{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CTO26GIKLZGENPLRHLGPH7273D","short_pith_number":"pith:CTO26GIK","canonical_record":{"source":{"id":"2408.07539","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T13:17:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8cbfdfd78f5d5afdee35b57ae0da813bb379f5d31253e50e20875cbca7faebb9","abstract_canon_sha256":"fe1df574292e5542ef7c8fdab355ba0be7fbb595ea90887de969696867558fae"},"schema_version":"1.0"},"canonical_sha256":"14ddaf190a5e4c46bd713accf3ff5fd8f59384cfa56e1f72894865d7fe1ec958","source":{"kind":"arxiv","id":"2408.07539","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07539","created_at":"2026-07-05T08:55:26Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07539v1","created_at":"2026-07-05T08:55:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07539","created_at":"2026-07-05T08:55:26Z"},{"alias_kind":"pith_short_12","alias_value":"CTO26GIKLZGE","created_at":"2026-07-05T08:55:26Z"},{"alias_kind":"pith_short_16","alias_value":"CTO26GIKLZGENPLR","created_at":"2026-07-05T08:55:26Z"},{"alias_kind":"pith_short_8","alias_value":"CTO26GIK","created_at":"2026-07-05T08:55:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CTO26GIKLZGENPLRHLGPH7273D","target":"record","payload":{"canonical_record":{"source":{"id":"2408.07539","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T13:17:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8cbfdfd78f5d5afdee35b57ae0da813bb379f5d31253e50e20875cbca7faebb9","abstract_canon_sha256":"fe1df574292e5542ef7c8fdab355ba0be7fbb595ea90887de969696867558fae"},"schema_version":"1.0"},"canonical_sha256":"14ddaf190a5e4c46bd713accf3ff5fd8f59384cfa56e1f72894865d7fe1ec958","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:26.684229Z","signature_b64":"1BBVaSQR6xu6zZKXR4l6iR0cvb82ZakZZBBmHhqyqv3fpY7zzK2WFDEedKzt+LCu5Gxj50mtneeZqJAAUlc9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14ddaf190a5e4c46bd713accf3ff5fd8f59384cfa56e1f72894865d7fe1ec958","last_reissued_at":"2026-07-05T08:55:26.683772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:26.683772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.07539","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":"2026-07-05T08:55:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bnEokSItnqAMEzJt3rBHp7iRQTNLMKLQ6B8mxPDIgl3PrKVi4AcJzZOhIDXFz+h5Y3HwwwYWJogkkO1Dm33HBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T04:10:41.670707Z"},"content_sha256":"c0648f42b65f653b1d64e235a7e059178338aad34232cbf64eddc4c546dbe2a8","schema_version":"1.0","event_id":"sha256:c0648f42b65f653b1d64e235a7e059178338aad34232cbf64eddc4c546dbe2a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CTO26GIKLZGENPLRHLGPH7273D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-aware Early Fusion with Stage-divided Vision and Language Transformer Encoders for Referring Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hyunwoo Yu, Suk-Ju Kang, Yubin Cho","submitted_at":"2024-08-14T13:17:41Z","abstract_excerpt":"Referring segmentation aims to segment a target object related to a natural language expression. Key challenges of this task are understanding the meaning of complex and ambiguous language expressions and determining the relevant regions in the image with multiple objects by referring to the expression. Recent models have focused on the early fusion with the language features at the intermediate stage of the vision encoder, but these approaches have a limitation that the language features cannot refer to the visual information. To address this issue, this paper proposes a novel architecture, C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07539","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/2408.07539/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":"2026-07-05T08:55:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W8jKWciirkgWk2p/N44BbT8tLiWs32cduWG1px+OGP3PfpMS+CHk7h9yBl7OVGxgSO0Uzv8ZsBoVgP/6gZJzCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T04:10:41.671098Z"},"content_sha256":"38b683f5940e1ab78001999dd120965c9c337035ab265ccd538f6f5c2f348d44","schema_version":"1.0","event_id":"sha256:38b683f5940e1ab78001999dd120965c9c337035ab265ccd538f6f5c2f348d44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CTO26GIKLZGENPLRHLGPH7273D/bundle.json","state_url":"https://pith.science/pith/CTO26GIKLZGENPLRHLGPH7273D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CTO26GIKLZGENPLRHLGPH7273D/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":"2026-07-21T04:10:41Z","links":{"resolver":"https://pith.science/pith/CTO26GIKLZGENPLRHLGPH7273D","bundle":"https://pith.science/pith/CTO26GIKLZGENPLRHLGPH7273D/bundle.json","state":"https://pith.science/pith/CTO26GIKLZGENPLRHLGPH7273D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CTO26GIKLZGENPLRHLGPH7273D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CTO26GIKLZGENPLRHLGPH7273D","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":"fe1df574292e5542ef7c8fdab355ba0be7fbb595ea90887de969696867558fae","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T13:17:41Z","title_canon_sha256":"8cbfdfd78f5d5afdee35b57ae0da813bb379f5d31253e50e20875cbca7faebb9"},"schema_version":"1.0","source":{"id":"2408.07539","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07539","created_at":"2026-07-05T08:55:26Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07539v1","created_at":"2026-07-05T08:55:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07539","created_at":"2026-07-05T08:55:26Z"},{"alias_kind":"pith_short_12","alias_value":"CTO26GIKLZGE","created_at":"2026-07-05T08:55:26Z"},{"alias_kind":"pith_short_16","alias_value":"CTO26GIKLZGENPLR","created_at":"2026-07-05T08:55:26Z"},{"alias_kind":"pith_short_8","alias_value":"CTO26GIK","created_at":"2026-07-05T08:55:26Z"}],"graph_snapshots":[{"event_id":"sha256:38b683f5940e1ab78001999dd120965c9c337035ab265ccd538f6f5c2f348d44","target":"graph","created_at":"2026-07-05T08:55:26Z","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/2408.07539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring segmentation aims to segment a target object related to a natural language expression. Key challenges of this task are understanding the meaning of complex and ambiguous language expressions and determining the relevant regions in the image with multiple objects by referring to the expression. Recent models have focused on the early fusion with the language features at the intermediate stage of the vision encoder, but these approaches have a limitation that the language features cannot refer to the visual information. To address this issue, this paper proposes a novel architecture, C","authors_text":"Hyunwoo Yu, Suk-Ju Kang, Yubin Cho","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T13:17:41Z","title":"Cross-aware Early Fusion with Stage-divided Vision and Language Transformer Encoders for Referring Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07539","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:c0648f42b65f653b1d64e235a7e059178338aad34232cbf64eddc4c546dbe2a8","target":"record","created_at":"2026-07-05T08:55:26Z","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":"fe1df574292e5542ef7c8fdab355ba0be7fbb595ea90887de969696867558fae","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T13:17:41Z","title_canon_sha256":"8cbfdfd78f5d5afdee35b57ae0da813bb379f5d31253e50e20875cbca7faebb9"},"schema_version":"1.0","source":{"id":"2408.07539","kind":"arxiv","version":1}},"canonical_sha256":"14ddaf190a5e4c46bd713accf3ff5fd8f59384cfa56e1f72894865d7fe1ec958","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14ddaf190a5e4c46bd713accf3ff5fd8f59384cfa56e1f72894865d7fe1ec958","first_computed_at":"2026-07-05T08:55:26.683772Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:26.683772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1BBVaSQR6xu6zZKXR4l6iR0cvb82ZakZZBBmHhqyqv3fpY7zzK2WFDEedKzt+LCu5Gxj50mtneeZqJAAUlc9CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:26.684229Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.07539","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0648f42b65f653b1d64e235a7e059178338aad34232cbf64eddc4c546dbe2a8","sha256:38b683f5940e1ab78001999dd120965c9c337035ab265ccd538f6f5c2f348d44"],"state_sha256":"dbdaa66613df9a712bed763c255ee29272e420dd927a82bb0162d2a2e7bccf87"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iMxtk4MsG+elfYN56Y4jTEUv8JZDuPU7C9+knK4hKOSzMmkkyn/kR8nVTBDeQtUpKLOqcolFNZchSwfwbkD/Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T04:10:41.673770Z","bundle_sha256":"42fc79e936707e95115c5466789c288e3598c69ecb454ad88494a4310cdca350"}}