{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2LOOK4WESOGES3NSKVB7BBOXP3","short_pith_number":"pith:2LOOK4WE","canonical_record":{"source":{"id":"2310.07394","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T11:26:35Z","cross_cats_sorted":[],"title_canon_sha256":"6a907a4fc3e1a523e8cb807061ea3e185692f15b96726b58f0b904efbae88e3c","abstract_canon_sha256":"4c37393f6078b955d04cafccf3c9e91e6ed7ccfb7ece1935b007442bc9c01ab7"},"schema_version":"1.0"},"canonical_sha256":"d2dce572c4938c496db25543f085d77ecb91233719fdced8bbe59ebf3d77eec8","source":{"kind":"arxiv","id":"2310.07394","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07394","created_at":"2026-07-05T06:59:45Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07394v1","created_at":"2026-07-05T06:59:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07394","created_at":"2026-07-05T06:59:45Z"},{"alias_kind":"pith_short_12","alias_value":"2LOOK4WESOGE","created_at":"2026-07-05T06:59:45Z"},{"alias_kind":"pith_short_16","alias_value":"2LOOK4WESOGES3NS","created_at":"2026-07-05T06:59:45Z"},{"alias_kind":"pith_short_8","alias_value":"2LOOK4WE","created_at":"2026-07-05T06:59:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2LOOK4WESOGES3NSKVB7BBOXP3","target":"record","payload":{"canonical_record":{"source":{"id":"2310.07394","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T11:26:35Z","cross_cats_sorted":[],"title_canon_sha256":"6a907a4fc3e1a523e8cb807061ea3e185692f15b96726b58f0b904efbae88e3c","abstract_canon_sha256":"4c37393f6078b955d04cafccf3c9e91e6ed7ccfb7ece1935b007442bc9c01ab7"},"schema_version":"1.0"},"canonical_sha256":"d2dce572c4938c496db25543f085d77ecb91233719fdced8bbe59ebf3d77eec8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:45.244491Z","signature_b64":"a6VrFNXtJO7/HjuA+1EQs+7RWYLz7W5kJg0CiKAHU0sEI/Kor+03uzMooMt+6qfJ1r3pH6m0Rpc6Bmh1gQcVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2dce572c4938c496db25543f085d77ecb91233719fdced8bbe59ebf3d77eec8","last_reissued_at":"2026-07-05T06:59:45.244117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:45.244117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.07394","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":"2026-07-05T06:59:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7J0ezQ4TiqYsbG16FIpR2tiwXt6YbrkSDyAAFZpTiXqjE7aYel8Wm4Kh2LeeBT3wXxXLMpNjj+UEVjAZvnGPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T07:02:25.537300Z"},"content_sha256":"24aa88b7eeea3b9cc652d383e2c4ca1b139d99c17bafe93553e5e382c791ca02","schema_version":"1.0","event_id":"sha256:24aa88b7eeea3b9cc652d383e2c4ca1b139d99c17bafe93553e5e382c791ca02"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2LOOK4WESOGES3NSKVB7BBOXP3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLIP for Lightweight Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ke Jin, Wankou Yang","submitted_at":"2023-10-11T11:26:35Z","abstract_excerpt":"The large-scale pretrained model CLIP, trained on 400 million image-text pairs, offers a promising paradigm for tackling vision tasks, albeit at the image level. Later works, such as DenseCLIP and LSeg, extend this paradigm to dense prediction, including semantic segmentation, and have achieved excellent results. However, the above methods either rely on CLIP-pretrained visual backbones or use none-pretrained but heavy backbones such as Swin, while falling ineffective when applied to lightweight backbones. The reason for this is that the lightweitht networks, feature extraction ability of whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07394","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/2310.07394/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":"2026-07-05T06:59:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"han1OZTh3/r7iF0n9tz2ZbgH+mPZuak+FKmDC4rL0IXBgv8MBkwMwjtmYaifeCLctswA5HhPYHkKzY60NieBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T07:02:25.537953Z"},"content_sha256":"1337e40b581da14729a947ac3bbff9f6cfd572ce628d5d712831e65b31e6e898","schema_version":"1.0","event_id":"sha256:1337e40b581da14729a947ac3bbff9f6cfd572ce628d5d712831e65b31e6e898"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2LOOK4WESOGES3NSKVB7BBOXP3/bundle.json","state_url":"https://pith.science/pith/2LOOK4WESOGES3NSKVB7BBOXP3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2LOOK4WESOGES3NSKVB7BBOXP3/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":"2026-07-09T07:02:25Z","links":{"resolver":"https://pith.science/pith/2LOOK4WESOGES3NSKVB7BBOXP3","bundle":"https://pith.science/pith/2LOOK4WESOGES3NSKVB7BBOXP3/bundle.json","state":"https://pith.science/pith/2LOOK4WESOGES3NSKVB7BBOXP3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2LOOK4WESOGES3NSKVB7BBOXP3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2LOOK4WESOGES3NSKVB7BBOXP3","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":"4c37393f6078b955d04cafccf3c9e91e6ed7ccfb7ece1935b007442bc9c01ab7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T11:26:35Z","title_canon_sha256":"6a907a4fc3e1a523e8cb807061ea3e185692f15b96726b58f0b904efbae88e3c"},"schema_version":"1.0","source":{"id":"2310.07394","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07394","created_at":"2026-07-05T06:59:45Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07394v1","created_at":"2026-07-05T06:59:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07394","created_at":"2026-07-05T06:59:45Z"},{"alias_kind":"pith_short_12","alias_value":"2LOOK4WESOGE","created_at":"2026-07-05T06:59:45Z"},{"alias_kind":"pith_short_16","alias_value":"2LOOK4WESOGES3NS","created_at":"2026-07-05T06:59:45Z"},{"alias_kind":"pith_short_8","alias_value":"2LOOK4WE","created_at":"2026-07-05T06:59:45Z"}],"graph_snapshots":[{"event_id":"sha256:1337e40b581da14729a947ac3bbff9f6cfd572ce628d5d712831e65b31e6e898","target":"graph","created_at":"2026-07-05T06:59:45Z","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/2310.07394/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The large-scale pretrained model CLIP, trained on 400 million image-text pairs, offers a promising paradigm for tackling vision tasks, albeit at the image level. Later works, such as DenseCLIP and LSeg, extend this paradigm to dense prediction, including semantic segmentation, and have achieved excellent results. However, the above methods either rely on CLIP-pretrained visual backbones or use none-pretrained but heavy backbones such as Swin, while falling ineffective when applied to lightweight backbones. The reason for this is that the lightweitht networks, feature extraction ability of whic","authors_text":"Ke Jin, Wankou Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T11:26:35Z","title":"CLIP for Lightweight Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07394","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":"sha256:24aa88b7eeea3b9cc652d383e2c4ca1b139d99c17bafe93553e5e382c791ca02","target":"record","created_at":"2026-07-05T06:59:45Z","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":"4c37393f6078b955d04cafccf3c9e91e6ed7ccfb7ece1935b007442bc9c01ab7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T11:26:35Z","title_canon_sha256":"6a907a4fc3e1a523e8cb807061ea3e185692f15b96726b58f0b904efbae88e3c"},"schema_version":"1.0","source":{"id":"2310.07394","kind":"arxiv","version":1}},"canonical_sha256":"d2dce572c4938c496db25543f085d77ecb91233719fdced8bbe59ebf3d77eec8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2dce572c4938c496db25543f085d77ecb91233719fdced8bbe59ebf3d77eec8","first_computed_at":"2026-07-05T06:59:45.244117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:45.244117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a6VrFNXtJO7/HjuA+1EQs+7RWYLz7W5kJg0CiKAHU0sEI/Kor+03uzMooMt+6qfJ1r3pH6m0Rpc6Bmh1gQcVDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:45.244491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07394","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24aa88b7eeea3b9cc652d383e2c4ca1b139d99c17bafe93553e5e382c791ca02","sha256:1337e40b581da14729a947ac3bbff9f6cfd572ce628d5d712831e65b31e6e898"],"state_sha256":"e23e2a5d89596147eafe00967e44afca75e70dae25aa9ebc56f683001a2914e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5GhCvPCHIwJpD0ClNftXuhi3MqeViUoVu3WxRdAlqPGTiQtUxWFU2XDoCcVYYaBbQsaT0DgMEOgCWoNvOIZsDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T07:02:25.542780Z","bundle_sha256":"c4e974e2a37ac4fe968bb05d653f0791ea59744444404fad866b9116cbc3631a"}}