{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5DEYPG7HFAP2R2CNUH5AHFLEMS","short_pith_number":"pith:5DEYPG7H","canonical_record":{"source":{"id":"2407.02880","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-03T07:54:08Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"0c5008d00513402985424b291e58ffbdaa9013a6acee5bb7eade22564760967c","abstract_canon_sha256":"e52858853176f55d236abf46e87ff3cdc10aa67906c5f2ad0c185ca7b9c1df12"},"schema_version":"1.0"},"canonical_sha256":"e8c9879be7281fa8e84da1fa03956464802cfd4bfea388928dd906b699c233f4","source":{"kind":"arxiv","id":"2407.02880","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02880","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02880v2","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02880","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"5DEYPG7HFAP2","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"5DEYPG7HFAP2R2CN","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"5DEYPG7H","created_at":"2026-07-05T09:27:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5DEYPG7HFAP2R2CNUH5AHFLEMS","target":"record","payload":{"canonical_record":{"source":{"id":"2407.02880","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-03T07:54:08Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"0c5008d00513402985424b291e58ffbdaa9013a6acee5bb7eade22564760967c","abstract_canon_sha256":"e52858853176f55d236abf46e87ff3cdc10aa67906c5f2ad0c185ca7b9c1df12"},"schema_version":"1.0"},"canonical_sha256":"e8c9879be7281fa8e84da1fa03956464802cfd4bfea388928dd906b699c233f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:23.967111Z","signature_b64":"XktUS2epIKxP60db5AQxfUBIdcaUz2S5lCzj/pwCkKmuvwruey5z+cx3+f08+osPm4o82omg/a65UZI9aGcXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8c9879be7281fa8e84da1fa03956464802cfd4bfea388928dd906b699c233f4","last_reissued_at":"2026-07-05T09:27:23.966631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:23.966631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.02880","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:27:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uqzeeufg730XeNAYRZe0dCSMMhG6e/7uqm2esaJB3U8qGb/mfIY8e9RvUjvyvIUr0ZCvw8Xl06jNall6zEVKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:58:15.542202Z"},"content_sha256":"71fb7f174846b94bf274e9cf6fbce31297e0f676f0d2e17e5f405136db6952ac","schema_version":"1.0","event_id":"sha256:71fb7f174846b94bf274e9cf6fbce31297e0f676f0d2e17e5f405136db6952ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5DEYPG7HFAP2R2CNUH5AHFLEMS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Knowledge Composition using Task Vectors with Learned Anisotropic Scaling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Anton van den Hengel, Cristian Rodriguez-Opazo, Ehsan Abbasnejad, Frederic Z. Zhang, Paul Albert","submitted_at":"2024-07-03T07:54:08Z","abstract_excerpt":"Pre-trained models produce strong generic representations that can be adapted via fine-tuning. The learned weight difference relative to the pre-trained model, known as a task vector, characterises the direction and stride of fine-tuning. The significance of task vectors is such that simple arithmetic operations on them can be used to combine diverse representations from different domains. This paper builds on these properties of task vectors and aims to answer (1) whether components of task vectors, particularly parameter blocks, exhibit similar characteristics, and (2) how such blocks can be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02880","kind":"arxiv","version":2},"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/2407.02880/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":"2026-07-05T09:27:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VCEUuurqnfDbXaa6g1L6+KNfyjEf77dQ/hQxTZxZwRErEYpSA+x1sPXFBRfEf+qYfJXHq9Luf9+3xMSnaYh+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:58:15.542815Z"},"content_sha256":"5ca543ab72ae339a0374679bdd7dfa9d3ff948af8d7048000bcbde2bec57e7bf","schema_version":"1.0","event_id":"sha256:5ca543ab72ae339a0374679bdd7dfa9d3ff948af8d7048000bcbde2bec57e7bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5DEYPG7HFAP2R2CNUH5AHFLEMS/bundle.json","state_url":"https://pith.science/pith/5DEYPG7HFAP2R2CNUH5AHFLEMS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5DEYPG7HFAP2R2CNUH5AHFLEMS/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":"2026-07-07T05:58:15Z","links":{"resolver":"https://pith.science/pith/5DEYPG7HFAP2R2CNUH5AHFLEMS","bundle":"https://pith.science/pith/5DEYPG7HFAP2R2CNUH5AHFLEMS/bundle.json","state":"https://pith.science/pith/5DEYPG7HFAP2R2CNUH5AHFLEMS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5DEYPG7HFAP2R2CNUH5AHFLEMS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5DEYPG7HFAP2R2CNUH5AHFLEMS","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":"e52858853176f55d236abf46e87ff3cdc10aa67906c5f2ad0c185ca7b9c1df12","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-03T07:54:08Z","title_canon_sha256":"0c5008d00513402985424b291e58ffbdaa9013a6acee5bb7eade22564760967c"},"schema_version":"1.0","source":{"id":"2407.02880","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02880","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02880v2","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02880","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"5DEYPG7HFAP2","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"5DEYPG7HFAP2R2CN","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"5DEYPG7H","created_at":"2026-07-05T09:27:23Z"}],"graph_snapshots":[{"event_id":"sha256:5ca543ab72ae339a0374679bdd7dfa9d3ff948af8d7048000bcbde2bec57e7bf","target":"graph","created_at":"2026-07-05T09:27:23Z","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/2407.02880/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained models produce strong generic representations that can be adapted via fine-tuning. The learned weight difference relative to the pre-trained model, known as a task vector, characterises the direction and stride of fine-tuning. The significance of task vectors is such that simple arithmetic operations on them can be used to combine diverse representations from different domains. This paper builds on these properties of task vectors and aims to answer (1) whether components of task vectors, particularly parameter blocks, exhibit similar characteristics, and (2) how such blocks can be","authors_text":"Anton van den Hengel, Cristian Rodriguez-Opazo, Ehsan Abbasnejad, Frederic Z. Zhang, Paul Albert","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-03T07:54:08Z","title":"Knowledge Composition using Task Vectors with Learned Anisotropic Scaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02880","kind":"arxiv","version":2},"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":"sha256:71fb7f174846b94bf274e9cf6fbce31297e0f676f0d2e17e5f405136db6952ac","target":"record","created_at":"2026-07-05T09:27:23Z","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":"e52858853176f55d236abf46e87ff3cdc10aa67906c5f2ad0c185ca7b9c1df12","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-03T07:54:08Z","title_canon_sha256":"0c5008d00513402985424b291e58ffbdaa9013a6acee5bb7eade22564760967c"},"schema_version":"1.0","source":{"id":"2407.02880","kind":"arxiv","version":2}},"canonical_sha256":"e8c9879be7281fa8e84da1fa03956464802cfd4bfea388928dd906b699c233f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8c9879be7281fa8e84da1fa03956464802cfd4bfea388928dd906b699c233f4","first_computed_at":"2026-07-05T09:27:23.966631Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:23.966631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XktUS2epIKxP60db5AQxfUBIdcaUz2S5lCzj/pwCkKmuvwruey5z+cx3+f08+osPm4o82omg/a65UZI9aGcXDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:23.967111Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02880","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71fb7f174846b94bf274e9cf6fbce31297e0f676f0d2e17e5f405136db6952ac","sha256:5ca543ab72ae339a0374679bdd7dfa9d3ff948af8d7048000bcbde2bec57e7bf"],"state_sha256":"c29a36ffd7ecb6e0626430008401d8dd443b993a5ac81e2324402ad02edce023"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"li3+ESQBAMAn/ZLieTm2LDxVHtpGDENFHbXYoty7p2b7BbSZ3XVWh01Hg3eIsDvNg1cDQhcgtMvuRaOSpFFBDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:58:15.546020Z","bundle_sha256":"7c044ad119d49803ba5afc2e97467f7d36e7f4ba4715570493eb7e19b1af809a"}}