{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EOL5K3N543O3MVEIUFU7NFYCLC","short_pith_number":"pith:EOL5K3N5","canonical_record":{"source":{"id":"2608.08147","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-08-08T14:11:56Z","cross_cats_sorted":[],"title_canon_sha256":"3cc2ce7e08c98d8e8eedda968d8d6b3a20362c06126ab0ee863488ea555c55ae","abstract_canon_sha256":"146f7386d3ca1d95984521b55c9d799e8b017732bd776a6bbf73c49c0de921e7"},"schema_version":"1.0"},"canonical_sha256":"2397d56dbde6ddb65488a169f6970258bea6d73a6b2449f780e0a0430fdb816b","source":{"kind":"arxiv","id":"2608.08147","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08147","created_at":"2026-08-11T01:21:49Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08147v1","created_at":"2026-08-11T01:21:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08147","created_at":"2026-08-11T01:21:49Z"},{"alias_kind":"pith_short_12","alias_value":"EOL5K3N543O3","created_at":"2026-08-11T01:21:49Z"},{"alias_kind":"pith_short_16","alias_value":"EOL5K3N543O3MVEI","created_at":"2026-08-11T01:21:49Z"},{"alias_kind":"pith_short_8","alias_value":"EOL5K3N5","created_at":"2026-08-11T01:21:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EOL5K3N543O3MVEIUFU7NFYCLC","target":"record","payload":{"canonical_record":{"source":{"id":"2608.08147","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-08-08T14:11:56Z","cross_cats_sorted":[],"title_canon_sha256":"3cc2ce7e08c98d8e8eedda968d8d6b3a20362c06126ab0ee863488ea555c55ae","abstract_canon_sha256":"146f7386d3ca1d95984521b55c9d799e8b017732bd776a6bbf73c49c0de921e7"},"schema_version":"1.0"},"canonical_sha256":"2397d56dbde6ddb65488a169f6970258bea6d73a6b2449f780e0a0430fdb816b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:21:49.332516Z","signature_b64":"QkAosXa03ZiXOlnQJxhKVhnr1NulTMOGFz0pMootYzj0C21Z+Fej1wQgd51eRwJpxZ6F/h6xbweO3fuTebemAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2397d56dbde6ddb65488a169f6970258bea6d73a6b2449f780e0a0430fdb816b","last_reissued_at":"2026-08-11T01:21:49.330169Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:21:49.330169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.08147","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":"2026-08-11T01:21:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9NgxWpbNs73kstbU4/xBzISJb3Ko5n0JdCvFwYscYs0U8JlvQkOGK6VquXhRrui1BqLuWvCUQ4z0/x5LKGrPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T06:01:31.910178Z"},"content_sha256":"a9547002082fe71525b9aac20d0b394c48defbc9dfe0de99bfd3c2dd0db5c7c1","schema_version":"1.0","event_id":"sha256:a9547002082fe71525b9aac20d0b394c48defbc9dfe0de99bfd3c2dd0db5c7c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EOL5K3N543O3MVEIUFU7NFYCLC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SAMOT: State-Aware Step Modulation and Optimal Transport Matching for Audio-Visual Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Huchuan Lu, Jingjing Li, Kai Peng, Leiye Liu, Miao Zhang, Wei Ji, Yongri Piao, Yunzhe Shen","submitted_at":"2026-08-08T14:11:56Z","abstract_excerpt":"Audio-Visual Instance Segmentation (AVIS) aims to simultaneously classify, segment, and track sounding objects within video sequences. Unlike Audio-Visual Semantic Segmentation (AVS), AVIS involves instance-level modeling across longer video sequences, introducing two key challenges: (1) complex modality-state changes disrupt long-range modeling, and (2) substantial structural and distributional discrepancies between modalities hinder precise instance-level association. Existing methods rely on fixed-step Transformers and recursive Mamba models, lacking adaptability to modality-state changes. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08147","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/2608.08147/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":"2026-08-11T01:21:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n4uuB8gueIPwFkoU29j0xf2/fRujF5JC6ipTQP2p18rCBbC0ZW6/5QeuruteCxyHd0Z1ALMBd8Pjn4CzXhlDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T06:01:31.910685Z"},"content_sha256":"45af933699e7cd4a801cc51512fcb5a0b09f73835f0aa1edde4b66e64adaa477","schema_version":"1.0","event_id":"sha256:45af933699e7cd4a801cc51512fcb5a0b09f73835f0aa1edde4b66e64adaa477"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EOL5K3N543O3MVEIUFU7NFYCLC/bundle.json","state_url":"https://pith.science/pith/EOL5K3N543O3MVEIUFU7NFYCLC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EOL5K3N543O3MVEIUFU7NFYCLC/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":"2026-08-19T06:01:31Z","links":{"resolver":"https://pith.science/pith/EOL5K3N543O3MVEIUFU7NFYCLC","bundle":"https://pith.science/pith/EOL5K3N543O3MVEIUFU7NFYCLC/bundle.json","state":"https://pith.science/pith/EOL5K3N543O3MVEIUFU7NFYCLC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EOL5K3N543O3MVEIUFU7NFYCLC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EOL5K3N543O3MVEIUFU7NFYCLC","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":"146f7386d3ca1d95984521b55c9d799e8b017732bd776a6bbf73c49c0de921e7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-08-08T14:11:56Z","title_canon_sha256":"3cc2ce7e08c98d8e8eedda968d8d6b3a20362c06126ab0ee863488ea555c55ae"},"schema_version":"1.0","source":{"id":"2608.08147","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08147","created_at":"2026-08-11T01:21:49Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08147v1","created_at":"2026-08-11T01:21:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08147","created_at":"2026-08-11T01:21:49Z"},{"alias_kind":"pith_short_12","alias_value":"EOL5K3N543O3","created_at":"2026-08-11T01:21:49Z"},{"alias_kind":"pith_short_16","alias_value":"EOL5K3N543O3MVEI","created_at":"2026-08-11T01:21:49Z"},{"alias_kind":"pith_short_8","alias_value":"EOL5K3N5","created_at":"2026-08-11T01:21:49Z"}],"graph_snapshots":[{"event_id":"sha256:45af933699e7cd4a801cc51512fcb5a0b09f73835f0aa1edde4b66e64adaa477","target":"graph","created_at":"2026-08-11T01:21:49Z","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/2608.08147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Instance Segmentation (AVIS) aims to simultaneously classify, segment, and track sounding objects within video sequences. Unlike Audio-Visual Semantic Segmentation (AVS), AVIS involves instance-level modeling across longer video sequences, introducing two key challenges: (1) complex modality-state changes disrupt long-range modeling, and (2) substantial structural and distributional discrepancies between modalities hinder precise instance-level association. Existing methods rely on fixed-step Transformers and recursive Mamba models, lacking adaptability to modality-state changes. ","authors_text":"Huchuan Lu, Jingjing Li, Kai Peng, Leiye Liu, Miao Zhang, Wei Ji, Yongri Piao, Yunzhe Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-08-08T14:11:56Z","title":"SAMOT: State-Aware Step Modulation and Optimal Transport Matching for Audio-Visual Instance Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08147","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:a9547002082fe71525b9aac20d0b394c48defbc9dfe0de99bfd3c2dd0db5c7c1","target":"record","created_at":"2026-08-11T01:21:49Z","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":"146f7386d3ca1d95984521b55c9d799e8b017732bd776a6bbf73c49c0de921e7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-08-08T14:11:56Z","title_canon_sha256":"3cc2ce7e08c98d8e8eedda968d8d6b3a20362c06126ab0ee863488ea555c55ae"},"schema_version":"1.0","source":{"id":"2608.08147","kind":"arxiv","version":1}},"canonical_sha256":"2397d56dbde6ddb65488a169f6970258bea6d73a6b2449f780e0a0430fdb816b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2397d56dbde6ddb65488a169f6970258bea6d73a6b2449f780e0a0430fdb816b","first_computed_at":"2026-08-11T01:21:49.330169Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:21:49.330169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QkAosXa03ZiXOlnQJxhKVhnr1NulTMOGFz0pMootYzj0C21Z+Fej1wQgd51eRwJpxZ6F/h6xbweO3fuTebemAA==","signature_status":"signed_v1","signed_at":"2026-08-11T01:21:49.332516Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08147","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9547002082fe71525b9aac20d0b394c48defbc9dfe0de99bfd3c2dd0db5c7c1","sha256:45af933699e7cd4a801cc51512fcb5a0b09f73835f0aa1edde4b66e64adaa477"],"state_sha256":"bfd9e8223e84af2d2d03922473ec6c38b11defece012c2a2602a9b427abc0012"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JlBP5ZfPyXlCltdjAT9BpiZs2ByY17yYJvWe1LiND5LSW3XNBVS02X9s8dlvXPqiH8kAsgPxVVVxuQpGumJEDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T06:01:31.914966Z","bundle_sha256":"25803e0766f51d3a2c8a3e4f5dd871e2d4119f4524656c1071ae703f75089c02"}}