{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Q7V7KV3TP2B2DWAVEZ65L2OXLC","short_pith_number":"pith:Q7V7KV3T","canonical_record":{"source":{"id":"2607.20922","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T04:57:22Z","cross_cats_sorted":[],"title_canon_sha256":"f39aa4df987e84225c0daaba47939cf3ff58380ad24ef46ffdf38d6b4e5ba1c8","abstract_canon_sha256":"0031067be5ce02481faa90b5f5f5a02c7b6ced90de22de03b9df785553a3b90b"},"schema_version":"1.0"},"canonical_sha256":"87ebf557737e83a1d815267dd5e9d75882411d4a2e698cdc960ea45adf938113","source":{"kind":"arxiv","id":"2607.20922","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20922","created_at":"2026-07-24T01:23:40Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20922v1","created_at":"2026-07-24T01:23:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20922","created_at":"2026-07-24T01:23:40Z"},{"alias_kind":"pith_short_12","alias_value":"Q7V7KV3TP2B2","created_at":"2026-07-24T01:23:40Z"},{"alias_kind":"pith_short_16","alias_value":"Q7V7KV3TP2B2DWAV","created_at":"2026-07-24T01:23:40Z"},{"alias_kind":"pith_short_8","alias_value":"Q7V7KV3T","created_at":"2026-07-24T01:23:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Q7V7KV3TP2B2DWAVEZ65L2OXLC","target":"record","payload":{"canonical_record":{"source":{"id":"2607.20922","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T04:57:22Z","cross_cats_sorted":[],"title_canon_sha256":"f39aa4df987e84225c0daaba47939cf3ff58380ad24ef46ffdf38d6b4e5ba1c8","abstract_canon_sha256":"0031067be5ce02481faa90b5f5f5a02c7b6ced90de22de03b9df785553a3b90b"},"schema_version":"1.0"},"canonical_sha256":"87ebf557737e83a1d815267dd5e9d75882411d4a2e698cdc960ea45adf938113","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:23:40.877469Z","signature_b64":"BOvKC4wo76znedy0usr8iV6+yOzS8qVQ4CecWfMeuGt+gqRlP19RxGIobhaRiCMBP/q4CAvtQ4CL86rFh4j3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87ebf557737e83a1d815267dd5e9d75882411d4a2e698cdc960ea45adf938113","last_reissued_at":"2026-07-24T01:23:40.876498Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:23:40.876498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.20922","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":"2026-07-24T01:23:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PE4CRz3HaffKq02blHJJ7DaUHB3DG2DnWy8m139GnLYPRUyU7XtjxDx/jWNCVES/S7RSL/9NpiWjGAJy6pE/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T14:29:04.648285Z"},"content_sha256":"8f9a3b0629234e6487e9fdf406c30b26023bfd601676561bb004ee110ae3bbd0","schema_version":"1.0","event_id":"sha256:8f9a3b0629234e6487e9fdf406c30b26023bfd601676561bb004ee110ae3bbd0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Q7V7KV3TP2B2DWAVEZ65L2OXLC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FA-LAM: Focus-Aware Large Avatar Model for One-Shot 4D Animatable Gaussian Head","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Zhang, Steven Hoi, Yiming Jiang, Yingdong Hu, Yisheng He, Zehong Lin","submitted_at":"2026-07-23T04:57:22Z","abstract_excerpt":"We propose FA-LAM, a Focus-Aware Large Avatar Model for one-shot animatable Gaussian head creation, while simultaneously enabling static 3D and dynamic 4D full-head recovery. The core of our method lies in a thorough analysis of the attention mechanisms and the entangled reconstruction and animation training pipeline adopted by prior state-of-the-art approaches. Our analysis identifies two main factors that compromise the quality of 3D full-head generation: (1) incorrect and noisy attention activations, and (2) conflicts between the tasks of reconstruction and animation. To address the first i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20922","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/2607.20922/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":"2026-07-24T01:23:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FLGwns3znoyNXclEKDTYe9QNGzWcdLetWWFNw1SohTjCTqrfuhUNr4fNDFUN+DqEG1nAj+kahFziJPcoawVwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T14:29:04.648876Z"},"content_sha256":"b4a362b253fe06288d00f2a1c3edcdf9ccdf26606511c85a27535e35043d354e","schema_version":"1.0","event_id":"sha256:b4a362b253fe06288d00f2a1c3edcdf9ccdf26606511c85a27535e35043d354e"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:Q7V7KV3TP2B2DWAVEZ65L2OXLC","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/iccv.2017.116) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Adrian Bulat and Georgios Tzimiropoulos. How far are we from solving the 2d & 3d face alignment problem? (and a dataset of 230,000 3d facial landmarks). In2017 IEEE International Conference on Computer Vision (ICCV), pages 1021–1030, 2017. ","arxiv_id":"2607.20922","detector":"doi_compliance","evidence":{"ref_index":58,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1109/iccv","reconstructed_doi":"10.1109/iccv.2017.116"},"severity":"advisory","ref_index":58,"audited_at":"2026-08-01T09:08:44.291565Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/iccv.2017.116","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"71f286107ba2577f8c9ce20d3a37244a6f023afb64786d1eb237e7478a3474cb","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":15527,"payload_sha256":"36c461667ef0341887535a95e12e2743fba3d57eaa2f6f681307ddca5c49a4ea","signature_b64":"XNC40WKJdje8EB9mrZpxb9xcrcs51w2xykn573JIUgltJKSH+/eHnTWObCXdjOjyWdqMLyWr9ihG8ZxM3wz5Bg==","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":"2026-08-01T09:13:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PTqKbfWLmOB3u87h+HDvIXFePpz7ghXzZXy/uTOOMnm4rfztmgU/qVUTKE8jZrEJ64MJL/hHbBFzYRXyEEpJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T14:29:04.652891Z"},"content_sha256":"9d721b3506bf79d5e92b59039b35b98e7377a7923c6b99b12f704d1c9c9c61c1","schema_version":"1.0","event_id":"sha256:9d721b3506bf79d5e92b59039b35b98e7377a7923c6b99b12f704d1c9c9c61c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q7V7KV3TP2B2DWAVEZ65L2OXLC/bundle.json","state_url":"https://pith.science/pith/Q7V7KV3TP2B2DWAVEZ65L2OXLC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q7V7KV3TP2B2DWAVEZ65L2OXLC/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":"2026-08-02T14:29:04Z","links":{"resolver":"https://pith.science/pith/Q7V7KV3TP2B2DWAVEZ65L2OXLC","bundle":"https://pith.science/pith/Q7V7KV3TP2B2DWAVEZ65L2OXLC/bundle.json","state":"https://pith.science/pith/Q7V7KV3TP2B2DWAVEZ65L2OXLC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q7V7KV3TP2B2DWAVEZ65L2OXLC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q7V7KV3TP2B2DWAVEZ65L2OXLC","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0031067be5ce02481faa90b5f5f5a02c7b6ced90de22de03b9df785553a3b90b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T04:57:22Z","title_canon_sha256":"f39aa4df987e84225c0daaba47939cf3ff58380ad24ef46ffdf38d6b4e5ba1c8"},"schema_version":"1.0","source":{"id":"2607.20922","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20922","created_at":"2026-07-24T01:23:40Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20922v1","created_at":"2026-07-24T01:23:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20922","created_at":"2026-07-24T01:23:40Z"},{"alias_kind":"pith_short_12","alias_value":"Q7V7KV3TP2B2","created_at":"2026-07-24T01:23:40Z"},{"alias_kind":"pith_short_16","alias_value":"Q7V7KV3TP2B2DWAV","created_at":"2026-07-24T01:23:40Z"},{"alias_kind":"pith_short_8","alias_value":"Q7V7KV3T","created_at":"2026-07-24T01:23:40Z"}],"graph_snapshots":[{"event_id":"sha256:b4a362b253fe06288d00f2a1c3edcdf9ccdf26606511c85a27535e35043d354e","target":"graph","created_at":"2026-07-24T01:23:40Z","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/2607.20922/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose FA-LAM, a Focus-Aware Large Avatar Model for one-shot animatable Gaussian head creation, while simultaneously enabling static 3D and dynamic 4D full-head recovery. The core of our method lies in a thorough analysis of the attention mechanisms and the entangled reconstruction and animation training pipeline adopted by prior state-of-the-art approaches. Our analysis identifies two main factors that compromise the quality of 3D full-head generation: (1) incorrect and noisy attention activations, and (2) conflicts between the tasks of reconstruction and animation. To address the first i","authors_text":"Jun Zhang, Steven Hoi, Yiming Jiang, Yingdong Hu, Yisheng He, Zehong Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T04:57:22Z","title":"FA-LAM: Focus-Aware Large Avatar Model for One-Shot 4D Animatable Gaussian Head"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20922","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":"sha256:8f9a3b0629234e6487e9fdf406c30b26023bfd601676561bb004ee110ae3bbd0","target":"record","created_at":"2026-07-24T01:23:40Z","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":"0031067be5ce02481faa90b5f5f5a02c7b6ced90de22de03b9df785553a3b90b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T04:57:22Z","title_canon_sha256":"f39aa4df987e84225c0daaba47939cf3ff58380ad24ef46ffdf38d6b4e5ba1c8"},"schema_version":"1.0","source":{"id":"2607.20922","kind":"arxiv","version":1}},"canonical_sha256":"87ebf557737e83a1d815267dd5e9d75882411d4a2e698cdc960ea45adf938113","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87ebf557737e83a1d815267dd5e9d75882411d4a2e698cdc960ea45adf938113","first_computed_at":"2026-07-24T01:23:40.876498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T01:23:40.876498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BOvKC4wo76znedy0usr8iV6+yOzS8qVQ4CecWfMeuGt+gqRlP19RxGIobhaRiCMBP/q4CAvtQ4CL86rFh4j3BQ==","signature_status":"signed_v1","signed_at":"2026-07-24T01:23:40.877469Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.20922","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f9a3b0629234e6487e9fdf406c30b26023bfd601676561bb004ee110ae3bbd0","sha256:b4a362b253fe06288d00f2a1c3edcdf9ccdf26606511c85a27535e35043d354e","sha256:9d721b3506bf79d5e92b59039b35b98e7377a7923c6b99b12f704d1c9c9c61c1"],"state_sha256":"676f8a631a609b619be8da4cd7da61012bab71b31c82779f84ff872bad80c78c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eHVr3q37VuXE/GdhmS7LtgE7Zr46gNvAiI8JflL2TLRa6vjv5CxQ5d/0D7Mydq+uGFQKVUkFm9hNuqLwCJV2Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T14:29:04.655377Z","bundle_sha256":"d466af1e16b0aaa3ad1a476354f7da3c3b6b50e8ab83f75bc4388a5abe6f358d"}}