{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EWGQECJFSU2LF3OFUJSTQH4XPV","short_pith_number":"pith:EWGQECJF","canonical_record":{"source":{"id":"2505.18605","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T08:59:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"74231cfd4fa9085e29b704c8021ef9083104c70f13e71815f89be6a67fe02e01","abstract_canon_sha256":"2061799d9419cb5733c938ec79a723f37c60b76446750ded808ac65edc0174ba"},"schema_version":"1.0"},"canonical_sha256":"258d0209259534b2edc5a265381f977d4f9dc5a747812259f55f315dc2d7688b","source":{"kind":"arxiv","id":"2505.18605","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18605","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18605v1","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18605","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_12","alias_value":"EWGQECJFSU2L","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_16","alias_value":"EWGQECJFSU2LF3OF","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_8","alias_value":"EWGQECJF","created_at":"2026-07-05T11:09:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EWGQECJFSU2LF3OFUJSTQH4XPV","target":"record","payload":{"canonical_record":{"source":{"id":"2505.18605","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T08:59:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"74231cfd4fa9085e29b704c8021ef9083104c70f13e71815f89be6a67fe02e01","abstract_canon_sha256":"2061799d9419cb5733c938ec79a723f37c60b76446750ded808ac65edc0174ba"},"schema_version":"1.0"},"canonical_sha256":"258d0209259534b2edc5a265381f977d4f9dc5a747812259f55f315dc2d7688b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:16.337790Z","signature_b64":"neZqhrUahRfQV09tOAlHb3Yr7GS53lbOQ+Nu9JAaXGkTDoodXI33inVzs8F9z8cVhw1U+GHwx937GcW9kJTCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"258d0209259534b2edc5a265381f977d4f9dc5a747812259f55f315dc2d7688b","last_reissued_at":"2026-07-05T11:09:16.337193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:16.337193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.18605","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":"2026-07-05T11:09:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lrGOvAtppWkZ74G4o+ew1yYzAgvxk4X18P8Lv2knP7T6pAFGb5ZCEjQk8TFAHNm1h+K7d7v1+3mNDS5HHwqRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:13:42.365202Z"},"content_sha256":"2fea6166f08b04b97abc0e4e382d47af5c95c155afd6e4ddc934f72f502576d0","schema_version":"1.0","event_id":"sha256:2fea6166f08b04b97abc0e4e382d47af5c95c155afd6e4ddc934f72f502576d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EWGQECJFSU2LF3OFUJSTQH4XPV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking Causal Mask Attention for Vision-Language Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chang Xu, Tao Huang, Xiaohuan Pei, Yanxiang Ma","submitted_at":"2025-05-24T08:59:28Z","abstract_excerpt":"Causal attention has become a foundational mechanism in autoregressive vision-language models (VLMs), unifying textual and visual inputs under a single generative framework. However, existing causal mask-based strategies are inherited from large language models (LLMs) where they are tailored for text-only decoding, and their adaptation to vision tokens is insufficiently addressed in the prefill stage. Strictly masking future positions for vision queries introduces overly rigid constraints, which hinder the model's ability to leverage future context that often contains essential semantic cues f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18605","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/2505.18605/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":"2026-07-05T11:09:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SH7kKvsZ4UU+WCIyipwiuooy9yROxbi2PSbnKI0W61Pg/nIyU2pJCBh2NBuDoFPTADOwuWEPYmbM44E+nT+kCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:13:42.365600Z"},"content_sha256":"8bcfa3759dbb73be76351cb37dce025928a52beac950272acd8424762deb0116","schema_version":"1.0","event_id":"sha256:8bcfa3759dbb73be76351cb37dce025928a52beac950272acd8424762deb0116"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EWGQECJFSU2LF3OFUJSTQH4XPV/bundle.json","state_url":"https://pith.science/pith/EWGQECJFSU2LF3OFUJSTQH4XPV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EWGQECJFSU2LF3OFUJSTQH4XPV/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":"2026-07-07T07:13:42Z","links":{"resolver":"https://pith.science/pith/EWGQECJFSU2LF3OFUJSTQH4XPV","bundle":"https://pith.science/pith/EWGQECJFSU2LF3OFUJSTQH4XPV/bundle.json","state":"https://pith.science/pith/EWGQECJFSU2LF3OFUJSTQH4XPV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EWGQECJFSU2LF3OFUJSTQH4XPV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EWGQECJFSU2LF3OFUJSTQH4XPV","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":"2061799d9419cb5733c938ec79a723f37c60b76446750ded808ac65edc0174ba","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T08:59:28Z","title_canon_sha256":"74231cfd4fa9085e29b704c8021ef9083104c70f13e71815f89be6a67fe02e01"},"schema_version":"1.0","source":{"id":"2505.18605","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18605","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18605v1","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18605","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_12","alias_value":"EWGQECJFSU2L","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_16","alias_value":"EWGQECJFSU2LF3OF","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_8","alias_value":"EWGQECJF","created_at":"2026-07-05T11:09:16Z"}],"graph_snapshots":[{"event_id":"sha256:8bcfa3759dbb73be76351cb37dce025928a52beac950272acd8424762deb0116","target":"graph","created_at":"2026-07-05T11:09:16Z","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/2505.18605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Causal attention has become a foundational mechanism in autoregressive vision-language models (VLMs), unifying textual and visual inputs under a single generative framework. However, existing causal mask-based strategies are inherited from large language models (LLMs) where they are tailored for text-only decoding, and their adaptation to vision tokens is insufficiently addressed in the prefill stage. Strictly masking future positions for vision queries introduces overly rigid constraints, which hinder the model's ability to leverage future context that often contains essential semantic cues f","authors_text":"Chang Xu, Tao Huang, Xiaohuan Pei, Yanxiang Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T08:59:28Z","title":"Rethinking Causal Mask Attention for Vision-Language Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18605","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":"sha256:2fea6166f08b04b97abc0e4e382d47af5c95c155afd6e4ddc934f72f502576d0","target":"record","created_at":"2026-07-05T11:09:16Z","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":"2061799d9419cb5733c938ec79a723f37c60b76446750ded808ac65edc0174ba","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T08:59:28Z","title_canon_sha256":"74231cfd4fa9085e29b704c8021ef9083104c70f13e71815f89be6a67fe02e01"},"schema_version":"1.0","source":{"id":"2505.18605","kind":"arxiv","version":1}},"canonical_sha256":"258d0209259534b2edc5a265381f977d4f9dc5a747812259f55f315dc2d7688b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"258d0209259534b2edc5a265381f977d4f9dc5a747812259f55f315dc2d7688b","first_computed_at":"2026-07-05T11:09:16.337193Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:16.337193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"neZqhrUahRfQV09tOAlHb3Yr7GS53lbOQ+Nu9JAaXGkTDoodXI33inVzs8F9z8cVhw1U+GHwx937GcW9kJTCDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:16.337790Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18605","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fea6166f08b04b97abc0e4e382d47af5c95c155afd6e4ddc934f72f502576d0","sha256:8bcfa3759dbb73be76351cb37dce025928a52beac950272acd8424762deb0116"],"state_sha256":"d4a4922629ca749d0373a2b9ff34888bfe3eeb8b0de3a49cfe5d4b6cec586e5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e8AiBkA1s46ONl5EPSpbPigoGF8KkWbJtis2zUMVg1eB6nYABf6sxuhBrnIUniW1Cs3pp9RSellJMrJfZD5OCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:13:42.368011Z","bundle_sha256":"ad85ab51c6fd8c1a2b118da46a05097fa17e4b2e96c826528cb7ca2a88c37569"}}