{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ND4ZHNXZF63B7FGZTJ2O4M5XNN","short_pith_number":"pith:ND4ZHNXZ","canonical_record":{"source":{"id":"2502.07436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-11T10:24:57Z","cross_cats_sorted":[],"title_canon_sha256":"da88ff51b908b857b6430bd749e006cdac6ccf385f325bb794a5dae710949018","abstract_canon_sha256":"b8f6805ce8c1d47182ea55e6281535951e1ccb67461ac05fa483c5f7b17dfcb2"},"schema_version":"1.0"},"canonical_sha256":"68f993b6f92fb61f94d99a74ee33b76b64a5966fbfc09c76c6d239021ae8d90c","source":{"kind":"arxiv","id":"2502.07436","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07436","created_at":"2026-07-05T10:12:37Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07436v1","created_at":"2026-07-05T10:12:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07436","created_at":"2026-07-05T10:12:37Z"},{"alias_kind":"pith_short_12","alias_value":"ND4ZHNXZF63B","created_at":"2026-07-05T10:12:37Z"},{"alias_kind":"pith_short_16","alias_value":"ND4ZHNXZF63B7FGZ","created_at":"2026-07-05T10:12:37Z"},{"alias_kind":"pith_short_8","alias_value":"ND4ZHNXZ","created_at":"2026-07-05T10:12:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ND4ZHNXZF63B7FGZTJ2O4M5XNN","target":"record","payload":{"canonical_record":{"source":{"id":"2502.07436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-11T10:24:57Z","cross_cats_sorted":[],"title_canon_sha256":"da88ff51b908b857b6430bd749e006cdac6ccf385f325bb794a5dae710949018","abstract_canon_sha256":"b8f6805ce8c1d47182ea55e6281535951e1ccb67461ac05fa483c5f7b17dfcb2"},"schema_version":"1.0"},"canonical_sha256":"68f993b6f92fb61f94d99a74ee33b76b64a5966fbfc09c76c6d239021ae8d90c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:37.352932Z","signature_b64":"ooeeUK9BVPygbGxVfjzINfL4GAVF94ikjHfMaZtew5qyj2kYKvb9vDTKhox46HVsUFpzk9THJMLr6N5gnxAMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68f993b6f92fb61f94d99a74ee33b76b64a5966fbfc09c76c6d239021ae8d90c","last_reissued_at":"2026-07-05T10:12:37.352477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:37.352477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.07436","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":"2026-07-05T10:12:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y4GkRmSztuZf7EXFi2ocQXwK/jY5QPB6pdEYmTvz5i/V5TbFEbff3usCPRy0ySjwOhmxFlq+PLmVVH0Fkoi2BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:53:10.615581Z"},"content_sha256":"fcb48b2276f413e0b527c64d0c104ed09e7071d8d24b8f87c8805cdf75bead6c","schema_version":"1.0","event_id":"sha256:fcb48b2276f413e0b527c64d0c104ed09e7071d8d24b8f87c8805cdf75bead6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ND4ZHNXZF63B7FGZTJ2O4M5XNN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Knowledge Distillation in Transformers: Enabling Multi-Head Attention without Alignment Barriers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiajun Liang, Linze Li, Zhaodong Bing","submitted_at":"2025-02-11T10:24:57Z","abstract_excerpt":"Knowledge distillation (KD) in transformers often faces challenges due to misalignment in the number of attention heads between teacher and student models. Existing methods either require identical head counts or introduce projectors to bridge dimensional gaps, limiting flexibility and efficiency. We propose Squeezing-Heads Distillation (SHD), a novel approach that enables seamless knowledge transfer between models with varying head counts by compressing multi-head attention maps via efficient linear approximation. Unlike prior work, SHD eliminates alignment barriers without additional paramet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07436","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/2502.07436/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":"2026-07-05T10:12:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IFvP0jGUgGeOMi9IazaSFPZGL+Kc4tlN1INp/brs2LUntXiQzgnxUFtjDH24IbKEPap6G8OBUl1TK6JWl3zaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:53:10.616081Z"},"content_sha256":"93af1d8d2299cf3ae45bb496ee64bcea73ce9e9d50c7fe28b798c759d5d62eea","schema_version":"1.0","event_id":"sha256:93af1d8d2299cf3ae45bb496ee64bcea73ce9e9d50c7fe28b798c759d5d62eea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ND4ZHNXZF63B7FGZTJ2O4M5XNN/bundle.json","state_url":"https://pith.science/pith/ND4ZHNXZF63B7FGZTJ2O4M5XNN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ND4ZHNXZF63B7FGZTJ2O4M5XNN/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":"2026-08-10T16:53:10Z","links":{"resolver":"https://pith.science/pith/ND4ZHNXZF63B7FGZTJ2O4M5XNN","bundle":"https://pith.science/pith/ND4ZHNXZF63B7FGZTJ2O4M5XNN/bundle.json","state":"https://pith.science/pith/ND4ZHNXZF63B7FGZTJ2O4M5XNN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ND4ZHNXZF63B7FGZTJ2O4M5XNN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ND4ZHNXZF63B7FGZTJ2O4M5XNN","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":"b8f6805ce8c1d47182ea55e6281535951e1ccb67461ac05fa483c5f7b17dfcb2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-11T10:24:57Z","title_canon_sha256":"da88ff51b908b857b6430bd749e006cdac6ccf385f325bb794a5dae710949018"},"schema_version":"1.0","source":{"id":"2502.07436","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07436","created_at":"2026-07-05T10:12:37Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07436v1","created_at":"2026-07-05T10:12:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07436","created_at":"2026-07-05T10:12:37Z"},{"alias_kind":"pith_short_12","alias_value":"ND4ZHNXZF63B","created_at":"2026-07-05T10:12:37Z"},{"alias_kind":"pith_short_16","alias_value":"ND4ZHNXZF63B7FGZ","created_at":"2026-07-05T10:12:37Z"},{"alias_kind":"pith_short_8","alias_value":"ND4ZHNXZ","created_at":"2026-07-05T10:12:37Z"}],"graph_snapshots":[{"event_id":"sha256:93af1d8d2299cf3ae45bb496ee64bcea73ce9e9d50c7fe28b798c759d5d62eea","target":"graph","created_at":"2026-07-05T10:12:37Z","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/2502.07436/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge distillation (KD) in transformers often faces challenges due to misalignment in the number of attention heads between teacher and student models. Existing methods either require identical head counts or introduce projectors to bridge dimensional gaps, limiting flexibility and efficiency. We propose Squeezing-Heads Distillation (SHD), a novel approach that enables seamless knowledge transfer between models with varying head counts by compressing multi-head attention maps via efficient linear approximation. Unlike prior work, SHD eliminates alignment barriers without additional paramet","authors_text":"Jiajun Liang, Linze Li, Zhaodong Bing","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-11T10:24:57Z","title":"Optimizing Knowledge Distillation in Transformers: Enabling Multi-Head Attention without Alignment Barriers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07436","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:fcb48b2276f413e0b527c64d0c104ed09e7071d8d24b8f87c8805cdf75bead6c","target":"record","created_at":"2026-07-05T10:12:37Z","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":"b8f6805ce8c1d47182ea55e6281535951e1ccb67461ac05fa483c5f7b17dfcb2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-11T10:24:57Z","title_canon_sha256":"da88ff51b908b857b6430bd749e006cdac6ccf385f325bb794a5dae710949018"},"schema_version":"1.0","source":{"id":"2502.07436","kind":"arxiv","version":1}},"canonical_sha256":"68f993b6f92fb61f94d99a74ee33b76b64a5966fbfc09c76c6d239021ae8d90c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68f993b6f92fb61f94d99a74ee33b76b64a5966fbfc09c76c6d239021ae8d90c","first_computed_at":"2026-07-05T10:12:37.352477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:37.352477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ooeeUK9BVPygbGxVfjzINfL4GAVF94ikjHfMaZtew5qyj2kYKvb9vDTKhox46HVsUFpzk9THJMLr6N5gnxAMAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:37.352932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07436","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcb48b2276f413e0b527c64d0c104ed09e7071d8d24b8f87c8805cdf75bead6c","sha256:93af1d8d2299cf3ae45bb496ee64bcea73ce9e9d50c7fe28b798c759d5d62eea"],"state_sha256":"d2c3375aa81897300570143162e2b3808130ddf40a12033547ea993e6a7d85f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7tmd3RnCfSfXLTh4t6aYjb+TYc3O4gXb97OUDGoDuzUaRdYlxU5bTvn9KfJumTmA3FOZlCVlm5xmpk0gxQs0Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T16:53:10.621195Z","bundle_sha256":"a3f573becb9946710c4a0949509859764ae6af48d132d354751652112810cb98"}}