{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NCNPVANIPFGXGYBOWGV3UMNQ77","short_pith_number":"pith:NCNPVANI","canonical_record":{"source":{"id":"2406.20076","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T17:38:18Z","cross_cats_sorted":[],"title_canon_sha256":"56348a571b65babcbe1957f954b0d13c548eb017ade6f3fd5c2dfb2248da9bd9","abstract_canon_sha256":"86548ec5924579c6c856b8ac17fe0f15f0018b0a964af1908fb8e912168fc283"},"schema_version":"1.0"},"canonical_sha256":"689afa81a8794d73602eb1abba31b0ffca0cf1e38bf388195ce69159f263d280","source":{"kind":"arxiv","id":"2406.20076","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.20076","created_at":"2026-07-05T10:27:11Z"},{"alias_kind":"arxiv_version","alias_value":"2406.20076v5","created_at":"2026-07-05T10:27:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.20076","created_at":"2026-07-05T10:27:11Z"},{"alias_kind":"pith_short_12","alias_value":"NCNPVANIPFGX","created_at":"2026-07-05T10:27:11Z"},{"alias_kind":"pith_short_16","alias_value":"NCNPVANIPFGXGYBO","created_at":"2026-07-05T10:27:11Z"},{"alias_kind":"pith_short_8","alias_value":"NCNPVANI","created_at":"2026-07-05T10:27:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NCNPVANIPFGXGYBOWGV3UMNQ77","target":"record","payload":{"canonical_record":{"source":{"id":"2406.20076","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T17:38:18Z","cross_cats_sorted":[],"title_canon_sha256":"56348a571b65babcbe1957f954b0d13c548eb017ade6f3fd5c2dfb2248da9bd9","abstract_canon_sha256":"86548ec5924579c6c856b8ac17fe0f15f0018b0a964af1908fb8e912168fc283"},"schema_version":"1.0"},"canonical_sha256":"689afa81a8794d73602eb1abba31b0ffca0cf1e38bf388195ce69159f263d280","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:11.865039Z","signature_b64":"eKvdc18iDje6E0qDYzu6synS4an2fFcDFNO65rAgVf6dt+nPXlrPLF/T/3CYUVZpcgf7KJMZ8CYPlJlUDlQkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"689afa81a8794d73602eb1abba31b0ffca0cf1e38bf388195ce69159f263d280","last_reissued_at":"2026-07-05T10:27:11.864519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:11.864519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.20076","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:27:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8obm528MxqzlWcCtN8BFOYpLOZVHB9q+lp1pNtqtI2PnhwqY30xk0JO+h9hC8qrihZmF90Z0A5jfWwgqzZ8iDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:57:57.304986Z"},"content_sha256":"80817a4cd3ba60355bd08b129b09398e80c11116ba07e02de93e0f45812b9661","schema_version":"1.0","event_id":"sha256:80817a4cd3ba60355bd08b129b09398e80c11116ba07e02de93e0f45812b9661"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NCNPVANIPFGXGYBOWGV3UMNQ77","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Liu, Lei Liu, Lianghui Zhu, Longjin Ran, Rui Hu, Tianheng Cheng, Wenyu Liu, Xiaoxin Chen, Xinggang Wang, Yuxuan Zhang","submitted_at":"2024-06-28T17:38:18Z","abstract_excerpt":"Segment Anything Model (SAM) has attracted widespread attention for its superior interactive segmentation capabilities with visual prompts while lacking further exploration of text prompts. In this paper, we empirically investigate what text prompt encoders (e.g., CLIP or LLM) are good for adapting SAM for referring expression segmentation and introduce the Early Vision-language Fusion-based SAM (EVF-SAM). EVF-SAM is a simple yet effective referring segmentation method which exploits multimodal prompts (i.e., image and text) and comprises a pre-trained vision-language model to generate referri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.20076","kind":"arxiv","version":5},"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/2406.20076/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":"2026-07-05T10:27:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EJE0os4fOz2x4NgnQXMgqIP4mqR0Hwg/hdd2GOyIrCPYc8FTQIz7XGLJ7xJ7yEj5lC3N6lvoEioMnD/qR8c1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:57:57.305888Z"},"content_sha256":"9053c65c7cf602f4addefa0f67860683048ddbf9d32f0d7c17466544cd238476","schema_version":"1.0","event_id":"sha256:9053c65c7cf602f4addefa0f67860683048ddbf9d32f0d7c17466544cd238476"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NCNPVANIPFGXGYBOWGV3UMNQ77/bundle.json","state_url":"https://pith.science/pith/NCNPVANIPFGXGYBOWGV3UMNQ77/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NCNPVANIPFGXGYBOWGV3UMNQ77/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":"2026-08-17T04:57:57Z","links":{"resolver":"https://pith.science/pith/NCNPVANIPFGXGYBOWGV3UMNQ77","bundle":"https://pith.science/pith/NCNPVANIPFGXGYBOWGV3UMNQ77/bundle.json","state":"https://pith.science/pith/NCNPVANIPFGXGYBOWGV3UMNQ77/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NCNPVANIPFGXGYBOWGV3UMNQ77/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NCNPVANIPFGXGYBOWGV3UMNQ77","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":"86548ec5924579c6c856b8ac17fe0f15f0018b0a964af1908fb8e912168fc283","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T17:38:18Z","title_canon_sha256":"56348a571b65babcbe1957f954b0d13c548eb017ade6f3fd5c2dfb2248da9bd9"},"schema_version":"1.0","source":{"id":"2406.20076","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.20076","created_at":"2026-07-05T10:27:11Z"},{"alias_kind":"arxiv_version","alias_value":"2406.20076v5","created_at":"2026-07-05T10:27:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.20076","created_at":"2026-07-05T10:27:11Z"},{"alias_kind":"pith_short_12","alias_value":"NCNPVANIPFGX","created_at":"2026-07-05T10:27:11Z"},{"alias_kind":"pith_short_16","alias_value":"NCNPVANIPFGXGYBO","created_at":"2026-07-05T10:27:11Z"},{"alias_kind":"pith_short_8","alias_value":"NCNPVANI","created_at":"2026-07-05T10:27:11Z"}],"graph_snapshots":[{"event_id":"sha256:9053c65c7cf602f4addefa0f67860683048ddbf9d32f0d7c17466544cd238476","target":"graph","created_at":"2026-07-05T10:27:11Z","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/2406.20076/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Segment Anything Model (SAM) has attracted widespread attention for its superior interactive segmentation capabilities with visual prompts while lacking further exploration of text prompts. In this paper, we empirically investigate what text prompt encoders (e.g., CLIP or LLM) are good for adapting SAM for referring expression segmentation and introduce the Early Vision-language Fusion-based SAM (EVF-SAM). EVF-SAM is a simple yet effective referring segmentation method which exploits multimodal prompts (i.e., image and text) and comprises a pre-trained vision-language model to generate referri","authors_text":"Heng Liu, Lei Liu, Lianghui Zhu, Longjin Ran, Rui Hu, Tianheng Cheng, Wenyu Liu, Xiaoxin Chen, Xinggang Wang, Yuxuan Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T17:38:18Z","title":"EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.20076","kind":"arxiv","version":5},"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":"sha256:80817a4cd3ba60355bd08b129b09398e80c11116ba07e02de93e0f45812b9661","target":"record","created_at":"2026-07-05T10:27:11Z","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":"86548ec5924579c6c856b8ac17fe0f15f0018b0a964af1908fb8e912168fc283","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T17:38:18Z","title_canon_sha256":"56348a571b65babcbe1957f954b0d13c548eb017ade6f3fd5c2dfb2248da9bd9"},"schema_version":"1.0","source":{"id":"2406.20076","kind":"arxiv","version":5}},"canonical_sha256":"689afa81a8794d73602eb1abba31b0ffca0cf1e38bf388195ce69159f263d280","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"689afa81a8794d73602eb1abba31b0ffca0cf1e38bf388195ce69159f263d280","first_computed_at":"2026-07-05T10:27:11.864519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:11.864519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eKvdc18iDje6E0qDYzu6synS4an2fFcDFNO65rAgVf6dt+nPXlrPLF/T/3CYUVZpcgf7KJMZ8CYPlJlUDlQkCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:11.865039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.20076","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80817a4cd3ba60355bd08b129b09398e80c11116ba07e02de93e0f45812b9661","sha256:9053c65c7cf602f4addefa0f67860683048ddbf9d32f0d7c17466544cd238476"],"state_sha256":"98457cd4dd5121558d07cfdfe7ffcf146d5f871753b7222c089ca136d0a70c03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7zD5XjeLjLuQGbKelX2MkK0QPYq0YM3h3f3vjJx/Mh0h1/+VxhT2bplWD1slbLWFjZCG4a1MFWQ6ebYyK9oUAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T04:57:57.312468Z","bundle_sha256":"2b1f75216c47f889199dec0ee423f41d271b4eec5f893a4be8e207c8e212e896"}}