{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PXDYEZ473GVATK3NVDIUORKIGJ","short_pith_number":"pith:PXDYEZ47","canonical_record":{"source":{"id":"2607.24567","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T15:35:52Z","cross_cats_sorted":["cs.CV","cs.IR"],"title_canon_sha256":"8bbf6d4895135cf60aed10c6dba97c9f43e94764d00bde438dbac32c8b6f7733","abstract_canon_sha256":"0678d3f8d7c555a9e80c91df823352d6052a9d93f136cb65c2c42434c40cfee9"},"schema_version":"1.0"},"canonical_sha256":"7dc782679fd9aa09ab6da8d147454832623b859df7660736b0802d73dc82a8ca","source":{"kind":"arxiv","id":"2607.24567","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24567","created_at":"2026-07-28T02:24:10Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24567v1","created_at":"2026-07-28T02:24:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24567","created_at":"2026-07-28T02:24:10Z"},{"alias_kind":"pith_short_12","alias_value":"PXDYEZ473GVA","created_at":"2026-07-28T02:24:10Z"},{"alias_kind":"pith_short_16","alias_value":"PXDYEZ473GVATK3N","created_at":"2026-07-28T02:24:10Z"},{"alias_kind":"pith_short_8","alias_value":"PXDYEZ47","created_at":"2026-07-28T02:24:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PXDYEZ473GVATK3NVDIUORKIGJ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.24567","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T15:35:52Z","cross_cats_sorted":["cs.CV","cs.IR"],"title_canon_sha256":"8bbf6d4895135cf60aed10c6dba97c9f43e94764d00bde438dbac32c8b6f7733","abstract_canon_sha256":"0678d3f8d7c555a9e80c91df823352d6052a9d93f136cb65c2c42434c40cfee9"},"schema_version":"1.0"},"canonical_sha256":"7dc782679fd9aa09ab6da8d147454832623b859df7660736b0802d73dc82a8ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:24:10.625405Z","signature_b64":"a9Td0iNw1q/poc50Q3hA/poc92u9vG+qZUjEw+qLExxJWEFPdxFEVNIKJsBYw8GBiXrPFGK1FNZ/iLOa268YBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dc782679fd9aa09ab6da8d147454832623b859df7660736b0802d73dc82a8ca","last_reissued_at":"2026-07-28T02:24:10.624589Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:24:10.624589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.24567","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":"2026-07-28T02:24:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Tq2K6//dkQw5/dZW2yXQGe8B8jfRqmv1izlXvIBOUQcyecctmIxwaEW+eIZXDMTFe724YHrz4mt68a8sg8TBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T21:47:22.077971Z"},"content_sha256":"a20c9c06ec3328d21d8efef529a62f250e892a55d93594e4401c9c987f998ccb","schema_version":"1.0","event_id":"sha256:a20c9c06ec3328d21d8efef529a62f250e892a55d93594e4401c9c987f998ccb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PXDYEZ473GVATK3NVDIUORKIGJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DSCH-Loss: A Dynamic Semantic Channel Objective for Deep Semantic Hashing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.IR"],"primary_cat":"cs.AI","authors_text":"Christian Bergler, Christian Riess, Daniel Loebenberger, Tobias J. Bauer","submitted_at":"2026-07-27T15:35:52Z","abstract_excerpt":"Semantic hashing methods for generating short binary hash codes that allow efficient approximate nearest neighbor search in high-dimensional data spaces have gained extensive consideration in recent years. Deep learning-based methods offer better semantic capturing capabilities than traditional approaches relying on manual feature engineering. Moreover, they enable a data-driven approach to semantic hashing across diverse data modalities, yielding high-quality cross-modal hash codes within a shared Hamming space. Previous work investigated the properties of this Hamming space and introduced a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24567","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/2607.24567/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":"2026-07-28T02:24:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"veJU4KfPnwcw7PlPsyEYOxh2UiskFRFKBiEukAUNALW+C2C88kbKgSJB9z45nU7or7pYX7uQBWwLHoE9pe0qDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T21:47:22.078538Z"},"content_sha256":"1ac809983735deeca645895468e7ea9fb8288e13fd58bad8db87e2623cc55c83","schema_version":"1.0","event_id":"sha256:1ac809983735deeca645895468e7ea9fb8288e13fd58bad8db87e2623cc55c83"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:PXDYEZ473GVATK3NVDIUORKIGJ","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1007/s13735-023-00268-7) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"L. Mingyong, L. Yewen, G. Mingyuan, and M. Longfei, “CLIP-based fusion-modal reconstructing hashing for large-scale unsupervised cross- modal retrieval,”International Journal of Multimedia Information Retrieval, vol. 12, no. 1, p. 2, Jun. 2","arxiv_id":"2607.24567","detector":"doi_compliance","evidence":{"ref_index":24,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1007/s13735-023-","reconstructed_doi":"10.1007/s13735-023-00268-7"},"severity":"advisory","ref_index":24,"audited_at":"2026-08-01T11:48:52.720389Z","event_type":"pith.integrity.v1","detected_doi":"10.1007/s13735-023-00268-7","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"48f3f4808aad0a58cb8453bf0d3cb8daaed79f1c820989221e8c894e9af07a05","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":15745,"payload_sha256":"2368c61069dc2de55b66255c805e4175921301140993ca2e03a4655dffe4a926","signature_b64":"UNyzVk+wmAZGS8nGiXjS8LvCUWnVBlQjQwOhWgjpHlhF0eF4T7IVFQVBgspH7gXE9BUMrQogQm918b5tsvw4Bw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-01T11:53:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3KVtq6RI32FZyvvZ2xyhyheAPnKewl5foDLhoy24jgUY332VeS5c3pWjwwEwVVTKr4K4sSY+NIOTsTcvxQ9YBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T21:47:22.082488Z"},"content_sha256":"94d58cab9457f3210c92455a8277ed6226be35b977c6e3e0d615165705e91d03","schema_version":"1.0","event_id":"sha256:94d58cab9457f3210c92455a8277ed6226be35b977c6e3e0d615165705e91d03"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:PXDYEZ473GVATK3NVDIUORKIGJ","target":"integrity","payload":{"note":"DOI is split by whitespace or line breaks in the printed bibliography. Reconstructed DOI 10.1007/s13735-023-00268-7 resolves to 'CLIP-based fusion-modal reconstructing hashing for large-scale unsupervised cross-modal retrieval'. A reader following the printed text alone cannot reach it.","snippet":"L. Mingyong, L. Yewen, G. Mingyuan, and M. Longfei, “CLIP-based fusion-modal reconstructing hashing for large-scale unsupervised cross- modal retrieval,”International Journal of Multimedia Information Retrieval, vol. 12, no. 1, p. 2, Jun. 2","arxiv_id":"2607.24567","detector":"doi_compliance","evidence":{"ref_index":24,"verdict_class":"incontrovertible","resolved_title":"CLIP-based fusion-modal reconstructing hashing for large-scale unsupervised cross-modal retrieval","printed_excerpt":"10.1007/s13735-023-","reconstructed_doi":"10.1007/s13735-023-00268-7"},"severity":"advisory","ref_index":24,"audited_at":"2026-07-31T11:42:27.733245Z","event_type":"pith.integrity.v1","detected_doi":"10.1007/s13735-023-00268-7","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"7ec2191df1b4afe506d8ac002b206f000f5405e39f96dea6408bf22efc3c934b","paper_version":1,"verdict_class":"incontrovertible","resolved_title":"CLIP-based fusion-modal reconstructing hashing for large-scale unsupervised cross-modal retrieval","detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":14350,"payload_sha256":"1c08fc01e011d9eb1cc5442298b70dc645c84b1c0908d606d863ce5f4a150266","signature_b64":null,"signing_key_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T11:46:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J9SlSuSBJeQMPBHVkFdfGJbYG5benOFoFoLiNcTPGT52LMrhqNBDO6tGkoR5TW/uTRlNOB6mxvC+m42+Z++/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T21:47:22.082895Z"},"content_sha256":"8742b0ccbb71d7c3abfc29020583673f321683f7c24ee33ca4ecf96f53d6098d","schema_version":"1.0","event_id":"sha256:8742b0ccbb71d7c3abfc29020583673f321683f7c24ee33ca4ecf96f53d6098d"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:PXDYEZ473GVATK3NVDIUORKIGJ","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/TCSVT.2024.3350695) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"J. Li, W. K. Wong, L. Jiang, X. Fang, S. Xie, and Y . Xu, “CKDH: CLIP- Based Knowledge Distillation Hashing for Cross-Modal Retrieval,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 34, no. 7, pp. 6530–6541, Jul. 2024","arxiv_id":"2607.24567","detector":"doi_compliance","evidence":{"ref_index":17,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1109/tcsvt.2024","reconstructed_doi":"10.1109/TCSVT.2024.3350695"},"severity":"advisory","ref_index":17,"audited_at":"2026-07-31T11:42:27.733245Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/TCSVT.2024.3350695","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"38d53228d48e4d49898e8b69457e918f794d8c3dc4be70e3e7222743ee066e6e","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":14349,"payload_sha256":"396e172bdeb8d9fcc64f43e18ad66712e8b38c8d8ebec5630f88c3b7146a5b2e","signature_b64":null,"signing_key_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T11:46:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2hJjrTKE0iVV5Ru3LpYWiB2l+3bzf9+oVbM9OdHKMndg+299UzQc7OeyKo6ihAXJn53KnV54Uk66UAVjv29SAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T21:47:22.083265Z"},"content_sha256":"d7b74bb176d7e145258973f5f6c5a630081a4d9ad234963f54f9501e5ec27223","schema_version":"1.0","event_id":"sha256:d7b74bb176d7e145258973f5f6c5a630081a4d9ad234963f54f9501e5ec27223"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:PXDYEZ473GVATK3NVDIUORKIGJ","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/ACCESS.2023.3339581) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"S. Zhou et al., “Transformer-Based Discriminative and Strong Rep- resentation Deep Hashing for Cross-Modal Retrieval,”IEEE Access, vol. 11, pp. 140 041–140 055, 2023.DOI: 10.1109/ACCESS.2023. 3339581","arxiv_id":"2607.24567","detector":"doi_compliance","evidence":{"ref_index":14,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1109/access.2023","reconstructed_doi":"10.1109/ACCESS.2023.3339581"},"severity":"advisory","ref_index":14,"audited_at":"2026-07-31T11:42:27.733245Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/ACCESS.2023.3339581","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"ba508fcabb3d16894f7089c3584046b329570cfc8e84c52ab1cddb0506d4b7b1","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":14348,"payload_sha256":"0e141f73227a295a10beaa54e566f336c643fa2d9fbe7e25958b8ab2bb21709d","signature_b64":null,"signing_key_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T11:46:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E6vJobJUNGi59izftgCGBc+P1tr3Ruy9XiMucgvB1LD8DRiHRdcwiDIKl+LWvHQ/e96xrarO05gi10jVc0a7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T21:47:22.083635Z"},"content_sha256":"9671f9c1d228e86c80bb405344176ec1b27a84d3252699e4bcfed29206247fb5","schema_version":"1.0","event_id":"sha256:9671f9c1d228e86c80bb405344176ec1b27a84d3252699e4bcfed29206247fb5"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:PXDYEZ473GVATK3NVDIUORKIGJ","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/CVPR.2017.348) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Q.-Y . Jiang and W.-J. Li, “Deep Cross-Modal Hashing,” in2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI: IEEE, Jul. 2017, pp. 3270–3278.DOI: 10.1109/CVPR. 2017.348","arxiv_id":"2607.24567","detector":"doi_compliance","evidence":{"ref_index":10,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1109/cvpr","reconstructed_doi":"10.1109/CVPR.2017.348"},"severity":"advisory","ref_index":10,"audited_at":"2026-07-31T11:42:27.733245Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/CVPR.2017.348","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"29bc83a91dc480530777ec874a0b89682764c7b88dea5b26d18148b5b59ea94f","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":14347,"payload_sha256":"f723df5f789c6cfa5fafdeda3fb0926093c1c31355d056d7fdb5820f34c7bf3d","signature_b64":null,"signing_key_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T11:46:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hwQhF/GO+ZH387xkL0sRLuw/BFQnSH5YLsgAqB3MFPp8MWNG/g2p+toRJy+T7Qmquvgxzy90onUmKDo2PC6oCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T21:47:22.084022Z"},"content_sha256":"db29006bfd5122f49d113613600c3ff348973333a756c19fc462cae830d3fb05","schema_version":"1.0","event_id":"sha256:db29006bfd5122f49d113613600c3ff348973333a756c19fc462cae830d3fb05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PXDYEZ473GVATK3NVDIUORKIGJ/bundle.json","state_url":"https://pith.science/pith/PXDYEZ473GVATK3NVDIUORKIGJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PXDYEZ473GVATK3NVDIUORKIGJ/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":"2026-08-02T21:47:22Z","links":{"resolver":"https://pith.science/pith/PXDYEZ473GVATK3NVDIUORKIGJ","bundle":"https://pith.science/pith/PXDYEZ473GVATK3NVDIUORKIGJ/bundle.json","state":"https://pith.science/pith/PXDYEZ473GVATK3NVDIUORKIGJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PXDYEZ473GVATK3NVDIUORKIGJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PXDYEZ473GVATK3NVDIUORKIGJ","merge_version":"pith-open-graph-merge-v1","event_count":7,"valid_event_count":7,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0678d3f8d7c555a9e80c91df823352d6052a9d93f136cb65c2c42434c40cfee9","cross_cats_sorted":["cs.CV","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T15:35:52Z","title_canon_sha256":"8bbf6d4895135cf60aed10c6dba97c9f43e94764d00bde438dbac32c8b6f7733"},"schema_version":"1.0","source":{"id":"2607.24567","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24567","created_at":"2026-07-28T02:24:10Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24567v1","created_at":"2026-07-28T02:24:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24567","created_at":"2026-07-28T02:24:10Z"},{"alias_kind":"pith_short_12","alias_value":"PXDYEZ473GVA","created_at":"2026-07-28T02:24:10Z"},{"alias_kind":"pith_short_16","alias_value":"PXDYEZ473GVATK3N","created_at":"2026-07-28T02:24:10Z"},{"alias_kind":"pith_short_8","alias_value":"PXDYEZ47","created_at":"2026-07-28T02:24:10Z"}],"graph_snapshots":[{"event_id":"sha256:1ac809983735deeca645895468e7ea9fb8288e13fd58bad8db87e2623cc55c83","target":"graph","created_at":"2026-07-28T02:24:10Z","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/2607.24567/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semantic hashing methods for generating short binary hash codes that allow efficient approximate nearest neighbor search in high-dimensional data spaces have gained extensive consideration in recent years. Deep learning-based methods offer better semantic capturing capabilities than traditional approaches relying on manual feature engineering. Moreover, they enable a data-driven approach to semantic hashing across diverse data modalities, yielding high-quality cross-modal hash codes within a shared Hamming space. Previous work investigated the properties of this Hamming space and introduced a ","authors_text":"Christian Bergler, Christian Riess, Daniel Loebenberger, Tobias J. Bauer","cross_cats":["cs.CV","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T15:35:52Z","title":"DSCH-Loss: A Dynamic Semantic Channel Objective for Deep Semantic Hashing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24567","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:a20c9c06ec3328d21d8efef529a62f250e892a55d93594e4401c9c987f998ccb","target":"record","created_at":"2026-07-28T02:24:10Z","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":"0678d3f8d7c555a9e80c91df823352d6052a9d93f136cb65c2c42434c40cfee9","cross_cats_sorted":["cs.CV","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T15:35:52Z","title_canon_sha256":"8bbf6d4895135cf60aed10c6dba97c9f43e94764d00bde438dbac32c8b6f7733"},"schema_version":"1.0","source":{"id":"2607.24567","kind":"arxiv","version":1}},"canonical_sha256":"7dc782679fd9aa09ab6da8d147454832623b859df7660736b0802d73dc82a8ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dc782679fd9aa09ab6da8d147454832623b859df7660736b0802d73dc82a8ca","first_computed_at":"2026-07-28T02:24:10.624589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T02:24:10.624589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a9Td0iNw1q/poc50Q3hA/poc92u9vG+qZUjEw+qLExxJWEFPdxFEVNIKJsBYw8GBiXrPFGK1FNZ/iLOa268YBA==","signature_status":"signed_v1","signed_at":"2026-07-28T02:24:10.625405Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24567","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:8742b0ccbb71d7c3abfc29020583673f321683f7c24ee33ca4ecf96f53d6098d","sha256:94d58cab9457f3210c92455a8277ed6226be35b977c6e3e0d615165705e91d03","sha256:9671f9c1d228e86c80bb405344176ec1b27a84d3252699e4bcfed29206247fb5","sha256:d7b74bb176d7e145258973f5f6c5a630081a4d9ad234963f54f9501e5ec27223","sha256:db29006bfd5122f49d113613600c3ff348973333a756c19fc462cae830d3fb05"]}],"invalid_events":[],"applied_event_ids":["sha256:a20c9c06ec3328d21d8efef529a62f250e892a55d93594e4401c9c987f998ccb","sha256:1ac809983735deeca645895468e7ea9fb8288e13fd58bad8db87e2623cc55c83"],"state_sha256":"fa2d0831df6c00cb8d84516cd55418b200abdf27c244c9bba64e4b862533534f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/hWU+8qzXmHNZScVr9U1ju4FCzcfST65ouGAoaCMtpE/+pLsZz/jk6qdi/ZHHdJ7Kg0W9l+0lOlYgdgqs+agAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T21:47:22.087711Z","bundle_sha256":"b1bd4235a2334166252b18a1ccf220f97096d7372cfb5110214666bb4f940620"}}