{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:I3UAGCDNDCYEDAWL4GHLX7VPUL","short_pith_number":"pith:I3UAGCDN","canonical_record":{"source":{"id":"2505.19242","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T17:42:53Z","cross_cats_sorted":[],"title_canon_sha256":"6c837f9abd714ab4a9a60ebf94babcd087fce087ea9015143364705f15f48957","abstract_canon_sha256":"969936b19b4234e0bef30ca7061dbd3abdc6ec7c6cef763cf4018dcd8353264a"},"schema_version":"1.0"},"canonical_sha256":"46e803086d18b04182cbe18ebbfeafa2ea12a9203bc9e812e1783c1fb421a7ae","source":{"kind":"arxiv","id":"2505.19242","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19242","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19242v1","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19242","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"pith_short_12","alias_value":"I3UAGCDNDCYE","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"pith_short_16","alias_value":"I3UAGCDNDCYEDAWL","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"pith_short_8","alias_value":"I3UAGCDN","created_at":"2026-07-05T11:09:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:I3UAGCDNDCYEDAWL4GHLX7VPUL","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19242","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T17:42:53Z","cross_cats_sorted":[],"title_canon_sha256":"6c837f9abd714ab4a9a60ebf94babcd087fce087ea9015143364705f15f48957","abstract_canon_sha256":"969936b19b4234e0bef30ca7061dbd3abdc6ec7c6cef763cf4018dcd8353264a"},"schema_version":"1.0"},"canonical_sha256":"46e803086d18b04182cbe18ebbfeafa2ea12a9203bc9e812e1783c1fb421a7ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:26.989978Z","signature_b64":"evMlN+XGAXInjcvXpp7QeWfpi4+StnTfUIDFDCU/7heoZnyVO2N0za0d4ogPvaLaoDeBcfnpUOVcwIdG9a7LDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46e803086d18b04182cbe18ebbfeafa2ea12a9203bc9e812e1783c1fb421a7ae","last_reissued_at":"2026-07-05T11:09:26.989480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:26.989480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19242","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":"2026-07-05T11:09:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3CSNRoRk5GYafw3hElV8g2dJQZ4KRtA8iJNhHLKYVUYoHnY/JEi0b+LZdtBwxusZFPLkDkhQA7yytCQ3EklkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:03:02.459235Z"},"content_sha256":"2ba22628bae5f670d1dd0d59ebd141e38149e134cbf3a562b8e6fca464803bea","schema_version":"1.0","event_id":"sha256:2ba22628bae5f670d1dd0d59ebd141e38149e134cbf3a562b8e6fca464803bea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:I3UAGCDNDCYEDAWL4GHLX7VPUL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deformable Attentive Visual Enhancement for Referring Segmentation Using Vision-Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alaa Dalaq, Muzammil Behzad","submitted_at":"2025-05-25T17:42:53Z","abstract_excerpt":"Image segmentation is a fundamental task in computer vision, aimed at partitioning an image into semantically meaningful regions. Referring image segmentation extends this task by using natural language expressions to localize specific objects, requiring effective integration of visual and linguistic information. In this work, we propose SegVLM, a vision-language model that incorporates architectural improvements to enhance segmentation accuracy and cross-modal alignment. The model integrates squeeze-and-excitation (SE) blocks for dynamic feature recalibration, deformable convolutions for geom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19242","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/2505.19242/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":"2026-07-05T11:09:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jjwhrw2AjVIEKTPTZ3K7SV+aerP5eBvTdLwz17rOecaExerJuprWsUkpO2M3H5G26DER21alRm/sk05XT5ZcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:03:02.460161Z"},"content_sha256":"a2a1c231f86349fbe92edef870cb7f03f88ed3dea8ba2cb326d546117112cdd6","schema_version":"1.0","event_id":"sha256:a2a1c231f86349fbe92edef870cb7f03f88ed3dea8ba2cb326d546117112cdd6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I3UAGCDNDCYEDAWL4GHLX7VPUL/bundle.json","state_url":"https://pith.science/pith/I3UAGCDNDCYEDAWL4GHLX7VPUL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I3UAGCDNDCYEDAWL4GHLX7VPUL/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":"2026-08-10T13:03:02Z","links":{"resolver":"https://pith.science/pith/I3UAGCDNDCYEDAWL4GHLX7VPUL","bundle":"https://pith.science/pith/I3UAGCDNDCYEDAWL4GHLX7VPUL/bundle.json","state":"https://pith.science/pith/I3UAGCDNDCYEDAWL4GHLX7VPUL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I3UAGCDNDCYEDAWL4GHLX7VPUL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I3UAGCDNDCYEDAWL4GHLX7VPUL","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":"969936b19b4234e0bef30ca7061dbd3abdc6ec7c6cef763cf4018dcd8353264a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T17:42:53Z","title_canon_sha256":"6c837f9abd714ab4a9a60ebf94babcd087fce087ea9015143364705f15f48957"},"schema_version":"1.0","source":{"id":"2505.19242","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19242","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19242v1","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19242","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"pith_short_12","alias_value":"I3UAGCDNDCYE","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"pith_short_16","alias_value":"I3UAGCDNDCYEDAWL","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"pith_short_8","alias_value":"I3UAGCDN","created_at":"2026-07-05T11:09:26Z"}],"graph_snapshots":[{"event_id":"sha256:a2a1c231f86349fbe92edef870cb7f03f88ed3dea8ba2cb326d546117112cdd6","target":"graph","created_at":"2026-07-05T11:09:26Z","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/2505.19242/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image segmentation is a fundamental task in computer vision, aimed at partitioning an image into semantically meaningful regions. Referring image segmentation extends this task by using natural language expressions to localize specific objects, requiring effective integration of visual and linguistic information. In this work, we propose SegVLM, a vision-language model that incorporates architectural improvements to enhance segmentation accuracy and cross-modal alignment. The model integrates squeeze-and-excitation (SE) blocks for dynamic feature recalibration, deformable convolutions for geom","authors_text":"Alaa Dalaq, Muzammil Behzad","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T17:42:53Z","title":"Deformable Attentive Visual Enhancement for Referring Segmentation Using Vision-Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19242","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":"sha256:2ba22628bae5f670d1dd0d59ebd141e38149e134cbf3a562b8e6fca464803bea","target":"record","created_at":"2026-07-05T11:09:26Z","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":"969936b19b4234e0bef30ca7061dbd3abdc6ec7c6cef763cf4018dcd8353264a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-25T17:42:53Z","title_canon_sha256":"6c837f9abd714ab4a9a60ebf94babcd087fce087ea9015143364705f15f48957"},"schema_version":"1.0","source":{"id":"2505.19242","kind":"arxiv","version":1}},"canonical_sha256":"46e803086d18b04182cbe18ebbfeafa2ea12a9203bc9e812e1783c1fb421a7ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46e803086d18b04182cbe18ebbfeafa2ea12a9203bc9e812e1783c1fb421a7ae","first_computed_at":"2026-07-05T11:09:26.989480Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:26.989480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"evMlN+XGAXInjcvXpp7QeWfpi4+StnTfUIDFDCU/7heoZnyVO2N0za0d4ogPvaLaoDeBcfnpUOVcwIdG9a7LDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:26.989978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19242","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ba22628bae5f670d1dd0d59ebd141e38149e134cbf3a562b8e6fca464803bea","sha256:a2a1c231f86349fbe92edef870cb7f03f88ed3dea8ba2cb326d546117112cdd6"],"state_sha256":"4f6055058fef2fd7ea7bd293fcb4c1a87a67dd17ad2cf4b868a7add965eb374b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yAOw3LIOK/XD6UhEfeGEt/M22kRc7fizFxzvNb/T/2nvbPqt7/YJLkRPf6oLUEjbPHsc236AYK+3squg4+IhBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T13:03:02.485052Z","bundle_sha256":"aa604997083fb979f0797a208fb9ad474cf00c53ca61bcc8b1c2a193bd85432b"}}