{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:NIK7EQRTHQ6T5XLU7WVJBB3Z37","short_pith_number":"pith:NIK7EQRT","canonical_record":{"source":{"id":"1412.3121","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-12-09T21:12:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"46a963dec286286ae959e49738e97ae2a122aa1618b985b3865f8f6e5c4e55c0","abstract_canon_sha256":"06e272be61560aff21920d97a081ab0fb601270c68906b51cd449af5ce0f1175"},"schema_version":"1.0"},"canonical_sha256":"6a15f242333c3d3edd74fdaa908779dfd993316aa8eb8c4976e8357f2aed4c59","source":{"kind":"arxiv","id":"1412.3121","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.3121","created_at":"2026-05-18T01:20:26Z"},{"alias_kind":"arxiv_version","alias_value":"1412.3121v2","created_at":"2026-05-18T01:20:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.3121","created_at":"2026-05-18T01:20:26Z"},{"alias_kind":"pith_short_12","alias_value":"NIK7EQRTHQ6T","created_at":"2026-05-18T12:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"NIK7EQRTHQ6T5XLU","created_at":"2026-05-18T12:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"NIK7EQRT","created_at":"2026-05-18T12:28:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:NIK7EQRTHQ6T5XLU7WVJBB3Z37","target":"record","payload":{"canonical_record":{"source":{"id":"1412.3121","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-12-09T21:12:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"46a963dec286286ae959e49738e97ae2a122aa1618b985b3865f8f6e5c4e55c0","abstract_canon_sha256":"06e272be61560aff21920d97a081ab0fb601270c68906b51cd449af5ce0f1175"},"schema_version":"1.0"},"canonical_sha256":"6a15f242333c3d3edd74fdaa908779dfd993316aa8eb8c4976e8357f2aed4c59","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:26.374705Z","signature_b64":"/jB4rGYDwkUkXhVYVbbEWc2b0rLHwgyCBdOb8V4xtY7n2G4CJebus0ElcKif8mpaFc1BS9+vAmjP3iZ7dQUSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a15f242333c3d3edd74fdaa908779dfd993316aa8eb8c4976e8357f2aed4c59","last_reissued_at":"2026-05-18T01:20:26.373983Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:26.373983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1412.3121","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":"2026-05-18T01:20:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DL1YRpQzEgeYuf51VXcl9s7KMoTwL+3AvvEKyYQh+JkQcjq0nTPtwJEruz7tf3VtUKakCfRnDj6l30zyZoGLAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T09:28:01.406076Z"},"content_sha256":"24e863bc952bac7e0b9ec96b8612e50e149b6ef5b2083244b1a30fb8a71f2de9","schema_version":"1.0","event_id":"sha256:24e863bc952bac7e0b9ec96b8612e50e149b6ef5b2083244b1a30fb8a71f2de9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:NIK7EQRTHQ6T5XLU7WVJBB3Z37","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Transfer Deep Learning with Applications in Audio-Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Haohan Wang, Seungwhan Moon, Suyoun Kim","submitted_at":"2014-12-09T21:12:19Z","abstract_excerpt":"We propose a transfer deep learning (TDL) framework that can transfer the knowledge obtained from a single-modal neural network to a network with a different modality. Specifically, we show that we can leverage speech data to fine-tune the network trained for video recognition, given an initial set of audio-video parallel dataset within the same semantics. Our approach first learns the analogy-preserving embeddings between the abstract representations learned from intermediate layers of each network, allowing for semantics-level transfer between the source and target modalities. We then apply "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.3121","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":""},"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":"2026-05-18T01:20:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZYkebA1dLLWmZHRefm8P5B85wXD/NNKW4YVZRRynaZDLA0H+D8S+EEnnUI/+vPNRngibAoO6itplU+/r77e8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T09:28:01.406526Z"},"content_sha256":"4f5ad658aed9997727aa75f5802382b4ad6948024d37ac07d3d8a1054498d626","schema_version":"1.0","event_id":"sha256:4f5ad658aed9997727aa75f5802382b4ad6948024d37ac07d3d8a1054498d626"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NIK7EQRTHQ6T5XLU7WVJBB3Z37/bundle.json","state_url":"https://pith.science/pith/NIK7EQRTHQ6T5XLU7WVJBB3Z37/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NIK7EQRTHQ6T5XLU7WVJBB3Z37/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":"2026-08-23T09:28:01Z","links":{"resolver":"https://pith.science/pith/NIK7EQRTHQ6T5XLU7WVJBB3Z37","bundle":"https://pith.science/pith/NIK7EQRTHQ6T5XLU7WVJBB3Z37/bundle.json","state":"https://pith.science/pith/NIK7EQRTHQ6T5XLU7WVJBB3Z37/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NIK7EQRTHQ6T5XLU7WVJBB3Z37/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:NIK7EQRTHQ6T5XLU7WVJBB3Z37","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":"06e272be61560aff21920d97a081ab0fb601270c68906b51cd449af5ce0f1175","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-12-09T21:12:19Z","title_canon_sha256":"46a963dec286286ae959e49738e97ae2a122aa1618b985b3865f8f6e5c4e55c0"},"schema_version":"1.0","source":{"id":"1412.3121","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.3121","created_at":"2026-05-18T01:20:26Z"},{"alias_kind":"arxiv_version","alias_value":"1412.3121v2","created_at":"2026-05-18T01:20:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.3121","created_at":"2026-05-18T01:20:26Z"},{"alias_kind":"pith_short_12","alias_value":"NIK7EQRTHQ6T","created_at":"2026-05-18T12:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"NIK7EQRTHQ6T5XLU","created_at":"2026-05-18T12:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"NIK7EQRT","created_at":"2026-05-18T12:28:41Z"}],"graph_snapshots":[{"event_id":"sha256:4f5ad658aed9997727aa75f5802382b4ad6948024d37ac07d3d8a1054498d626","target":"graph","created_at":"2026-05-18T01:20:26Z","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"},"paper":{"abstract_excerpt":"We propose a transfer deep learning (TDL) framework that can transfer the knowledge obtained from a single-modal neural network to a network with a different modality. Specifically, we show that we can leverage speech data to fine-tune the network trained for video recognition, given an initial set of audio-video parallel dataset within the same semantics. Our approach first learns the analogy-preserving embeddings between the abstract representations learned from intermediate layers of each network, allowing for semantics-level transfer between the source and target modalities. We then apply ","authors_text":"Haohan Wang, Seungwhan Moon, Suyoun Kim","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-12-09T21:12:19Z","title":"Multimodal Transfer Deep Learning with Applications in Audio-Visual Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.3121","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":"sha256:24e863bc952bac7e0b9ec96b8612e50e149b6ef5b2083244b1a30fb8a71f2de9","target":"record","created_at":"2026-05-18T01:20:26Z","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":"06e272be61560aff21920d97a081ab0fb601270c68906b51cd449af5ce0f1175","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-12-09T21:12:19Z","title_canon_sha256":"46a963dec286286ae959e49738e97ae2a122aa1618b985b3865f8f6e5c4e55c0"},"schema_version":"1.0","source":{"id":"1412.3121","kind":"arxiv","version":2}},"canonical_sha256":"6a15f242333c3d3edd74fdaa908779dfd993316aa8eb8c4976e8357f2aed4c59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a15f242333c3d3edd74fdaa908779dfd993316aa8eb8c4976e8357f2aed4c59","first_computed_at":"2026-05-18T01:20:26.373983Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:20:26.373983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/jB4rGYDwkUkXhVYVbbEWc2b0rLHwgyCBdOb8V4xtY7n2G4CJebus0ElcKif8mpaFc1BS9+vAmjP3iZ7dQUSBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:20:26.374705Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.3121","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24e863bc952bac7e0b9ec96b8612e50e149b6ef5b2083244b1a30fb8a71f2de9","sha256:4f5ad658aed9997727aa75f5802382b4ad6948024d37ac07d3d8a1054498d626"],"state_sha256":"10c19cb41688f95ef8665ac2a1b8f9bb1fb41662a43e94692a675a8a8a735288"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A3/Jt8wKLr7QDCekp1ND1S6fPS+rT648jMoOXge+Z0OoklT4O+IFhk3xmWMAOOO7mogNnKx/W1CVglyLdOkXAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T09:28:01.411053Z","bundle_sha256":"ed6bdabe076b321245c15a01fc21670937e2d2ff86e308677fa8f14ac1e2f545"}}