Yixin Tan, Yiyang Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T14:14:46Z","title":"Listening makes Vision Clear for VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23763","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":"sha256:5628ee261f5a9c21bd1d77b5c936575766340d693820d4c49d6334e138b68425","target":"record","created_at":"2026-06-24T00:14:25Z","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":"55b2da0b6d362227d1099dc751937631889658ddf6d1999d52e25b30625dc830","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T14:14:46Z","title_canon_sha256":"b667652aa4ef71bdfefdce86333e6e01a22b131856050c565c1bc7a1f5d685ba"},"schema_version":"1.0","source":{"id":"2606.23763","kind":"arxiv","version":1}},"canonical_sha256":"f65fb9d4768c2bc866e4c5936700087e5ed0777d18d61ef261d877e1339f86d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f65fb9d4768c2bc866e4c5936700087e5ed0777d18d61ef261d877e1339f86d0","first_computed_at":"2026-06-24T00:14:25.345216Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T00:14:25.345216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3YIRfBMTxvBvC/OhKOy0nVcFa5Yn/3lIUbSRxTyTEnOYcDpW0pHBUVOht6ZrK2BrojCklfVDqqWHS79G/5ofCQ==","signature_status":"signed_v1","signed_at":"2026-06-24T00:14:25.345651Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23763","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5628ee261f5a9c21bd1d77b5c936575766340d693820d4c49d6334e138b68425","sha256:806421047dd95d4e80a3292f5bc30ae0236b67de9ddc8bed6d9fadc28f59e848"],"state_sha256":"b93015544883a9f4e6cfe69096dead8e7cff5fd385d89a08539878715ef7c315"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dCwInQGfcDKpZmyPR4w+vKm2d0QEIEuLhqQi70+9hHD3oif+aUhhnhG6CDq6ygf4KELrigjhYtp8n+X5XDPcAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T11:07:11.075177Z","bundle_sha256":"6fd343fad4f045046f1bca75fc051a9c16e3be8e03586ad9873ac5083e9a9f4a"}}