{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:53YJHGVOI3GBLTYXEECMOEHVP4","short_pith_number":"pith:53YJHGVO","canonical_record":{"source":{"id":"2605.28331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T11:34:27Z","cross_cats_sorted":[],"title_canon_sha256":"c2f04aee38419704f226bc9fb589c587d81b7d0bb89a65ee4fe9a8a6a0f838df","abstract_canon_sha256":"44f399d23632114f51086f8ab2310799780563319a8a4ad242e3571b2f9a5bc3"},"schema_version":"1.0"},"canonical_sha256":"eef0939aae46cc15cf172104c710f57f226d02bd770380692fac9151de541568","source":{"kind":"arxiv","id":"2605.28331","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28331","created_at":"2026-05-28T01:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28331v1","created_at":"2026-05-28T01:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28331","created_at":"2026-05-28T01:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"53YJHGVOI3GB","created_at":"2026-05-28T01:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"53YJHGVOI3GBLTYX","created_at":"2026-05-28T01:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"53YJHGVO","created_at":"2026-05-28T01:05:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:53YJHGVOI3GBLTYXEECMOEHVP4","target":"record","payload":{"canonical_record":{"source":{"id":"2605.28331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T11:34:27Z","cross_cats_sorted":[],"title_canon_sha256":"c2f04aee38419704f226bc9fb589c587d81b7d0bb89a65ee4fe9a8a6a0f838df","abstract_canon_sha256":"44f399d23632114f51086f8ab2310799780563319a8a4ad242e3571b2f9a5bc3"},"schema_version":"1.0"},"canonical_sha256":"eef0939aae46cc15cf172104c710f57f226d02bd770380692fac9151de541568","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:13.179396Z","signature_b64":"k1CNel717bRDCQrXrbGeY+ZQyVCCNsSZiNy7FJN1hXQ4r9QvCo5p+kQYrzLO52zophjuVMxzzBf2X/J/zoGiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eef0939aae46cc15cf172104c710f57f226d02bd770380692fac9151de541568","last_reissued_at":"2026-05-28T01:05:13.178950Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:13.178950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.28331","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":"2026-05-28T01:05:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jz3rpLVRiKJl74oPuJpq74y/B4JUPK/xPaid34cFk9IXguQUHZa1ist+5cXXIYYQ5aj9MqDvrsTJRh4op2o7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T01:14:22.013532Z"},"content_sha256":"fc2e7268ba72fa98d4d373f7afe6ccc057371e49115861edb8b46d7fb602deb2","schema_version":"1.0","event_id":"sha256:fc2e7268ba72fa98d4d373f7afe6ccc057371e49115861edb8b46d7fb602deb2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:53YJHGVOI3GBLTYXEECMOEHVP4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transfer learning RGB models to hyperspectral images with trainable tensor decompositions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hendrik Blockeel, Laurens Devos, Mariette Sch\\\"onfeld, Wannes Meert","submitted_at":"2026-05-27T11:34:27Z","abstract_excerpt":"Transfer learning makes it possible to use large vision networks on a variety of domains, by specializing their models' general filters to new tasks. However, these networks assume the input images to have 3 input channels, making them incompatible with multi- or hyperspectral images. Current approaches that mitigate this incompatibility sacrifice information in either the image, or the model. This work proposes a novel approach that preserves the image and spatial information present in the model by using partially trainable tensor decompositions. We create such decompositions of pretrained c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28331","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/2605.28331/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":"2026-05-28T01:05:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2SDIDHQO3Jw6YxFnsnjojBepQlqxwRoOrMTSWcRayg8ZHCMrmGTNft2MfTQbRRMPuht8eSZ958sXyisQcR5cAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T01:14:22.013933Z"},"content_sha256":"59a58f558708656b6164e3ccabbbc63b0778736ccd7b9b066f6404445adca43d","schema_version":"1.0","event_id":"sha256:59a58f558708656b6164e3ccabbbc63b0778736ccd7b9b066f6404445adca43d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/53YJHGVOI3GBLTYXEECMOEHVP4/bundle.json","state_url":"https://pith.science/pith/53YJHGVOI3GBLTYXEECMOEHVP4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/53YJHGVOI3GBLTYXEECMOEHVP4/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":"2026-06-01T01:14:22Z","links":{"resolver":"https://pith.science/pith/53YJHGVOI3GBLTYXEECMOEHVP4","bundle":"https://pith.science/pith/53YJHGVOI3GBLTYXEECMOEHVP4/bundle.json","state":"https://pith.science/pith/53YJHGVOI3GBLTYXEECMOEHVP4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/53YJHGVOI3GBLTYXEECMOEHVP4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:53YJHGVOI3GBLTYXEECMOEHVP4","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":"44f399d23632114f51086f8ab2310799780563319a8a4ad242e3571b2f9a5bc3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T11:34:27Z","title_canon_sha256":"c2f04aee38419704f226bc9fb589c587d81b7d0bb89a65ee4fe9a8a6a0f838df"},"schema_version":"1.0","source":{"id":"2605.28331","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28331","created_at":"2026-05-28T01:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28331v1","created_at":"2026-05-28T01:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28331","created_at":"2026-05-28T01:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"53YJHGVOI3GB","created_at":"2026-05-28T01:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"53YJHGVOI3GBLTYX","created_at":"2026-05-28T01:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"53YJHGVO","created_at":"2026-05-28T01:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:59a58f558708656b6164e3ccabbbc63b0778736ccd7b9b066f6404445adca43d","target":"graph","created_at":"2026-05-28T01:05:13Z","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/2605.28331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transfer learning makes it possible to use large vision networks on a variety of domains, by specializing their models' general filters to new tasks. However, these networks assume the input images to have 3 input channels, making them incompatible with multi- or hyperspectral images. Current approaches that mitigate this incompatibility sacrifice information in either the image, or the model. This work proposes a novel approach that preserves the image and spatial information present in the model by using partially trainable tensor decompositions. We create such decompositions of pretrained c","authors_text":"Hendrik Blockeel, Laurens Devos, Mariette Sch\\\"onfeld, Wannes Meert","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T11:34:27Z","title":"Transfer learning RGB models to hyperspectral images with trainable tensor decompositions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28331","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:fc2e7268ba72fa98d4d373f7afe6ccc057371e49115861edb8b46d7fb602deb2","target":"record","created_at":"2026-05-28T01:05:13Z","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":"44f399d23632114f51086f8ab2310799780563319a8a4ad242e3571b2f9a5bc3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T11:34:27Z","title_canon_sha256":"c2f04aee38419704f226bc9fb589c587d81b7d0bb89a65ee4fe9a8a6a0f838df"},"schema_version":"1.0","source":{"id":"2605.28331","kind":"arxiv","version":1}},"canonical_sha256":"eef0939aae46cc15cf172104c710f57f226d02bd770380692fac9151de541568","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eef0939aae46cc15cf172104c710f57f226d02bd770380692fac9151de541568","first_computed_at":"2026-05-28T01:05:13.178950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:05:13.178950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k1CNel717bRDCQrXrbGeY+ZQyVCCNsSZiNy7FJN1hXQ4r9QvCo5p+kQYrzLO52zophjuVMxzzBf2X/J/zoGiCw==","signature_status":"signed_v1","signed_at":"2026-05-28T01:05:13.179396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28331","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc2e7268ba72fa98d4d373f7afe6ccc057371e49115861edb8b46d7fb602deb2","sha256:59a58f558708656b6164e3ccabbbc63b0778736ccd7b9b066f6404445adca43d"],"state_sha256":"3895a929e87c26cc11c802c26152d05ff646446ae38ae714be4c1ff7c89216c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lgdR6MV803pVA990XRALqnVoy6UWSs+Zu9zCmbKIGhzDKDr9FQySqMQGPwK8Em/JhwGU8ziYHl22c644ctwtCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T01:14:22.016748Z","bundle_sha256":"bea9c49ef9e17b5d81ab0959768d3222ba24df02fc19a026bd35e0425aa012b3"}}