{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:G5FHCQ3UBJFQDXUT2OXA6Z42XW","short_pith_number":"pith:G5FHCQ3U","canonical_record":{"source":{"id":"2506.18034","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T13:34:00Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"0a2ce1902a37ac0778f35c83e6c311e4b85ba61934b9be81bc5ec99c4f49355a","abstract_canon_sha256":"17ec4b339ea4b5be749dde5c2c1ecf87d5b4809a9a0acb28711564d60d6a1f25"},"schema_version":"1.0"},"canonical_sha256":"374a7143740a4b01de93d3ae0f679abda17cdb9ef6fddbcf08b33a389d6dcf4d","source":{"kind":"arxiv","id":"2506.18034","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18034","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18034v1","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18034","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"pith_short_12","alias_value":"G5FHCQ3UBJFQ","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"pith_short_16","alias_value":"G5FHCQ3UBJFQDXUT","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"pith_short_8","alias_value":"G5FHCQ3U","created_at":"2026-07-05T11:25:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:G5FHCQ3UBJFQDXUT2OXA6Z42XW","target":"record","payload":{"canonical_record":{"source":{"id":"2506.18034","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T13:34:00Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"0a2ce1902a37ac0778f35c83e6c311e4b85ba61934b9be81bc5ec99c4f49355a","abstract_canon_sha256":"17ec4b339ea4b5be749dde5c2c1ecf87d5b4809a9a0acb28711564d60d6a1f25"},"schema_version":"1.0"},"canonical_sha256":"374a7143740a4b01de93d3ae0f679abda17cdb9ef6fddbcf08b33a389d6dcf4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:27.436191Z","signature_b64":"DHAnwTwDWS4fZvhcWyQG44l4xe7PwymPA50DeH+StMajJbBvl770SPzS8TjG0dcDlx+kxIos/K4JAL09HBrODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"374a7143740a4b01de93d3ae0f679abda17cdb9ef6fddbcf08b33a389d6dcf4d","last_reissued_at":"2026-07-05T11:25:27.435680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:27.435680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.18034","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":"2026-07-05T11:25:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FIMz9B0t+TsDR9kO9Z7ayrRbv8V5q4bIPbDMsod06neuuXUUjv31wsVuyGIE5kr51hcovj+p/Iu5WiAJjpOKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:16:04.318320Z"},"content_sha256":"6732a7d9ad7c3858c8a08e77af2ce77c32be20d71fa1a4de58ca7a5bb3eaa1ba","schema_version":"1.0","event_id":"sha256:6732a7d9ad7c3858c8a08e77af2ce77c32be20d71fa1a4de58ca7a5bb3eaa1ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:G5FHCQ3UBJFQDXUT2OXA6Z42XW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pre-Trained LLM is a Semantic-Aware and Generalizable Segmentation Booster","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Fenghe Tang, S. Kevin Zhou, Wenxin Ma, Xiaodong Tao, Zhiyang He, Zihang Jiang","submitted_at":"2025-06-22T13:34:00Z","abstract_excerpt":"With the advancement of Large Language Model (LLM) for natural language processing, this paper presents an intriguing finding: a frozen pre-trained LLM layer can process visual tokens for medical image segmentation tasks. Specifically, we propose a simple hybrid structure that integrates a pre-trained, frozen LLM layer within the CNN encoder-decoder segmentation framework (LLM4Seg). Surprisingly, this design improves segmentation performance with a minimal increase in trainable parameters across various modalities, including ultrasound, dermoscopy, polypscopy, and CT scans. Our in-depth analys"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18034","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/2506.18034/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":"2026-07-05T11:25:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oUjHO1vdD+6/Ry2nGRq0i02Wu8lV4NuPVE0gR3pQKqaOp14PcT1dwOX7+JaYb1vjiy65DWpgim30Ah9whgFgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:16:04.319224Z"},"content_sha256":"c093d9eecfad26089d08a345251fc6cc016904a48abb4491948575673749ee0d","schema_version":"1.0","event_id":"sha256:c093d9eecfad26089d08a345251fc6cc016904a48abb4491948575673749ee0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G5FHCQ3UBJFQDXUT2OXA6Z42XW/bundle.json","state_url":"https://pith.science/pith/G5FHCQ3UBJFQDXUT2OXA6Z42XW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G5FHCQ3UBJFQDXUT2OXA6Z42XW/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":"2026-08-08T01:16:04Z","links":{"resolver":"https://pith.science/pith/G5FHCQ3UBJFQDXUT2OXA6Z42XW","bundle":"https://pith.science/pith/G5FHCQ3UBJFQDXUT2OXA6Z42XW/bundle.json","state":"https://pith.science/pith/G5FHCQ3UBJFQDXUT2OXA6Z42XW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G5FHCQ3UBJFQDXUT2OXA6Z42XW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G5FHCQ3UBJFQDXUT2OXA6Z42XW","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":"17ec4b339ea4b5be749dde5c2c1ecf87d5b4809a9a0acb28711564d60d6a1f25","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T13:34:00Z","title_canon_sha256":"0a2ce1902a37ac0778f35c83e6c311e4b85ba61934b9be81bc5ec99c4f49355a"},"schema_version":"1.0","source":{"id":"2506.18034","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18034","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18034v1","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18034","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"pith_short_12","alias_value":"G5FHCQ3UBJFQ","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"pith_short_16","alias_value":"G5FHCQ3UBJFQDXUT","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"pith_short_8","alias_value":"G5FHCQ3U","created_at":"2026-07-05T11:25:27Z"}],"graph_snapshots":[{"event_id":"sha256:c093d9eecfad26089d08a345251fc6cc016904a48abb4491948575673749ee0d","target":"graph","created_at":"2026-07-05T11:25:27Z","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/2506.18034/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the advancement of Large Language Model (LLM) for natural language processing, this paper presents an intriguing finding: a frozen pre-trained LLM layer can process visual tokens for medical image segmentation tasks. Specifically, we propose a simple hybrid structure that integrates a pre-trained, frozen LLM layer within the CNN encoder-decoder segmentation framework (LLM4Seg). Surprisingly, this design improves segmentation performance with a minimal increase in trainable parameters across various modalities, including ultrasound, dermoscopy, polypscopy, and CT scans. Our in-depth analys","authors_text":"Fenghe Tang, S. Kevin Zhou, Wenxin Ma, Xiaodong Tao, Zhiyang He, Zihang Jiang","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T13:34:00Z","title":"Pre-Trained LLM is a Semantic-Aware and Generalizable Segmentation Booster"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18034","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":"sha256:6732a7d9ad7c3858c8a08e77af2ce77c32be20d71fa1a4de58ca7a5bb3eaa1ba","target":"record","created_at":"2026-07-05T11:25:27Z","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":"17ec4b339ea4b5be749dde5c2c1ecf87d5b4809a9a0acb28711564d60d6a1f25","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T13:34:00Z","title_canon_sha256":"0a2ce1902a37ac0778f35c83e6c311e4b85ba61934b9be81bc5ec99c4f49355a"},"schema_version":"1.0","source":{"id":"2506.18034","kind":"arxiv","version":1}},"canonical_sha256":"374a7143740a4b01de93d3ae0f679abda17cdb9ef6fddbcf08b33a389d6dcf4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"374a7143740a4b01de93d3ae0f679abda17cdb9ef6fddbcf08b33a389d6dcf4d","first_computed_at":"2026-07-05T11:25:27.435680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:27.435680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DHAnwTwDWS4fZvhcWyQG44l4xe7PwymPA50DeH+StMajJbBvl770SPzS8TjG0dcDlx+kxIos/K4JAL09HBrODQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:27.436191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.18034","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6732a7d9ad7c3858c8a08e77af2ce77c32be20d71fa1a4de58ca7a5bb3eaa1ba","sha256:c093d9eecfad26089d08a345251fc6cc016904a48abb4491948575673749ee0d"],"state_sha256":"b2d1136425a3d2ceacf97ba0e8ab223b3d1fa5c40ba89d0fc56a1c364336430d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5P1QKmJdMdTEIo8dqqt/IC0Jf1+mdfUkQQi6l1eXk1ebNA9vn+Vht5CgETD5UfUE5YjYmN3TIcMyOJi8lonWDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:16:04.325025Z","bundle_sha256":"0a4eadf801e013fb2d18bd7750eeeb44c434713f9ca60f7c74c2ba176e58ad51"}}