{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YLUTT6ZCOF34IYL6P7ELRP76JF","short_pith_number":"pith:YLUTT6ZC","canonical_record":{"source":{"id":"2607.03551","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T18:27:18Z","cross_cats_sorted":[],"title_canon_sha256":"68f25e52409171065e0e7fb0dbfc1c9685805d61c079c550a0dda7740f2874e7","abstract_canon_sha256":"80f9b9d33cfd7ce2e6d0048a86995760679885ffe4042528e8db594bb86ffb39"},"schema_version":"1.0"},"canonical_sha256":"c2e939fb227177c4617e7fc8b8bffe497de111a01f74e7d1eb1b119ab6fc2986","source":{"kind":"arxiv","id":"2607.03551","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03551","created_at":"2026-07-07T02:17:53Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03551v1","created_at":"2026-07-07T02:17:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03551","created_at":"2026-07-07T02:17:53Z"},{"alias_kind":"pith_short_12","alias_value":"YLUTT6ZCOF34","created_at":"2026-07-07T02:17:53Z"},{"alias_kind":"pith_short_16","alias_value":"YLUTT6ZCOF34IYL6","created_at":"2026-07-07T02:17:53Z"},{"alias_kind":"pith_short_8","alias_value":"YLUTT6ZC","created_at":"2026-07-07T02:17:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YLUTT6ZCOF34IYL6P7ELRP76JF","target":"record","payload":{"canonical_record":{"source":{"id":"2607.03551","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T18:27:18Z","cross_cats_sorted":[],"title_canon_sha256":"68f25e52409171065e0e7fb0dbfc1c9685805d61c079c550a0dda7740f2874e7","abstract_canon_sha256":"80f9b9d33cfd7ce2e6d0048a86995760679885ffe4042528e8db594bb86ffb39"},"schema_version":"1.0"},"canonical_sha256":"c2e939fb227177c4617e7fc8b8bffe497de111a01f74e7d1eb1b119ab6fc2986","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:17:53.312386Z","signature_b64":"52A0foeaODYh/0MPaSSPSL5/k9F30fSWByrcMDk6O4VCBc+tcNO7KmNRtt/CmXJiPFtmXTIyFRUPGPJjWi7tCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2e939fb227177c4617e7fc8b8bffe497de111a01f74e7d1eb1b119ab6fc2986","last_reissued_at":"2026-07-07T02:17:53.311628Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:17:53.311628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.03551","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":"2026-07-07T02:17:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m/c5MYnNni/1QbSCIERQjh1JqcXMYngmW/sMYsFAFR5IMXLyBtV+BlcbJDaFNTl+DN0ZvNYPZlhoFH6PtuWvDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T03:46:05.760459Z"},"content_sha256":"9dee215c78b8164733cba1bb56e856fd46ca59cbf71dbdcbf502ae6e16ed5466","schema_version":"1.0","event_id":"sha256:9dee215c78b8164733cba1bb56e856fd46ca59cbf71dbdcbf502ae6e16ed5466"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YLUTT6ZCOF34IYL6P7ELRP76JF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WeightCLIP: Aligning Datasets and Models for Weight Space Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aron Asefaw, Damian Borth, Damian Falk, Konstantinos Tzevelekakis, L\\'eo Meynent","submitted_at":"2026-07-03T18:27:18Z","abstract_excerpt":"Weight space learning aims to learn representations of neural network (NN) weights, enabling different downstream tasks. Existing approaches show promising performance, but lacking a way to shape these weight-space representations using information about the datasets the models were trained on, thus limiting downstream applications. We propose WeightCLIP, a method for learning a dataset-aligned latent space for neural networks, where datasets information is induced during training. The NNs are encoded as latent representations using an autoencoder, while dataset samples are encoded using a dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03551","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/2607.03551/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":"2026-07-07T02:17:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VxHgOMxggK5SAhhSu3GDbcjwaB+O0C41MnruRl7RIa+t/KhcPPeYMFhp0+a//DEkyozLaS4vVrLogUjzwjiODA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T03:46:05.760838Z"},"content_sha256":"d2d0dbe9c6672be967be6ea70a0bf8d23d6e518411d3e26ce9cf401ce9599686","schema_version":"1.0","event_id":"sha256:d2d0dbe9c6672be967be6ea70a0bf8d23d6e518411d3e26ce9cf401ce9599686"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:YLUTT6ZCOF34IYL6P7ELRP76JF","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/TBME.2015.2496264.Tian) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"doi: 10.1109/TBME. 2015.2496264. Tian, B., Chen, W., Li, Z., Lai, S., Wu, J., and Yue, Y . Text2weight: Bridging natural language and neural net- work weight spaces. InProceedings of the 33rd ACM In- ternational Conference on Multimedia, pp","arxiv_id":"2607.03551","detector":"doi_compliance","evidence":{"ref_index":22,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"doi: 10.1109/TBME. 2015.2496264. Tian, B., Chen, W., Li, Z., Lai, S., Wu, J., and Yue, Y . Text2weight: Bridging natural language and neural net- work weight spaces. InProceedings of the 33rd ACM In- ternational Conference on Multimedia, pp","reconstructed_doi":"10.1109/TBME.2015.2496264.Tian"},"severity":"advisory","ref_index":22,"audited_at":"2026-07-12T01:47:32.005514Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/TBME.2015.2496264.Tian","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"4ae8c1f48371ce233a2b0ba9ef89adfc5f2785201415aa8706b336c3b3bcfa50","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":12405,"payload_sha256":"d28609fd3584d96e6dded8173fab7e809c81afb8d1beee7ee3832cc8fa6e43a2","signature_b64":"Mh6JIUrI1Ig57kspmHJnk3LhYEUpUXHb+SScKMfizg4H1BeWgMPRFXT6nIgMBlwjgGRCAi66IT2cXb7c0GS4AA==","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":"2026-07-12T01:51:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yxsmG941u4h9RFVr3vY54APpfa1OBPx15e9BcMfkC049ZkQ4hTf4dFQE/gfpluQ8/qUbZYfhXSVQoVgKl9q/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T03:46:05.762544Z"},"content_sha256":"e0a934af262b895195b7c553562c4ce724ad7d0613a2f28df3be15b179376098","schema_version":"1.0","event_id":"sha256:e0a934af262b895195b7c553562c4ce724ad7d0613a2f28df3be15b179376098"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:YLUTT6ZCOF34IYL6P7ELRP76JF","target":"integrity","payload":{"note":"DOI '10.1109/wacv' as printed in the bibliography is syntactically invalid and cannot resolve.","snippet":"doi: 10.1109/WACV . 2018.00011. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Om- mer, B. High-Resolution Image Synthesis with Latent Diffusion Models. InIEEE/CVF Conference on Com- puter Vision and Pattern Recognition (CVPR),","arxiv_id":"2607.03551","detector":"doi_compliance","evidence":{"ref_index":20,"raw_excerpt":"doi: 10.1109/WACV . 2018.00011. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Om- mer, B. High-Resolution Image Synthesis with Latent Diffusion Models. InIEEE/CVF Conference on Com- puter Vision and Pattern Recognition (CVPR),","verdict_class":"incontrovertible","doi_as_printed":"10.1109/wacv"},"severity":"critical","ref_index":20,"audited_at":"2026-07-12T01:47:32.005514Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/wacv","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"broken_identifier","evidence_hash":"206d465811abfffc4fc803270441f18f9b63c16799da3dcebef49fc4b6960aa0","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":12404,"payload_sha256":"81894f9a825dea79c9950facaa9b07eed9a160554d2bcf2aec4c1315031d9b16","signature_b64":"hmbi4DxVpXLmsqTxPzfXt6lvEGz7MpwwAFD1Y2TsWumxpyMs5ORQM0b8Dz2Q8Q6SKOnSY/1aDumnUCjv7RGuCg==","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":"2026-07-12T01:51:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KxoBvNSbg0mpxMBbM3eId4DuCzaGIpwR1dtFAxJZIcrD8pqNlqetKP00pCvZw5onsooW3j8PZzHQfl/V/BExDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T03:46:05.762830Z"},"content_sha256":"d5a816f540188ca401cc50705acab0dd81f2c51cd94714543a3f359fd8ad629a","schema_version":"1.0","event_id":"sha256:d5a816f540188ca401cc50705acab0dd81f2c51cd94714543a3f359fd8ad629a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YLUTT6ZCOF34IYL6P7ELRP76JF/bundle.json","state_url":"https://pith.science/pith/YLUTT6ZCOF34IYL6P7ELRP76JF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YLUTT6ZCOF34IYL6P7ELRP76JF/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":"2026-07-27T03:46:05Z","links":{"resolver":"https://pith.science/pith/YLUTT6ZCOF34IYL6P7ELRP76JF","bundle":"https://pith.science/pith/YLUTT6ZCOF34IYL6P7ELRP76JF/bundle.json","state":"https://pith.science/pith/YLUTT6ZCOF34IYL6P7ELRP76JF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YLUTT6ZCOF34IYL6P7ELRP76JF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YLUTT6ZCOF34IYL6P7ELRP76JF","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"80f9b9d33cfd7ce2e6d0048a86995760679885ffe4042528e8db594bb86ffb39","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T18:27:18Z","title_canon_sha256":"68f25e52409171065e0e7fb0dbfc1c9685805d61c079c550a0dda7740f2874e7"},"schema_version":"1.0","source":{"id":"2607.03551","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03551","created_at":"2026-07-07T02:17:53Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03551v1","created_at":"2026-07-07T02:17:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03551","created_at":"2026-07-07T02:17:53Z"},{"alias_kind":"pith_short_12","alias_value":"YLUTT6ZCOF34","created_at":"2026-07-07T02:17:53Z"},{"alias_kind":"pith_short_16","alias_value":"YLUTT6ZCOF34IYL6","created_at":"2026-07-07T02:17:53Z"},{"alias_kind":"pith_short_8","alias_value":"YLUTT6ZC","created_at":"2026-07-07T02:17:53Z"}],"graph_snapshots":[{"event_id":"sha256:d2d0dbe9c6672be967be6ea70a0bf8d23d6e518411d3e26ce9cf401ce9599686","target":"graph","created_at":"2026-07-07T02:17:53Z","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/2607.03551/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Weight space learning aims to learn representations of neural network (NN) weights, enabling different downstream tasks. Existing approaches show promising performance, but lacking a way to shape these weight-space representations using information about the datasets the models were trained on, thus limiting downstream applications. We propose WeightCLIP, a method for learning a dataset-aligned latent space for neural networks, where datasets information is induced during training. The NNs are encoded as latent representations using an autoencoder, while dataset samples are encoded using a dat","authors_text":"Aron Asefaw, Damian Borth, Damian Falk, Konstantinos Tzevelekakis, L\\'eo Meynent","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T18:27:18Z","title":"WeightCLIP: Aligning Datasets and Models for Weight Space Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03551","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":"sha256:9dee215c78b8164733cba1bb56e856fd46ca59cbf71dbdcbf502ae6e16ed5466","target":"record","created_at":"2026-07-07T02:17:53Z","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":"80f9b9d33cfd7ce2e6d0048a86995760679885ffe4042528e8db594bb86ffb39","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T18:27:18Z","title_canon_sha256":"68f25e52409171065e0e7fb0dbfc1c9685805d61c079c550a0dda7740f2874e7"},"schema_version":"1.0","source":{"id":"2607.03551","kind":"arxiv","version":1}},"canonical_sha256":"c2e939fb227177c4617e7fc8b8bffe497de111a01f74e7d1eb1b119ab6fc2986","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2e939fb227177c4617e7fc8b8bffe497de111a01f74e7d1eb1b119ab6fc2986","first_computed_at":"2026-07-07T02:17:53.311628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:17:53.311628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"52A0foeaODYh/0MPaSSPSL5/k9F30fSWByrcMDk6O4VCBc+tcNO7KmNRtt/CmXJiPFtmXTIyFRUPGPJjWi7tCg==","signature_status":"signed_v1","signed_at":"2026-07-07T02:17:53.312386Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.03551","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:d5a816f540188ca401cc50705acab0dd81f2c51cd94714543a3f359fd8ad629a","sha256:e0a934af262b895195b7c553562c4ce724ad7d0613a2f28df3be15b179376098"]}],"invalid_events":[],"applied_event_ids":["sha256:9dee215c78b8164733cba1bb56e856fd46ca59cbf71dbdcbf502ae6e16ed5466","sha256:d2d0dbe9c6672be967be6ea70a0bf8d23d6e518411d3e26ce9cf401ce9599686"],"state_sha256":"e341a7479d02c6aded3bf56642c082936127c89164a17632284e94dea8d1b6b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hb/JG9aeF4mqviT1x2S1f6nwBw2z8Od3AYwYFYqjBf7MSJOueqyE3dnXfpQSiSeoiUlCDLPtqEH21ODtjgOnBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T03:46:05.764434Z","bundle_sha256":"8167fc4ad59fe5f9dba420bb2dd88e1cc1e994a98db889216fb2808244fa1f0f"}}